ton/YiemAgent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
narawat lamaiin
2024-12-09 20:48:45 +07:00
parent 4f1280daa3
commit 9aef993813
47 changed files with 16623 additions and 12554 deletions
Download Patch File Download Diff File Expand all files Collapse all files

187
Manifest.toml
View File

@@ -1,8 +1,8 @@
# This file is machine-generated - editing it directly is not advised
julia_version = "1.10.5"
julia_version = "1.11.2"
manifest_format = "2.0"
project_hash = "bf6c32becbc917fa1c33558e7aa59c1aac5237e3"
project_hash = "3fbf548b167fd8368831ce3bd276589c6cddf72e"
[[deps.AliasTables]]
deps = ["PtrArrays", "Random"]
@@ -12,13 +12,15 @@ version = "1.1.3"
[[deps.ArgTools]]
uuid = "0dad84c5-d112-42e6-8d28-ef12dabb789f"
version = "1.1.1"
version = "1.1.2"
[[deps.Artifacts]]
uuid = "56f22d72-fd6d-98f1-02f0-08ddc0907c33"
version = "1.11.0"
[[deps.Base64]]
uuid = "2a0f44e3-6c83-55bd-87e4-b1978d98bd5f"
version = "1.11.0"
[[deps.BitFlags]]
git-tree-sha1 = "0691e34b3bb8be9307330f88d1a3c3f25466c24d"
@@ -32,9 +34,9 @@ version = "0.5.0"
[[deps.CSV]]
deps = ["CodecZlib", "Dates", "FilePathsBase", "InlineStrings", "Mmap", "Parsers", "PooledArrays", "PrecompileTools", "SentinelArrays", "Tables", "Unicode", "WeakRefStrings", "WorkerUtilities"]
git-tree-sha1 = "6c834533dc1fabd820c1db03c839bf97e45a3fab"
git-tree-sha1 = "deddd8725e5e1cc49ee205a1964256043720a6c3"
uuid = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
version = "0.10.14"
version = "0.10.15"
[[deps.CodeTracking]]
deps = ["InteractiveUtils", "UUIDs"]
@@ -69,12 +71,6 @@ git-tree-sha1 = "ea32b83ca4fefa1768dc84e504cc0a94fb1ab8d1"
uuid = "f0e56b4a-5159-44fe-b623-3e5288b988bb"
version = "2.4.2"
[[deps.CondaPkg]]
deps = ["JSON3", "Markdown", "MicroMamba", "Pidfile", "Pkg", "Preferences", "TOML"]
git-tree-sha1 = "8f7faef2ca039ee068cd971a80ccd710d23fb2eb"
uuid = "992eb4ea-22a4-4c89-a5bb-47a3300528ab"
version = "0.2.23"
[[deps.Crayons]]
git-tree-sha1 = "249fe38abf76d48563e2f4556bebd215aa317e15"
uuid = "a8cc5b0e-0ffa-5ad4-8c14-923d3ee1735f"
@@ -110,6 +106,7 @@ version = "1.0.0"
[[deps.Dates]]
deps = ["Printf"]
uuid = "ade2ca70-3891-5945-98fb-dc099432e06a"
version = "1.11.0"
[[deps.Decimals]]
git-tree-sha1 = "e98abef36d02a0ec385d68cd7dadbce9b28cbd88"
@@ -119,12 +116,13 @@ version = "0.4.1"
[[deps.Distributed]]
deps = ["Random", "Serialization", "Sockets"]
uuid = "8ba89e20-285c-5b6f-9357-94700520ee1b"
version = "1.11.0"
[[deps.Distributions]]
deps = ["AliasTables", "FillArrays", "LinearAlgebra", "PDMats", "Printf", "QuadGK", "Random", "SpecialFunctions", "Statistics", "StatsAPI", "StatsBase", "StatsFuns"]
git-tree-sha1 = "d7477ecdafb813ddee2ae727afa94e9dcb5f3fb0"
git-tree-sha1 = "3101c32aab536e7a27b1763c0797dba151b899ad"
uuid = "31c24e10-a181-5473-b8eb-7969acd0382f"
version = "0.25.112"
version = "0.25.113"
[deps.Distributions.extensions]
DistributionsChainRulesCoreExt = "ChainRulesCore"
@@ -149,21 +147,15 @@ version = "1.6.0"
[[deps.ExceptionUnwrapping]]
deps = ["Test"]
git-tree-sha1 = "dcb08a0d93ec0b1cdc4af184b26b591e9695423a"
git-tree-sha1 = "d36f682e590a83d63d1c7dbd287573764682d12a"
uuid = "460bff9d-24e4-43bc-9d9f-a8973cb893f4"
version = "0.1.10"
version = "0.1.11"
[[deps.ExprTools]]
git-tree-sha1 = "27415f162e6028e81c72b82ef756bf321213b6ec"
uuid = "e2ba6199-217a-4e67-a87a-7c52f15ade04"
version = "0.1.10"
[[deps.FileIO]]
deps = ["Pkg", "Requires", "UUIDs"]
git-tree-sha1 = "62ca0547a14c57e98154423419d8a342dca75ca9"
uuid = "5789e2e9-d7fb-5bc7-8068-2c6fae9b9549"
version = "1.16.4"
[[deps.FilePathsBase]]
deps = ["Compat", "Dates"]
git-tree-sha1 = "7878ff7172a8e6beedd1dea14bd27c3c6340d361"
@@ -177,6 +169,7 @@ weakdeps = ["Mmap", "Test"]
[[deps.FileWatching]]
uuid = "7b1f6079-737a-58dc-b8bc-7a2ca5c1b5ee"
version = "1.11.0"
[[deps.FillArrays]]
deps = ["LinearAlgebra"]
@@ -193,24 +186,27 @@ weakdeps = ["PDMats", "SparseArrays", "Statistics"]
[[deps.Future]]
deps = ["Random"]
uuid = "9fa8497b-333b-5362-9e8d-4d0656e87820"
version = "1.11.0"
[[deps.GeneralUtils]]
deps = ["CSV", "DataFrames", "DataStructures", "Dates", "Distributions", "JSON3", "MQTTClient", "PrettyPrinting", "Random", "SHA", "UUIDs"]
path = "/appfolder/app/privatejuliapkg/GeneralUtils"
git-tree-sha1 = "978d9a5c3fc30205dd72d4a2a2ed4fa85ebee5cf"
repo-rev = "main"
repo-url = "https://git.yiem.cc/ton/GeneralUtils"
uuid = "c6c72f09-b708-4ac8-ac7c-2084d70108fe"
version = "0.1.0"
[[deps.HTTP]]
deps = ["Base64", "CodecZlib", "ConcurrentUtilities", "Dates", "ExceptionUnwrapping", "Logging", "LoggingExtras", "MbedTLS", "NetworkOptions", "OpenSSL", "Random", "SimpleBufferStream", "Sockets", "URIs", "UUIDs"]
git-tree-sha1 = "d1d712be3164d61d1fb98e7ce9bcbc6cc06b45ed"
deps = ["Base64", "CodecZlib", "ConcurrentUtilities", "Dates", "ExceptionUnwrapping", "Logging", "LoggingExtras", "MbedTLS", "NetworkOptions", "OpenSSL", "PrecompileTools", "Random", "SimpleBufferStream", "Sockets", "URIs", "UUIDs"]
git-tree-sha1 = "6c22309e9a356ac1ebc5c8a217045f9bae6f8d9a"
uuid = "cd3eb016-35fb-5094-929b-558a96fad6f3"
version = "1.10.8"
version = "1.10.13"
[[deps.HypergeometricFunctions]]
deps = ["LinearAlgebra", "OpenLibm_jll", "SpecialFunctions"]
git-tree-sha1 = "7c4195be1649ae622304031ed46a2f4df989f1eb"
git-tree-sha1 = "b1c2585431c382e3fe5805874bda6aea90a95de9"
uuid = "34004b35-14d8-5ef3-9330-4cdb6864b03a"
version = "0.3.24"
version = "0.3.25"
[[deps.ICU_jll]]
deps = ["Artifacts", "JLLWrappers", "Libdl", "Pkg"]
@@ -240,6 +236,7 @@ version = "1.4.2"
[[deps.InteractiveUtils]]
deps = ["Markdown"]
uuid = "b77e0a4c-d291-57a0-90e8-8db25a27a240"
version = "1.11.0"
[[deps.Intervals]]
deps = ["Dates", "Printf", "RecipesBase", "Serialization", "TimeZones"]
@@ -287,9 +284,9 @@ version = "1.14.1"
[[deps.JuliaInterpreter]]
deps = ["CodeTracking", "InteractiveUtils", "Random", "UUIDs"]
git-tree-sha1 = "2984284a8abcfcc4784d95a9e2ea4e352dd8ede7"
git-tree-sha1 = "10da5154188682e5c0726823c2b5125957ec3778"
uuid = "aa1ae85d-cabe-5617-a682-6adf51b2e16a"
version = "0.9.36"
version = "0.9.38"
[[deps.Kerberos_krb5_jll]]
deps = ["Artifacts", "JLLWrappers", "Libdl", "Pkg"]
@@ -297,12 +294,6 @@ git-tree-sha1 = "60274b4ab38e8d1248216fe6b6ace75ae09b0502"
uuid = "b39eb1a6-c29a-53d7-8c32-632cd16f18da"
version = "1.19.3+0"
[[deps.LLMMCTS]]
deps = ["GeneralUtils", "JSON3"]
path = "/appfolder/app/privatejuliapkg/LLMMCTS"
uuid = "d76c5a4d-449e-4835-8cc4-dd86ec44f241"
version = "0.1.0"
[[deps.LaTeXStrings]]
git-tree-sha1 = "dda21b8cbd6a6c40d9d02a73230f9d70fed6918c"
uuid = "b964fa9f-0449-5b57-a5c2-d3ea65f4040f"
@@ -313,10 +304,6 @@ git-tree-sha1 = "6087ad3521d6278ebe5c27ae55e7bbb15ca312cb"
uuid = "6f188dcb-512c-564b-bc01-e0f76e72f166"
version = "1.0.0"
[[deps.LazyArtifacts]]
deps = ["Artifacts", "Pkg"]
uuid = "4af54fe1-eca0-43a8-85a7-787d91b784e3"
[[deps.LibCURL]]
deps = ["LibCURL_jll", "MozillaCACerts_jll"]
uuid = "b27032c2-a3e7-50c8-80cd-2d36dbcbfd21"
@@ -325,16 +312,17 @@ version = "0.6.4"
[[deps.LibCURL_jll]]
deps = ["Artifacts", "LibSSH2_jll", "Libdl", "MbedTLS_jll", "Zlib_jll", "nghttp2_jll"]
uuid = "deac9b47-8bc7-5906-a0fe-35ac56dc84c0"
version = "8.4.0+0"
version = "8.6.0+0"
[[deps.LibGit2]]
deps = ["Base64", "LibGit2_jll", "NetworkOptions", "Printf", "SHA"]
uuid = "76f85450-5226-5b5a-8eaa-529ad045b433"
version = "1.11.0"
[[deps.LibGit2_jll]]
deps = ["Artifacts", "LibSSH2_jll", "Libdl", "MbedTLS_jll"]
uuid = "e37daf67-58a4-590a-8e99-b0245dd2ffc5"
version = "1.6.4+0"
version = "1.7.2+0"
[[deps.LibPQ]]
deps = ["CEnum", "DBInterface", "Dates", "Decimals", "DocStringExtensions", "FileWatching", "Infinity", "Intervals", "IterTools", "LayerDicts", "LibPQ_jll", "Libdl", "Memento", "OffsetArrays", "SQLStrings", "Tables", "TimeZones", "UTCDateTimes"]
@@ -355,10 +343,12 @@ version = "1.11.0+1"
[[deps.Libdl]]
uuid = "8f399da3-3557-5675-b5ff-fb832c97cbdb"
version = "1.11.0"
[[deps.LinearAlgebra]]
deps = ["Libdl", "OpenBLAS_jll", "libblastrampoline_jll"]
uuid = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
version = "1.11.0"
[[deps.LogExpFunctions]]
deps = ["DocStringExtensions", "IrrationalConstants", "LinearAlgebra"]
@@ -378,18 +368,19 @@ version = "0.3.28"
[[deps.Logging]]
uuid = "56ddb016-857b-54e1-b83d-db4d58db5568"
version = "1.11.0"
[[deps.LoggingExtras]]
deps = ["Dates", "Logging"]
git-tree-sha1 = "c1dd6d7978c12545b4179fb6153b9250c96b0075"
git-tree-sha1 = "f02b56007b064fbfddb4c9cd60161b6dd0f40df3"
uuid = "e6f89c97-d47a-5376-807f-9c37f3926c36"
version = "1.0.3"
version = "1.1.0"
[[deps.LoweredCodeUtils]]
deps = ["JuliaInterpreter"]
git-tree-sha1 = "260dc274c1bc2cb839e758588c63d9c8b5e639d1"
git-tree-sha1 = "688d6d9e098109051ae33d126fcfc88c4ce4a021"
uuid = "6f1432cf-f94c-5a45-995e-cdbf5db27b0b"
version = "3.0.5"
version = "3.1.0"
[[deps.MQTTClient]]
deps = ["Distributed", "Random", "Sockets"]
@@ -401,15 +392,10 @@ weakdeps = ["PrecompileTools"]
[deps.MQTTClient.extensions]
PrecompileMQTT = "PrecompileTools"
[[deps.MacroTools]]
deps = ["Markdown", "Random"]
git-tree-sha1 = "2fa9ee3e63fd3a4f7a9a4f4744a52f4856de82df"
uuid = "1914dd2f-81c6-5fcd-8719-6d5c9610ff09"
version = "0.5.13"
[[deps.Markdown]]
deps = ["Base64"]
uuid = "d6f4376e-aef5-505a-96c1-9c027394607a"
version = "1.11.0"
[[deps.MbedTLS]]
deps = ["Dates", "MbedTLS_jll", "MozillaCACerts_jll", "NetworkOptions", "Random", "Sockets"]
@@ -420,7 +406,7 @@ version = "1.1.9"
[[deps.MbedTLS_jll]]
deps = ["Artifacts", "Libdl"]
uuid = "c8ffd9c3-330d-5841-b78e-0817d7145fa1"
version = "2.28.2+1"
version = "2.28.6+0"
[[deps.Memento]]
deps = ["Dates", "Distributed", "Requires", "Serialization", "Sockets", "Test", "UUIDs"]
@@ -428,12 +414,6 @@ git-tree-sha1 = "bb2e8f4d9f400f6e90d57b34860f6abdc51398e5"
uuid = "f28f55f0-a522-5efc-85c2-fe41dfb9b2d9"
version = "1.4.1"
[[deps.MicroMamba]]
deps = ["Pkg", "Scratch", "micromamba_jll"]
git-tree-sha1 = "011cab361eae7bcd7d278f0a7a00ff9c69000c51"
uuid = "0b3b1443-0f03-428d-bdfb-f27f9c1191ea"
version = "0.1.14"
[[deps.Missings]]
deps = ["DataAPI"]
git-tree-sha1 = "ec4f7fbeab05d7747bdf98eb74d130a2a2ed298d"
@@ -442,6 +422,7 @@ version = "1.2.0"
[[deps.Mmap]]
uuid = "a63ad114-7e13-5084-954f-fe012c677804"
version = "1.11.0"
[[deps.Mocking]]
deps = ["Compat", "ExprTools"]
@@ -451,16 +432,16 @@ version = "0.8.1"
[[deps.MozillaCACerts_jll]]
uuid = "14a3606d-f60d-562e-9121-12d972cd8159"
version = "2023.1.10"
version = "2023.12.12"
[[deps.NetworkOptions]]
uuid = "ca575930-c2e3-43a9-ace4-1e988b2c1908"
version = "1.2.0"
[[deps.OffsetArrays]]
git-tree-sha1 = "1a27764e945a152f7ca7efa04de513d473e9542e"
git-tree-sha1 = "39d000d9c33706b8364817d8894fae1548f40295"
uuid = "6fe1bfb0-de20-5000-8ca7-80f57d26f881"
version = "1.14.1"
version = "1.14.2"
[deps.OffsetArrays.extensions]
OffsetArraysAdaptExt = "Adapt"
@@ -471,7 +452,7 @@ version = "1.14.1"
[[deps.OpenBLAS_jll]]
deps = ["Artifacts", "CompilerSupportLibraries_jll", "Libdl"]
uuid = "4536629a-c528-5b80-bd46-f80d51c5b363"
version = "0.3.23+4"
version = "0.3.27+1"
[[deps.OpenLibm_jll]]
deps = ["Artifacts", "Libdl"]
@@ -497,9 +478,9 @@ uuid = "efe28fd5-8261-553b-a9e1-b2916fc3738e"
version = "0.5.5+0"
[[deps.OrderedCollections]]
git-tree-sha1 = "dfdf5519f235516220579f949664f1bf44e741c5"
git-tree-sha1 = "12f1439c4f986bb868acda6ea33ebc78e19b95ad"
uuid = "bac558e1-5e72-5ebc-8fee-abe8a469f55d"
version = "1.6.3"
version = "1.7.0"
[[deps.PDMats]]
deps = ["LinearAlgebra", "SparseArrays", "SuiteSparse"]
@@ -513,16 +494,14 @@ git-tree-sha1 = "8489905bcdbcfac64d1daa51ca07c0d8f0283821"
uuid = "69de0a69-1ddd-5017-9359-2bf0b02dc9f0"
version = "2.8.1"
[[deps.Pidfile]]
deps = ["FileWatching", "Test"]
git-tree-sha1 = "2d8aaf8ee10df53d0dfb9b8ee44ae7c04ced2b03"
uuid = "fa939f87-e72e-5be4-a000-7fc836dbe307"
version = "1.3.0"
[[deps.Pkg]]
deps = ["Artifacts", "Dates", "Downloads", "FileWatching", "LibGit2", "Libdl", "Logging", "Markdown", "Printf", "REPL", "Random", "SHA", "Serialization", "TOML", "Tar", "UUIDs", "p7zip_jll"]
deps = ["Artifacts", "Dates", "Downloads", "FileWatching", "LibGit2", "Libdl", "Logging", "Markdown", "Printf", "Random", "SHA", "TOML", "Tar", "UUIDs", "p7zip_jll"]
uuid = "44cfe95a-1eb2-52ea-b672-e2afdf69b78f"
version = "1.10.0"
version = "1.11.0"
weakdeps = ["REPL"]
[deps.Pkg.extensions]
REPLExt = "REPL"
[[deps.PooledArrays]]
deps = ["DataAPI", "Future"]
@@ -556,18 +535,13 @@ version = "2.4.0"
[[deps.Printf]]
deps = ["Unicode"]
uuid = "de0858da-6303-5e67-8744-51eddeeeb8d7"
version = "1.11.0"
[[deps.PtrArrays]]
git-tree-sha1 = "77a42d78b6a92df47ab37e177b2deac405e1c88f"
uuid = "43287f4e-b6f4-7ad1-bb20-aadabca52c3d"
version = "1.2.1"
[[deps.PythonCall]]
deps = ["CondaPkg", "Dates", "Libdl", "MacroTools", "Markdown", "Pkg", "REPL", "Requires", "Serialization", "Tables", "UnsafePointers"]
git-tree-sha1 = "06a778ec6d6e76b0c2fb661436a18bce853ec45f"
uuid = "6099a3de-0909-46bc-b1f4-468b9a2dfc0d"
version = "0.9.23"
[[deps.QuadGK]]
deps = ["DataStructures", "LinearAlgebra"]
git-tree-sha1 = "cda3b045cf9ef07a08ad46731f5a3165e56cf3da"
@@ -581,12 +555,14 @@ version = "2.11.1"
Enzyme = "7da242da-08ed-463a-9acd-ee780be4f1d9"
[[deps.REPL]]
deps = ["InteractiveUtils", "Markdown", "Sockets", "Unicode"]
deps = ["InteractiveUtils", "Markdown", "Sockets", "StyledStrings", "Unicode"]
uuid = "3fa0cd96-eef1-5676-8a61-b3b8758bbffb"
version = "1.11.0"
[[deps.Random]]
deps = ["SHA"]
uuid = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
version = "1.11.0"
[[deps.RecipesBase]]
deps = ["PrecompileTools"]
@@ -607,9 +583,9 @@ version = "1.3.0"
[[deps.Revise]]
deps = ["CodeTracking", "Distributed", "FileWatching", "JuliaInterpreter", "LibGit2", "LoweredCodeUtils", "OrderedCollections", "REPL", "Requires", "UUIDs", "Unicode"]
git-tree-sha1 = "7f4228017b83c66bd6aa4fddeb170ce487e53bc7"
git-tree-sha1 = "470f48c9c4ea2170fd4d0f8eb5118327aada22f5"
uuid = "295af30f-e4ad-537b-8983-00126c2a3abe"
version = "3.6.2"
version = "3.6.4"
[[deps.Rmath]]
deps = ["Random", "Rmath_jll"]
@@ -627,12 +603,6 @@ version = "0.5.1+0"
uuid = "ea8e919c-243c-51af-8825-aaa63cd721ce"
version = "0.7.0"
[[deps.SQLLLM]]
deps = ["CSV", "CondaPkg", "DataFrames", "DataStructures", "Dates", "FileIO", "GeneralUtils", "HTTP", "JSON3", "LLMMCTS", "LibPQ", "MQTTClient", "PrettyPrinting", "PythonCall", "Random", "Revise", "StatsBase", "Tables", "URIs", "UUIDs"]
path = "/appfolder/app/privatejuliapkg/SQLLLM"
uuid = "2ebc79c7-cc10-4a3a-9665-d2e1d61e63d3"
version = "0.1.0"
[[deps.SQLStrings]]
git-tree-sha1 = "55de0530689832b1d3d43491ee6b67bd54d3323c"
uuid = "af517c2e-c243-48fa-aab8-efac3db270f5"
@@ -646,12 +616,13 @@ version = "1.2.1"
[[deps.SentinelArrays]]
deps = ["Dates", "Random"]
git-tree-sha1 = "ff11acffdb082493657550959d4feb4b6149e73a"
git-tree-sha1 = "d0553ce4031a081cc42387a9b9c8441b7d99f32d"
uuid = "91c51154-3ec4-41a3-a24f-3f23e20d615c"
version = "1.4.5"
version = "1.4.7"
[[deps.Serialization]]
uuid = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
version = "1.11.0"
[[deps.SimpleBufferStream]]
git-tree-sha1 = "f305871d2f381d21527c770d4788c06c097c9bc1"
@@ -660,6 +631,7 @@ version = "1.2.0"
[[deps.Sockets]]
uuid = "6462fe0b-24de-5631-8697-dd941f90decc"
version = "1.11.0"
[[deps.SortingAlgorithms]]
deps = ["DataStructures"]
@@ -670,7 +642,7 @@ version = "1.2.1"
[[deps.SparseArrays]]
deps = ["Libdl", "LinearAlgebra", "Random", "Serialization", "SuiteSparse_jll"]
uuid = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"
version = "1.10.0"
version = "1.11.0"
[[deps.SpecialFunctions]]
deps = ["IrrationalConstants", "LogExpFunctions", "OpenLibm_jll", "OpenSpecFun_jll"]
@@ -685,9 +657,14 @@ version = "2.4.0"
ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
[[deps.Statistics]]
deps = ["LinearAlgebra", "SparseArrays"]
deps = ["LinearAlgebra"]
git-tree-sha1 = "ae3bb1eb3bba077cd276bc5cfc337cc65c3075c0"
uuid = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
version = "1.10.0"
version = "1.11.1"
weakdeps = ["SparseArrays"]
[deps.Statistics.extensions]
SparseArraysExt = ["SparseArrays"]
[[deps.StatsAPI]]
deps = ["LinearAlgebra"]
@@ -727,6 +704,10 @@ git-tree-sha1 = "159331b30e94d7b11379037feeb9b690950cace8"
uuid = "856f2bd8-1eba-4b0a-8007-ebc267875bd4"
version = "1.11.0"
[[deps.StyledStrings]]
uuid = "f489334b-da3d-4c2e-b8f0-e476e12c162b"
version = "1.11.0"
[[deps.SuiteSparse]]
deps = ["Libdl", "LinearAlgebra", "Serialization", "SparseArrays"]
uuid = "4607b0f0-06f3-5cda-b6b1-a6196a1729e9"
@@ -734,7 +715,7 @@ uuid = "4607b0f0-06f3-5cda-b6b1-a6196a1729e9"
[[deps.SuiteSparse_jll]]
deps = ["Artifacts", "Libdl", "libblastrampoline_jll"]
uuid = "bea87d4a-7f5b-5778-9afe-8cc45184846c"
version = "7.2.1+1"
version = "7.7.0+0"
[[deps.TOML]]
deps = ["Dates"]
@@ -767,12 +748,13 @@ version = "1.10.0"
[[deps.Test]]
deps = ["InteractiveUtils", "Logging", "Random", "Serialization"]
uuid = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
version = "1.11.0"
[[deps.TimeZones]]
deps = ["Dates", "Downloads", "InlineStrings", "Mocking", "Printf", "Scratch", "TZJData", "Unicode", "p7zip_jll"]
git-tree-sha1 = "8323074bc977aa85cf5ad71099a83ac75b0ac107"
git-tree-sha1 = "33c771f2157712ff4c85931186a4984efbe58934"
uuid = "f269a46b-ccf7-5d73-abea-4c690281aa53"
version = "1.18.1"
version = "1.19.0"
weakdeps = ["RecipesBase"]
[deps.TimeZones.extensions]
@@ -797,14 +779,11 @@ version = "1.6.1"
[[deps.UUIDs]]
deps = ["Random", "SHA"]
uuid = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
version = "1.11.0"
[[deps.Unicode]]
uuid = "4ec0a83e-493e-50e2-b9ac-8f72acf5a8f5"
[[deps.UnsafePointers]]
git-tree-sha1 = "c81331b3b2e60a982be57c046ec91f599ede674a"
uuid = "e17b2a0c-0bdf-430a-bd0c-3a23cae4ff39"
version = "1.0.0"
version = "1.11.0"
[[deps.WeakRefStrings]]
deps = ["DataAPI", "InlineStrings", "Parsers"]
@@ -833,16 +812,10 @@ deps = ["Artifacts", "Libdl"]
uuid = "8e850b90-86db-534c-a0d3-1478176c7d93"
version = "5.11.0+0"
[[deps.micromamba_jll]]
deps = ["Artifacts", "JLLWrappers", "LazyArtifacts", "Libdl"]
git-tree-sha1 = "b4a5a3943078f9fd11ae0b5ab1bdbf7718617945"
uuid = "f8abcde7-e9b7-5caa-b8af-a437887ae8e4"
version = "1.5.8+0"
[[deps.nghttp2_jll]]
deps = ["Artifacts", "Libdl"]
uuid = "8e850ede-7688-5339-a07c-302acd2aaf8d"
version = "1.52.0+1"
version = "1.59.0+0"
[[deps.p7zip_jll]]
deps = ["Artifacts", "Libdl"]

7
Project.toml
View File

@@ -4,20 +4,19 @@ authors = ["narawat lamaiin <narawat@outlook.com>"]
version = "0.1.0"
[deps]
CondaPkg = "992eb4ea-22a4-4c89-a5bb-47a3300528ab"
DataStructures = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
Dates = "ade2ca70-3891-5945-98fb-dc099432e06a"
GeneralUtils = "c6c72f09-b708-4ac8-ac7c-2084d70108fe"
HTTP = "cd3eb016-35fb-5094-929b-558a96fad6f3"
JSON3 = "0f8b85d8-7281-11e9-16c2-39a750bddbf1"
LLMMCTS = "d76c5a4d-449e-4835-8cc4-dd86ec44f241"
LibPQ = "194296ae-ab2e-5f79-8cd4-7183a0a5a0d1"
MQTTClient = "985f35cc-2c3d-4943-b8c1-f0931d5f0959"
PrettyPrinting = "54e16d92-306c-5ea0-a30b-337be88ac337"
PythonCall = "6099a3de-0909-46bc-b1f4-468b9a2dfc0d"
Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
Revise = "295af30f-e4ad-537b-8983-00126c2a3abe"
SQLLLM = "2ebc79c7-cc10-4a3a-9665-d2e1d61e63d3"
Serialization = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
URIs = "5c2747f8-b7ea-4ff2-ba2e-563bfd36b1d4"
UUIDs = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
[compat]
GeneralUtils = "0.1.0"

850
previousversion/0.2/Manifest.toml Normal file
View File

@@ -0,0 +1,850 @@
# This file is machine-generated - editing it directly is not advised
julia_version = "1.10.5"
manifest_format = "2.0"
project_hash = "bf6c32becbc917fa1c33558e7aa59c1aac5237e3"
[[deps.AliasTables]]
deps = ["PtrArrays", "Random"]
git-tree-sha1 = "9876e1e164b144ca45e9e3198d0b689cadfed9ff"
uuid = "66dad0bd-aa9a-41b7-9441-69ab47430ed8"
version = "1.1.3"
[[deps.ArgTools]]
uuid = "0dad84c5-d112-42e6-8d28-ef12dabb789f"
version = "1.1.1"
[[deps.Artifacts]]
uuid = "56f22d72-fd6d-98f1-02f0-08ddc0907c33"
[[deps.Base64]]
uuid = "2a0f44e3-6c83-55bd-87e4-b1978d98bd5f"
[[deps.BitFlags]]
git-tree-sha1 = "0691e34b3bb8be9307330f88d1a3c3f25466c24d"
uuid = "d1d4a3ce-64b1-5f1a-9ba4-7e7e69966f35"
version = "0.1.9"
[[deps.CEnum]]
git-tree-sha1 = "389ad5c84de1ae7cf0e28e381131c98ea87d54fc"
uuid = "fa961155-64e5-5f13-b03f-caf6b980ea82"
version = "0.5.0"
[[deps.CSV]]
deps = ["CodecZlib", "Dates", "FilePathsBase", "InlineStrings", "Mmap", "Parsers", "PooledArrays", "PrecompileTools", "SentinelArrays", "Tables", "Unicode", "WeakRefStrings", "WorkerUtilities"]
git-tree-sha1 = "6c834533dc1fabd820c1db03c839bf97e45a3fab"
uuid = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
version = "0.10.14"
[[deps.CodeTracking]]
deps = ["InteractiveUtils", "UUIDs"]
git-tree-sha1 = "7eee164f122511d3e4e1ebadb7956939ea7e1c77"
uuid = "da1fd8a2-8d9e-5ec2-8556-3022fb5608a2"
version = "1.3.6"
[[deps.CodecZlib]]
deps = ["TranscodingStreams", "Zlib_jll"]
git-tree-sha1 = "bce6804e5e6044c6daab27bb533d1295e4a2e759"
uuid = "944b1d66-785c-5afd-91f1-9de20f533193"
version = "0.7.6"
[[deps.Compat]]
deps = ["TOML", "UUIDs"]
git-tree-sha1 = "8ae8d32e09f0dcf42a36b90d4e17f5dd2e4c4215"
uuid = "34da2185-b29b-5c13-b0c7-acf172513d20"
version = "4.16.0"
weakdeps = ["Dates", "LinearAlgebra"]
[deps.Compat.extensions]
CompatLinearAlgebraExt = "LinearAlgebra"
[[deps.CompilerSupportLibraries_jll]]
deps = ["Artifacts", "Libdl"]
uuid = "e66e0078-7015-5450-92f7-15fbd957f2ae"
version = "1.1.1+0"
[[deps.ConcurrentUtilities]]
deps = ["Serialization", "Sockets"]
git-tree-sha1 = "ea32b83ca4fefa1768dc84e504cc0a94fb1ab8d1"
uuid = "f0e56b4a-5159-44fe-b623-3e5288b988bb"
version = "2.4.2"
[[deps.CondaPkg]]
deps = ["JSON3", "Markdown", "MicroMamba", "Pidfile", "Pkg", "Preferences", "TOML"]
git-tree-sha1 = "8f7faef2ca039ee068cd971a80ccd710d23fb2eb"
uuid = "992eb4ea-22a4-4c89-a5bb-47a3300528ab"
version = "0.2.23"
[[deps.Crayons]]
git-tree-sha1 = "249fe38abf76d48563e2f4556bebd215aa317e15"
uuid = "a8cc5b0e-0ffa-5ad4-8c14-923d3ee1735f"
version = "4.1.1"
[[deps.DBInterface]]
git-tree-sha1 = "a444404b3f94deaa43ca2a58e18153a82695282b"
uuid = "a10d1c49-ce27-4219-8d33-6db1a4562965"
version = "2.6.1"
[[deps.DataAPI]]
git-tree-sha1 = "abe83f3a2f1b857aac70ef8b269080af17764bbe"
uuid = "9a962f9c-6df0-11e9-0e5d-c546b8b5ee8a"
version = "1.16.0"
[[deps.DataFrames]]
deps = ["Compat", "DataAPI", "DataStructures", "Future", "InlineStrings", "InvertedIndices", "IteratorInterfaceExtensions", "LinearAlgebra", "Markdown", "Missings", "PooledArrays", "PrecompileTools", "PrettyTables", "Printf", "Random", "Reexport", "SentinelArrays", "SortingAlgorithms", "Statistics", "TableTraits", "Tables", "Unicode"]
git-tree-sha1 = "fb61b4812c49343d7ef0b533ba982c46021938a6"
uuid = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
version = "1.7.0"
[[deps.DataStructures]]
deps = ["Compat", "InteractiveUtils", "OrderedCollections"]
git-tree-sha1 = "1d0a14036acb104d9e89698bd408f63ab58cdc82"
uuid = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
version = "0.18.20"
[[deps.DataValueInterfaces]]
git-tree-sha1 = "bfc1187b79289637fa0ef6d4436ebdfe6905cbd6"
uuid = "e2d170a0-9d28-54be-80f0-106bbe20a464"
version = "1.0.0"
[[deps.Dates]]
deps = ["Printf"]
uuid = "ade2ca70-3891-5945-98fb-dc099432e06a"
[[deps.Decimals]]
git-tree-sha1 = "e98abef36d02a0ec385d68cd7dadbce9b28cbd88"
uuid = "abce61dc-4473-55a0-ba07-351d65e31d42"
version = "0.4.1"
[[deps.Distributed]]
deps = ["Random", "Serialization", "Sockets"]
uuid = "8ba89e20-285c-5b6f-9357-94700520ee1b"
[[deps.Distributions]]
deps = ["AliasTables", "FillArrays", "LinearAlgebra", "PDMats", "Printf", "QuadGK", "Random", "SpecialFunctions", "Statistics", "StatsAPI", "StatsBase", "StatsFuns"]
git-tree-sha1 = "d7477ecdafb813ddee2ae727afa94e9dcb5f3fb0"
uuid = "31c24e10-a181-5473-b8eb-7969acd0382f"
version = "0.25.112"
[deps.Distributions.extensions]
DistributionsChainRulesCoreExt = "ChainRulesCore"
DistributionsDensityInterfaceExt = "DensityInterface"
DistributionsTestExt = "Test"
[deps.Distributions.weakdeps]
ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
DensityInterface = "b429d917-457f-4dbc-8f4c-0cc954292b1d"
Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
[[deps.DocStringExtensions]]
deps = ["LibGit2"]
git-tree-sha1 = "2fb1e02f2b635d0845df5d7c167fec4dd739b00d"
uuid = "ffbed154-4ef7-542d-bbb7-c09d3a79fcae"
version = "0.9.3"
[[deps.Downloads]]
deps = ["ArgTools", "FileWatching", "LibCURL", "NetworkOptions"]
uuid = "f43a241f-c20a-4ad4-852c-f6b1247861c6"
version = "1.6.0"
[[deps.ExceptionUnwrapping]]
deps = ["Test"]
git-tree-sha1 = "dcb08a0d93ec0b1cdc4af184b26b591e9695423a"
uuid = "460bff9d-24e4-43bc-9d9f-a8973cb893f4"
version = "0.1.10"
[[deps.ExprTools]]
git-tree-sha1 = "27415f162e6028e81c72b82ef756bf321213b6ec"
uuid = "e2ba6199-217a-4e67-a87a-7c52f15ade04"
version = "0.1.10"
[[deps.FileIO]]
deps = ["Pkg", "Requires", "UUIDs"]
git-tree-sha1 = "62ca0547a14c57e98154423419d8a342dca75ca9"
uuid = "5789e2e9-d7fb-5bc7-8068-2c6fae9b9549"
version = "1.16.4"
[[deps.FilePathsBase]]
deps = ["Compat", "Dates"]
git-tree-sha1 = "7878ff7172a8e6beedd1dea14bd27c3c6340d361"
uuid = "48062228-2e41-5def-b9a4-89aafe57970f"
version = "0.9.22"
weakdeps = ["Mmap", "Test"]
[deps.FilePathsBase.extensions]
FilePathsBaseMmapExt = "Mmap"
FilePathsBaseTestExt = "Test"
[[deps.FileWatching]]
uuid = "7b1f6079-737a-58dc-b8bc-7a2ca5c1b5ee"
[[deps.FillArrays]]
deps = ["LinearAlgebra"]
git-tree-sha1 = "6a70198746448456524cb442b8af316927ff3e1a"
uuid = "1a297f60-69ca-5386-bcde-b61e274b549b"
version = "1.13.0"
weakdeps = ["PDMats", "SparseArrays", "Statistics"]
[deps.FillArrays.extensions]
FillArraysPDMatsExt = "PDMats"
FillArraysSparseArraysExt = "SparseArrays"
FillArraysStatisticsExt = "Statistics"
[[deps.Future]]
deps = ["Random"]
uuid = "9fa8497b-333b-5362-9e8d-4d0656e87820"
[[deps.GeneralUtils]]
deps = ["CSV", "DataFrames", "DataStructures", "Dates", "Distributions", "JSON3", "MQTTClient", "PrettyPrinting", "Random", "SHA", "UUIDs"]
path = "/appfolder/app/privatejuliapkg/GeneralUtils"
uuid = "c6c72f09-b708-4ac8-ac7c-2084d70108fe"
version = "0.1.0"
[[deps.HTTP]]
deps = ["Base64", "CodecZlib", "ConcurrentUtilities", "Dates", "ExceptionUnwrapping", "Logging", "LoggingExtras", "MbedTLS", "NetworkOptions", "OpenSSL", "Random", "SimpleBufferStream", "Sockets", "URIs", "UUIDs"]
git-tree-sha1 = "d1d712be3164d61d1fb98e7ce9bcbc6cc06b45ed"
uuid = "cd3eb016-35fb-5094-929b-558a96fad6f3"
version = "1.10.8"
[[deps.HypergeometricFunctions]]
deps = ["LinearAlgebra", "OpenLibm_jll", "SpecialFunctions"]
git-tree-sha1 = "7c4195be1649ae622304031ed46a2f4df989f1eb"
uuid = "34004b35-14d8-5ef3-9330-4cdb6864b03a"
version = "0.3.24"
[[deps.ICU_jll]]
deps = ["Artifacts", "JLLWrappers", "Libdl", "Pkg"]
git-tree-sha1 = "20b6765a3016e1fca0c9c93c80d50061b94218b7"
uuid = "a51ab1cf-af8e-5615-a023-bc2c838bba6b"
version = "69.1.0+0"
[[deps.Infinity]]
deps = ["Dates", "Random", "Requires"]
git-tree-sha1 = "cf8234411cbeb98676c173f930951ea29dca3b23"
uuid = "a303e19e-6eb4-11e9-3b09-cd9505f79100"
version = "0.2.4"
[[deps.InlineStrings]]
git-tree-sha1 = "45521d31238e87ee9f9732561bfee12d4eebd52d"
uuid = "842dd82b-1e85-43dc-bf29-5d0ee9dffc48"
version = "1.4.2"
[deps.InlineStrings.extensions]
ArrowTypesExt = "ArrowTypes"
ParsersExt = "Parsers"
[deps.InlineStrings.weakdeps]
ArrowTypes = "31f734f8-188a-4ce0-8406-c8a06bd891cd"
Parsers = "69de0a69-1ddd-5017-9359-2bf0b02dc9f0"
[[deps.InteractiveUtils]]
deps = ["Markdown"]
uuid = "b77e0a4c-d291-57a0-90e8-8db25a27a240"
[[deps.Intervals]]
deps = ["Dates", "Printf", "RecipesBase", "Serialization", "TimeZones"]
git-tree-sha1 = "ac0aaa807ed5eaf13f67afe188ebc07e828ff640"
uuid = "d8418881-c3e1-53bb-8760-2df7ec849ed5"
version = "1.10.0"
[[deps.InvertedIndices]]
git-tree-sha1 = "0dc7b50b8d436461be01300fd8cd45aa0274b038"
uuid = "41ab1584-1d38-5bbf-9106-f11c6c58b48f"
version = "1.3.0"
[[deps.IrrationalConstants]]
git-tree-sha1 = "630b497eafcc20001bba38a4651b327dcfc491d2"
uuid = "92d709cd-6900-40b7-9082-c6be49f344b6"
version = "0.2.2"
[[deps.IterTools]]
git-tree-sha1 = "42d5f897009e7ff2cf88db414a389e5ed1bdd023"
uuid = "c8e1da08-722c-5040-9ed9-7db0dc04731e"
version = "1.10.0"
[[deps.IteratorInterfaceExtensions]]
git-tree-sha1 = "a3f24677c21f5bbe9d2a714f95dcd58337fb2856"
uuid = "82899510-4779-5014-852e-03e436cf321d"
version = "1.0.0"
[[deps.JLLWrappers]]
deps = ["Artifacts", "Preferences"]
git-tree-sha1 = "be3dc50a92e5a386872a493a10050136d4703f9b"
uuid = "692b3bcd-3c85-4b1f-b108-f13ce0eb3210"
version = "1.6.1"
[[deps.JSON3]]
deps = ["Dates", "Mmap", "Parsers", "PrecompileTools", "StructTypes", "UUIDs"]
git-tree-sha1 = "1d322381ef7b087548321d3f878cb4c9bd8f8f9b"
uuid = "0f8b85d8-7281-11e9-16c2-39a750bddbf1"
version = "1.14.1"
[deps.JSON3.extensions]
JSON3ArrowExt = ["ArrowTypes"]
[deps.JSON3.weakdeps]
ArrowTypes = "31f734f8-188a-4ce0-8406-c8a06bd891cd"
[[deps.JuliaInterpreter]]
deps = ["CodeTracking", "InteractiveUtils", "Random", "UUIDs"]
git-tree-sha1 = "2984284a8abcfcc4784d95a9e2ea4e352dd8ede7"
uuid = "aa1ae85d-cabe-5617-a682-6adf51b2e16a"
version = "0.9.36"
[[deps.Kerberos_krb5_jll]]
deps = ["Artifacts", "JLLWrappers", "Libdl", "Pkg"]
git-tree-sha1 = "60274b4ab38e8d1248216fe6b6ace75ae09b0502"
uuid = "b39eb1a6-c29a-53d7-8c32-632cd16f18da"
version = "1.19.3+0"
[[deps.LLMMCTS]]
deps = ["GeneralUtils", "JSON3"]
path = "/appfolder/app/privatejuliapkg/LLMMCTS"
uuid = "d76c5a4d-449e-4835-8cc4-dd86ec44f241"
version = "0.1.0"
[[deps.LaTeXStrings]]
git-tree-sha1 = "dda21b8cbd6a6c40d9d02a73230f9d70fed6918c"
uuid = "b964fa9f-0449-5b57-a5c2-d3ea65f4040f"
version = "1.4.0"
[[deps.LayerDicts]]
git-tree-sha1 = "6087ad3521d6278ebe5c27ae55e7bbb15ca312cb"
uuid = "6f188dcb-512c-564b-bc01-e0f76e72f166"
version = "1.0.0"
[[deps.LazyArtifacts]]
deps = ["Artifacts", "Pkg"]
uuid = "4af54fe1-eca0-43a8-85a7-787d91b784e3"
[[deps.LibCURL]]
deps = ["LibCURL_jll", "MozillaCACerts_jll"]
uuid = "b27032c2-a3e7-50c8-80cd-2d36dbcbfd21"
version = "0.6.4"
[[deps.LibCURL_jll]]
deps = ["Artifacts", "LibSSH2_jll", "Libdl", "MbedTLS_jll", "Zlib_jll", "nghttp2_jll"]
uuid = "deac9b47-8bc7-5906-a0fe-35ac56dc84c0"
version = "8.4.0+0"
[[deps.LibGit2]]
deps = ["Base64", "LibGit2_jll", "NetworkOptions", "Printf", "SHA"]
uuid = "76f85450-5226-5b5a-8eaa-529ad045b433"
[[deps.LibGit2_jll]]
deps = ["Artifacts", "LibSSH2_jll", "Libdl", "MbedTLS_jll"]
uuid = "e37daf67-58a4-590a-8e99-b0245dd2ffc5"
version = "1.6.4+0"
[[deps.LibPQ]]
deps = ["CEnum", "DBInterface", "Dates", "Decimals", "DocStringExtensions", "FileWatching", "Infinity", "Intervals", "IterTools", "LayerDicts", "LibPQ_jll", "Libdl", "Memento", "OffsetArrays", "SQLStrings", "Tables", "TimeZones", "UTCDateTimes"]
git-tree-sha1 = "3d227cd13cbf1e9a54d7748dab33e078da6f9168"
uuid = "194296ae-ab2e-5f79-8cd4-7183a0a5a0d1"
version = "1.18.0"
[[deps.LibPQ_jll]]
deps = ["Artifacts", "ICU_jll", "JLLWrappers", "Kerberos_krb5_jll", "Libdl", "OpenSSL_jll", "Zstd_jll"]
git-tree-sha1 = "09163f837936c8cc44f4691cb41d805eb1769642"
uuid = "08be9ffa-1c94-5ee5-a977-46a84ec9b350"
version = "16.0.0+0"
[[deps.LibSSH2_jll]]
deps = ["Artifacts", "Libdl", "MbedTLS_jll"]
uuid = "29816b5a-b9ab-546f-933c-edad1886dfa8"
version = "1.11.0+1"
[[deps.Libdl]]
uuid = "8f399da3-3557-5675-b5ff-fb832c97cbdb"
[[deps.LinearAlgebra]]
deps = ["Libdl", "OpenBLAS_jll", "libblastrampoline_jll"]
uuid = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
[[deps.LogExpFunctions]]
deps = ["DocStringExtensions", "IrrationalConstants", "LinearAlgebra"]
git-tree-sha1 = "a2d09619db4e765091ee5c6ffe8872849de0feea"
uuid = "2ab3a3ac-af41-5b50-aa03-7779005ae688"
version = "0.3.28"
[deps.LogExpFunctions.extensions]
LogExpFunctionsChainRulesCoreExt = "ChainRulesCore"
LogExpFunctionsChangesOfVariablesExt = "ChangesOfVariables"
LogExpFunctionsInverseFunctionsExt = "InverseFunctions"
[deps.LogExpFunctions.weakdeps]
ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
ChangesOfVariables = "9e997f8a-9a97-42d5-a9f1-ce6bfc15e2c0"
InverseFunctions = "3587e190-3f89-42d0-90ee-14403ec27112"
[[deps.Logging]]
uuid = "56ddb016-857b-54e1-b83d-db4d58db5568"
[[deps.LoggingExtras]]
deps = ["Dates", "Logging"]
git-tree-sha1 = "c1dd6d7978c12545b4179fb6153b9250c96b0075"
uuid = "e6f89c97-d47a-5376-807f-9c37f3926c36"
version = "1.0.3"
[[deps.LoweredCodeUtils]]
deps = ["JuliaInterpreter"]
git-tree-sha1 = "260dc274c1bc2cb839e758588c63d9c8b5e639d1"
uuid = "6f1432cf-f94c-5a45-995e-cdbf5db27b0b"
version = "3.0.5"
[[deps.MQTTClient]]
deps = ["Distributed", "Random", "Sockets"]
git-tree-sha1 = "f2597b290d4bf17b577346153cd2ddf9accb5c26"
uuid = "985f35cc-2c3d-4943-b8c1-f0931d5f0959"
version = "0.3.1"
weakdeps = ["PrecompileTools"]
[deps.MQTTClient.extensions]
PrecompileMQTT = "PrecompileTools"
[[deps.MacroTools]]
deps = ["Markdown", "Random"]
git-tree-sha1 = "2fa9ee3e63fd3a4f7a9a4f4744a52f4856de82df"
uuid = "1914dd2f-81c6-5fcd-8719-6d5c9610ff09"
version = "0.5.13"
[[deps.Markdown]]
deps = ["Base64"]
uuid = "d6f4376e-aef5-505a-96c1-9c027394607a"
[[deps.MbedTLS]]
deps = ["Dates", "MbedTLS_jll", "MozillaCACerts_jll", "NetworkOptions", "Random", "Sockets"]
git-tree-sha1 = "c067a280ddc25f196b5e7df3877c6b226d390aaf"
uuid = "739be429-bea8-5141-9913-cc70e7f3736d"
version = "1.1.9"
[[deps.MbedTLS_jll]]
deps = ["Artifacts", "Libdl"]
uuid = "c8ffd9c3-330d-5841-b78e-0817d7145fa1"
version = "2.28.2+1"
[[deps.Memento]]
deps = ["Dates", "Distributed", "Requires", "Serialization", "Sockets", "Test", "UUIDs"]
git-tree-sha1 = "bb2e8f4d9f400f6e90d57b34860f6abdc51398e5"
uuid = "f28f55f0-a522-5efc-85c2-fe41dfb9b2d9"
version = "1.4.1"
[[deps.MicroMamba]]
deps = ["Pkg", "Scratch", "micromamba_jll"]
git-tree-sha1 = "011cab361eae7bcd7d278f0a7a00ff9c69000c51"
uuid = "0b3b1443-0f03-428d-bdfb-f27f9c1191ea"
version = "0.1.14"
[[deps.Missings]]
deps = ["DataAPI"]
git-tree-sha1 = "ec4f7fbeab05d7747bdf98eb74d130a2a2ed298d"
uuid = "e1d29d7a-bbdc-5cf2-9ac0-f12de2c33e28"
version = "1.2.0"
[[deps.Mmap]]
uuid = "a63ad114-7e13-5084-954f-fe012c677804"
[[deps.Mocking]]
deps = ["Compat", "ExprTools"]
git-tree-sha1 = "2c140d60d7cb82badf06d8783800d0bcd1a7daa2"
uuid = "78c3b35d-d492-501b-9361-3d52fe80e533"
version = "0.8.1"
[[deps.MozillaCACerts_jll]]
uuid = "14a3606d-f60d-562e-9121-12d972cd8159"
version = "2023.1.10"
[[deps.NetworkOptions]]
uuid = "ca575930-c2e3-43a9-ace4-1e988b2c1908"
version = "1.2.0"
[[deps.OffsetArrays]]
git-tree-sha1 = "1a27764e945a152f7ca7efa04de513d473e9542e"
uuid = "6fe1bfb0-de20-5000-8ca7-80f57d26f881"
version = "1.14.1"
[deps.OffsetArrays.extensions]
OffsetArraysAdaptExt = "Adapt"
[deps.OffsetArrays.weakdeps]
Adapt = "79e6a3ab-5dfb-504d-930d-738a2a938a0e"
[[deps.OpenBLAS_jll]]
deps = ["Artifacts", "CompilerSupportLibraries_jll", "Libdl"]
uuid = "4536629a-c528-5b80-bd46-f80d51c5b363"
version = "0.3.23+4"
[[deps.OpenLibm_jll]]
deps = ["Artifacts", "Libdl"]
uuid = "05823500-19ac-5b8b-9628-191a04bc5112"
version = "0.8.1+2"
[[deps.OpenSSL]]
deps = ["BitFlags", "Dates", "MozillaCACerts_jll", "OpenSSL_jll", "Sockets"]
git-tree-sha1 = "38cb508d080d21dc1128f7fb04f20387ed4c0af4"
uuid = "4d8831e6-92b7-49fb-bdf8-b643e874388c"
version = "1.4.3"
[[deps.OpenSSL_jll]]
deps = ["Artifacts", "JLLWrappers", "Libdl"]
git-tree-sha1 = "7493f61f55a6cce7325f197443aa80d32554ba10"
uuid = "458c3c95-2e84-50aa-8efc-19380b2a3a95"
version = "3.0.15+1"
[[deps.OpenSpecFun_jll]]
deps = ["Artifacts", "CompilerSupportLibraries_jll", "JLLWrappers", "Libdl", "Pkg"]
git-tree-sha1 = "13652491f6856acfd2db29360e1bbcd4565d04f1"
uuid = "efe28fd5-8261-553b-a9e1-b2916fc3738e"
version = "0.5.5+0"
[[deps.OrderedCollections]]
git-tree-sha1 = "dfdf5519f235516220579f949664f1bf44e741c5"
uuid = "bac558e1-5e72-5ebc-8fee-abe8a469f55d"
version = "1.6.3"
[[deps.PDMats]]
deps = ["LinearAlgebra", "SparseArrays", "SuiteSparse"]
git-tree-sha1 = "949347156c25054de2db3b166c52ac4728cbad65"
uuid = "90014a1f-27ba-587c-ab20-58faa44d9150"
version = "0.11.31"
[[deps.Parsers]]
deps = ["Dates", "PrecompileTools", "UUIDs"]
git-tree-sha1 = "8489905bcdbcfac64d1daa51ca07c0d8f0283821"
uuid = "69de0a69-1ddd-5017-9359-2bf0b02dc9f0"
version = "2.8.1"
[[deps.Pidfile]]
deps = ["FileWatching", "Test"]
git-tree-sha1 = "2d8aaf8ee10df53d0dfb9b8ee44ae7c04ced2b03"
uuid = "fa939f87-e72e-5be4-a000-7fc836dbe307"
version = "1.3.0"
[[deps.Pkg]]
deps = ["Artifacts", "Dates", "Downloads", "FileWatching", "LibGit2", "Libdl", "Logging", "Markdown", "Printf", "REPL", "Random", "SHA", "Serialization", "TOML", "Tar", "UUIDs", "p7zip_jll"]
uuid = "44cfe95a-1eb2-52ea-b672-e2afdf69b78f"
version = "1.10.0"
[[deps.PooledArrays]]
deps = ["DataAPI", "Future"]
git-tree-sha1 = "36d8b4b899628fb92c2749eb488d884a926614d3"
uuid = "2dfb63ee-cc39-5dd5-95bd-886bf059d720"
version = "1.4.3"
[[deps.PrecompileTools]]
deps = ["Preferences"]
git-tree-sha1 = "5aa36f7049a63a1528fe8f7c3f2113413ffd4e1f"
uuid = "aea7be01-6a6a-4083-8856-8a6e6704d82a"
version = "1.2.1"
[[deps.Preferences]]
deps = ["TOML"]
git-tree-sha1 = "9306f6085165d270f7e3db02af26a400d580f5c6"
uuid = "21216c6a-2e73-6563-6e65-726566657250"
version = "1.4.3"
[[deps.PrettyPrinting]]
git-tree-sha1 = "142ee93724a9c5d04d78df7006670a93ed1b244e"
uuid = "54e16d92-306c-5ea0-a30b-337be88ac337"
version = "0.4.2"
[[deps.PrettyTables]]
deps = ["Crayons", "LaTeXStrings", "Markdown", "PrecompileTools", "Printf", "Reexport", "StringManipulation", "Tables"]
git-tree-sha1 = "1101cd475833706e4d0e7b122218257178f48f34"
uuid = "08abe8d2-0d0c-5749-adfa-8a2ac140af0d"
version = "2.4.0"
[[deps.Printf]]
deps = ["Unicode"]
uuid = "de0858da-6303-5e67-8744-51eddeeeb8d7"
[[deps.PtrArrays]]
git-tree-sha1 = "77a42d78b6a92df47ab37e177b2deac405e1c88f"
uuid = "43287f4e-b6f4-7ad1-bb20-aadabca52c3d"
version = "1.2.1"
[[deps.PythonCall]]
deps = ["CondaPkg", "Dates", "Libdl", "MacroTools", "Markdown", "Pkg", "REPL", "Requires", "Serialization", "Tables", "UnsafePointers"]
git-tree-sha1 = "06a778ec6d6e76b0c2fb661436a18bce853ec45f"
uuid = "6099a3de-0909-46bc-b1f4-468b9a2dfc0d"
version = "0.9.23"
[[deps.QuadGK]]
deps = ["DataStructures", "LinearAlgebra"]
git-tree-sha1 = "cda3b045cf9ef07a08ad46731f5a3165e56cf3da"
uuid = "1fd47b50-473d-5c70-9696-f719f8f3bcdc"
version = "2.11.1"
[deps.QuadGK.extensions]
QuadGKEnzymeExt = "Enzyme"
[deps.QuadGK.weakdeps]
Enzyme = "7da242da-08ed-463a-9acd-ee780be4f1d9"
[[deps.REPL]]
deps = ["InteractiveUtils", "Markdown", "Sockets", "Unicode"]
uuid = "3fa0cd96-eef1-5676-8a61-b3b8758bbffb"
[[deps.Random]]
deps = ["SHA"]
uuid = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
[[deps.RecipesBase]]
deps = ["PrecompileTools"]
git-tree-sha1 = "5c3d09cc4f31f5fc6af001c250bf1278733100ff"
uuid = "3cdcf5f2-1ef4-517c-9805-6587b60abb01"
version = "1.3.4"
[[deps.Reexport]]
git-tree-sha1 = "45e428421666073eab6f2da5c9d310d99bb12f9b"
uuid = "189a3867-3050-52da-a836-e630ba90ab69"
version = "1.2.2"
[[deps.Requires]]
deps = ["UUIDs"]
git-tree-sha1 = "838a3a4188e2ded87a4f9f184b4b0d78a1e91cb7"
uuid = "ae029012-a4dd-5104-9daa-d747884805df"
version = "1.3.0"
[[deps.Revise]]
deps = ["CodeTracking", "Distributed", "FileWatching", "JuliaInterpreter", "LibGit2", "LoweredCodeUtils", "OrderedCollections", "REPL", "Requires", "UUIDs", "Unicode"]
git-tree-sha1 = "7f4228017b83c66bd6aa4fddeb170ce487e53bc7"
uuid = "295af30f-e4ad-537b-8983-00126c2a3abe"
version = "3.6.2"
[[deps.Rmath]]
deps = ["Random", "Rmath_jll"]
git-tree-sha1 = "852bd0f55565a9e973fcfee83a84413270224dc4"
uuid = "79098fc4-a85e-5d69-aa6a-4863f24498fa"
version = "0.8.0"
[[deps.Rmath_jll]]
deps = ["Artifacts", "JLLWrappers", "Libdl"]
git-tree-sha1 = "58cdd8fb2201a6267e1db87ff148dd6c1dbd8ad8"
uuid = "f50d1b31-88e8-58de-be2c-1cc44531875f"
version = "0.5.1+0"
[[deps.SHA]]
uuid = "ea8e919c-243c-51af-8825-aaa63cd721ce"
version = "0.7.0"
[[deps.SQLLLM]]
deps = ["CSV", "CondaPkg", "DataFrames", "DataStructures", "Dates", "FileIO", "GeneralUtils", "HTTP", "JSON3", "LLMMCTS", "LibPQ", "MQTTClient", "PrettyPrinting", "PythonCall", "Random", "Revise", "StatsBase", "Tables", "URIs", "UUIDs"]
path = "/appfolder/app/privatejuliapkg/SQLLLM"
uuid = "2ebc79c7-cc10-4a3a-9665-d2e1d61e63d3"
version = "0.1.0"
[[deps.SQLStrings]]
git-tree-sha1 = "55de0530689832b1d3d43491ee6b67bd54d3323c"
uuid = "af517c2e-c243-48fa-aab8-efac3db270f5"
version = "0.1.0"
[[deps.Scratch]]
deps = ["Dates"]
git-tree-sha1 = "3bac05bc7e74a75fd9cba4295cde4045d9fe2386"
uuid = "6c6a2e73-6563-6170-7368-637461726353"
version = "1.2.1"
[[deps.SentinelArrays]]
deps = ["Dates", "Random"]
git-tree-sha1 = "ff11acffdb082493657550959d4feb4b6149e73a"
uuid = "91c51154-3ec4-41a3-a24f-3f23e20d615c"
version = "1.4.5"
[[deps.Serialization]]
uuid = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
[[deps.SimpleBufferStream]]
git-tree-sha1 = "f305871d2f381d21527c770d4788c06c097c9bc1"
uuid = "777ac1f9-54b0-4bf8-805c-2214025038e7"
version = "1.2.0"
[[deps.Sockets]]
uuid = "6462fe0b-24de-5631-8697-dd941f90decc"
[[deps.SortingAlgorithms]]
deps = ["DataStructures"]
git-tree-sha1 = "66e0a8e672a0bdfca2c3f5937efb8538b9ddc085"
uuid = "a2af1166-a08f-5f64-846c-94a0d3cef48c"
version = "1.2.1"
[[deps.SparseArrays]]
deps = ["Libdl", "LinearAlgebra", "Random", "Serialization", "SuiteSparse_jll"]
uuid = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"
version = "1.10.0"
[[deps.SpecialFunctions]]
deps = ["IrrationalConstants", "LogExpFunctions", "OpenLibm_jll", "OpenSpecFun_jll"]
git-tree-sha1 = "2f5d4697f21388cbe1ff299430dd169ef97d7e14"
uuid = "276daf66-3868-5448-9aa4-cd146d93841b"
version = "2.4.0"
[deps.SpecialFunctions.extensions]
SpecialFunctionsChainRulesCoreExt = "ChainRulesCore"
[deps.SpecialFunctions.weakdeps]
ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
[[deps.Statistics]]
deps = ["LinearAlgebra", "SparseArrays"]
uuid = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
version = "1.10.0"
[[deps.StatsAPI]]
deps = ["LinearAlgebra"]
git-tree-sha1 = "1ff449ad350c9c4cbc756624d6f8a8c3ef56d3ed"
uuid = "82ae8749-77ed-4fe6-ae5f-f523153014b0"
version = "1.7.0"
[[deps.StatsBase]]
deps = ["DataAPI", "DataStructures", "LinearAlgebra", "LogExpFunctions", "Missings", "Printf", "Random", "SortingAlgorithms", "SparseArrays", "Statistics", "StatsAPI"]
git-tree-sha1 = "5cf7606d6cef84b543b483848d4ae08ad9832b21"
uuid = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
version = "0.34.3"
[[deps.StatsFuns]]
deps = ["HypergeometricFunctions", "IrrationalConstants", "LogExpFunctions", "Reexport", "Rmath", "SpecialFunctions"]
git-tree-sha1 = "b423576adc27097764a90e163157bcfc9acf0f46"
uuid = "4c63d2b9-4356-54db-8cca-17b64c39e42c"
version = "1.3.2"
[deps.StatsFuns.extensions]
StatsFunsChainRulesCoreExt = "ChainRulesCore"
StatsFunsInverseFunctionsExt = "InverseFunctions"
[deps.StatsFuns.weakdeps]
ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
InverseFunctions = "3587e190-3f89-42d0-90ee-14403ec27112"
[[deps.StringManipulation]]
deps = ["PrecompileTools"]
git-tree-sha1 = "a6b1675a536c5ad1a60e5a5153e1fee12eb146e3"
uuid = "892a3eda-7b42-436c-8928-eab12a02cf0e"
version = "0.4.0"
[[deps.StructTypes]]
deps = ["Dates", "UUIDs"]
git-tree-sha1 = "159331b30e94d7b11379037feeb9b690950cace8"
uuid = "856f2bd8-1eba-4b0a-8007-ebc267875bd4"
version = "1.11.0"
[[deps.SuiteSparse]]
deps = ["Libdl", "LinearAlgebra", "Serialization", "SparseArrays"]
uuid = "4607b0f0-06f3-5cda-b6b1-a6196a1729e9"
[[deps.SuiteSparse_jll]]
deps = ["Artifacts", "Libdl", "libblastrampoline_jll"]
uuid = "bea87d4a-7f5b-5778-9afe-8cc45184846c"
version = "7.2.1+1"
[[deps.TOML]]
deps = ["Dates"]
uuid = "fa267f1f-6049-4f14-aa54-33bafae1ed76"
version = "1.0.3"
[[deps.TZJData]]
deps = ["Artifacts"]
git-tree-sha1 = "36b40607bf2bf856828690e097e1c799623b0602"
uuid = "dc5dba14-91b3-4cab-a142-028a31da12f7"
version = "1.3.0+2024b"
[[deps.TableTraits]]
deps = ["IteratorInterfaceExtensions"]
git-tree-sha1 = "c06b2f539df1c6efa794486abfb6ed2022561a39"
uuid = "3783bdb8-4a98-5b6b-af9a-565f29a5fe9c"
version = "1.0.1"
[[deps.Tables]]
deps = ["DataAPI", "DataValueInterfaces", "IteratorInterfaceExtensions", "OrderedCollections", "TableTraits"]
git-tree-sha1 = "598cd7c1f68d1e205689b1c2fe65a9f85846f297"
uuid = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
version = "1.12.0"
[[deps.Tar]]
deps = ["ArgTools", "SHA"]
uuid = "a4e569a6-e804-4fa4-b0f3-eef7a1d5b13e"
version = "1.10.0"
[[deps.Test]]
deps = ["InteractiveUtils", "Logging", "Random", "Serialization"]
uuid = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
[[deps.TimeZones]]
deps = ["Dates", "Downloads", "InlineStrings", "Mocking", "Printf", "Scratch", "TZJData", "Unicode", "p7zip_jll"]
git-tree-sha1 = "8323074bc977aa85cf5ad71099a83ac75b0ac107"
uuid = "f269a46b-ccf7-5d73-abea-4c690281aa53"
version = "1.18.1"
weakdeps = ["RecipesBase"]
[deps.TimeZones.extensions]
TimeZonesRecipesBaseExt = "RecipesBase"
[[deps.TranscodingStreams]]
git-tree-sha1 = "0c45878dcfdcfa8480052b6ab162cdd138781742"
uuid = "3bb67fe8-82b1-5028-8e26-92a6c54297fa"
version = "0.11.3"
[[deps.URIs]]
git-tree-sha1 = "67db6cc7b3821e19ebe75791a9dd19c9b1188f2b"
uuid = "5c2747f8-b7ea-4ff2-ba2e-563bfd36b1d4"
version = "1.5.1"
[[deps.UTCDateTimes]]
deps = ["Dates", "TimeZones"]
git-tree-sha1 = "4af3552bf0cf4a071bf3d14bd20023ea70f31b62"
uuid = "0f7cfa37-7abf-4834-b969-a8aa512401c2"
version = "1.6.1"
[[deps.UUIDs]]
deps = ["Random", "SHA"]
uuid = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
[[deps.Unicode]]
uuid = "4ec0a83e-493e-50e2-b9ac-8f72acf5a8f5"
[[deps.UnsafePointers]]
git-tree-sha1 = "c81331b3b2e60a982be57c046ec91f599ede674a"
uuid = "e17b2a0c-0bdf-430a-bd0c-3a23cae4ff39"
version = "1.0.0"
[[deps.WeakRefStrings]]
deps = ["DataAPI", "InlineStrings", "Parsers"]
git-tree-sha1 = "b1be2855ed9ed8eac54e5caff2afcdb442d52c23"
uuid = "ea10d353-3f73-51f8-a26c-33c1cb351aa5"
version = "1.4.2"
[[deps.WorkerUtilities]]
git-tree-sha1 = "cd1659ba0d57b71a464a29e64dbc67cfe83d54e7"
uuid = "76eceee3-57b5-4d4a-8e66-0e911cebbf60"
version = "1.6.1"
[[deps.Zlib_jll]]
deps = ["Libdl"]
uuid = "83775a58-1f1d-513f-b197-d71354ab007a"
version = "1.2.13+1"
[[deps.Zstd_jll]]
deps = ["Artifacts", "JLLWrappers", "Libdl"]
git-tree-sha1 = "555d1076590a6cc2fdee2ef1469451f872d8b41b"
uuid = "3161d3a3-bdf6-5164-811a-617609db77b4"
version = "1.5.6+1"
[[deps.libblastrampoline_jll]]
deps = ["Artifacts", "Libdl"]
uuid = "8e850b90-86db-534c-a0d3-1478176c7d93"
version = "5.11.0+0"
[[deps.micromamba_jll]]
deps = ["Artifacts", "JLLWrappers", "LazyArtifacts", "Libdl"]
git-tree-sha1 = "b4a5a3943078f9fd11ae0b5ab1bdbf7718617945"
uuid = "f8abcde7-e9b7-5caa-b8af-a437887ae8e4"
version = "1.5.8+0"
[[deps.nghttp2_jll]]
deps = ["Artifacts", "Libdl"]
uuid = "8e850ede-7688-5339-a07c-302acd2aaf8d"
version = "1.52.0+1"
[[deps.p7zip_jll]]
deps = ["Artifacts", "Libdl"]
uuid = "3f19e933-33d8-53b3-aaab-bd5110c3b7a0"
version = "17.4.0+2"

23
previousversion/0.2/Project.toml Normal file
View File

@@ -0,0 +1,23 @@
name = "YiemAgent"
uuid = "e012c34b-7f78-48e0-971c-7abb83b6f0a2"
authors = ["narawat lamaiin <narawat@outlook.com>"]
version = "0.1.0"
[deps]
CondaPkg = "992eb4ea-22a4-4c89-a5bb-47a3300528ab"
DataStructures = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
Dates = "ade2ca70-3891-5945-98fb-dc099432e06a"
GeneralUtils = "c6c72f09-b708-4ac8-ac7c-2084d70108fe"
HTTP = "cd3eb016-35fb-5094-929b-558a96fad6f3"
JSON3 = "0f8b85d8-7281-11e9-16c2-39a750bddbf1"
LLMMCTS = "d76c5a4d-449e-4835-8cc4-dd86ec44f241"
LibPQ = "194296ae-ab2e-5f79-8cd4-7183a0a5a0d1"
MQTTClient = "985f35cc-2c3d-4943-b8c1-f0931d5f0959"
PrettyPrinting = "54e16d92-306c-5ea0-a30b-337be88ac337"
PythonCall = "6099a3de-0909-46bc-b1f4-468b9a2dfc0d"
Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
Revise = "295af30f-e4ad-537b-8983-00126c2a3abe"
SQLLLM = "2ebc79c7-cc10-4a3a-9665-d2e1d61e63d3"
Serialization = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
URIs = "5c2747f8-b7ea-4ff2-ba2e-563bfd36b1d4"
UUIDs = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"

7
previousversion/0.2/README.md Normal file
View File

@@ -0,0 +1,7 @@
version 0.1.0
TODO:
[WORKING] build MCTS() for planning
[] executeplan() to execute the plan
Change from version: 0.0.9
-

537
previousversion/0.2/src/MCTSexamplePrompt.py Normal file
View File

@@ -0,0 +1,537 @@
https://github.com/andyz245/LanguageAgentTreeSearch/blob/main/hotpot/hotpot.py
standard_prompt = '''
Write a coherent passage of 4 short paragraphs. The end sentence of each paragraph must be: {input}
'''
reflection_prompt = '''You are an advanced reasoning agent that can improve based on self refection. You will be given a previous reasoning trial in which you were given access to an Docstore API environment and a question to answer. You were unsuccessful in answering the question either because you guessed the wrong answer with Finish[<answer>], or you used up your set number of reasoning steps. In a few sentences, Diagnose a possible reason for failure and devise a new, concise, high level plan that aims to mitigate the same failure. Use complete sentences.
Here are some examples:
Previous Trial:
Question: The Rome Protocols were signed by three Prime Ministers one of which was assassinated as part of what?
Thought 1: I need to search Rome Protocols, find the three Prime Ministers, then find what they were assassinated as part of.
Action 1: Search[Rome Protocols]
Observation 1: The Rome Protocols were a series of three international agreements concluded in Rome on 17 March 1934 between the governments of Austria, Hungary and Italy. They were signed by Italian Prime Minister Benito Mussolini, Austrian Chancellor Engelbert Dollfuss and Hungarian Prime Minister Gyula Gömbös. All of the protocols went into effect on 12 July 1934 and were registered in League of Nations Treaty Series on 12 December 1934.
Thought 2: The three Prime Ministers were Benito Mussolini, Engelbert Dollfuss, and Gyula Gömbös. I need to search Benito Mussolini and find what he was assassinated as part of.
Action 2: Search[Benito Mussolini]
Observation 2: Benito Amilcare Andrea Mussolini (UK: MU(U)SS-ə-LEE-nee, US: MOOSS-, Italian: [beˈniːto aˈmilkare anˈdrɛːa mussoˈliːni]; 29 July 1883 – 28 April 1945) was an Italian politician and journalist who founded and led the National Fascist Party (PNF). He was Prime Minister of Italy from the March on Rome in 1922 until his deposition in 1943, as well as "Duce" of Italian fascism from the establishment of the Italian Fasces of Combat in 1919 until his summary execution in 1945 by Italian partisans. As dictator of Italy and principal founder of fascism, Mussolini inspired and supported the international spread of fascist movements during the inter-war period.Mussolini was originally a socialist politician and a journalist at the Avanti! newspaper. In 1912, he became a member of the National Directorate of the Italian Socialist Party (PSI), but he was expelled from the PSI for advocating military intervention in World War I, in opposition to the party's stance on neutrality. In 1914, Mussolini founded a new journal, Il Popolo d'Italia, and served in the Royal Italian Army during the war until he was wounded and discharged in 1917. Mussolini denounced the PSI, his views now centering on Italian nationalism instead of socialism, and later founded the fascist movement which came to oppose egalitarianism and class conflict, instead advocating "revolutionary nationalism" transcending class lines. On 31 October 1922, following the March on Rome (28–30 October), Mussolini was appointed prime minister by King Victor Emmanuel III, becoming the youngest individual to hold the office up to that time. After removing all political opposition through his secret police and outlawing labor strikes, Mussolini and his followers consolidated power through a series of laws that transformed the nation into a one-party dictatorship. Within five years, Mussolini had established dictatorial authority by both legal and illegal means and aspired to create a totalitarian state. In 1929, Mussolini signed the Lateran Treaty with the Holy See to establish Vatican City.
Mussolini's foreign policy aimed to restore the ancient grandeur of the Roman Empire by expanding Italian colonial possessions and the fascist sphere of influence. In the 1920s, he ordered the Pacification of Libya, instructed the bombing of Corfu over an incident with Greece, established a protectorate over Albania, and incorporated the city of Fiume into the Italian state via agreements with Yugoslavia. In 1936, Ethiopia was conquered following the Second Italo-Ethiopian War and merged into Italian East Africa (AOI) with Eritrea and Somalia. In 1939, Italian forces annexed Albania. Between 1936 and 1939, Mussolini ordered the successful Italian military intervention in Spain in favor of Francisco Franco during the Spanish Civil War. Mussolini's Italy initially tried to avoid the outbreak of a second global war, sending troops at the Brenner Pass to delay Anschluss and taking part in the Stresa Front, the Lytton Report, the Treaty of Lausanne, the Four-Power Pact and the Munich Agreement. However, Italy then alienated itself from Britain and France by aligning with Germany and Japan. Germany invaded Poland on 1 September 1939, resulting in declarations of war by France and the UK and the start of World War II.
On 10 June 1940, Mussolini decided to enter the war on the Axis side. Despite initial success, the subsequent Axis collapse on multiple fronts and eventual Allied invasion of Sicily made Mussolini lose the support of the population and members of the Fascist Party. As a consequence, early on 25 July 1943, the Grand Council of Fascism passed a motion of no confidence in Mussolini; later that day King Victor Emmanuel III dismissed him as head of government and had him placed in custody, appointing Pietro Badoglio to succeed him as Prime Minister. After the king agreed to an armistice with the Allies, on 12 September 1943 Mussolini was rescued from captivity in the Gran Sasso raid by German paratroopers and Waffen-SS commandos led by Major Otto-Harald Mors. Adolf Hitler, after meeting with the rescued former dictator, then put Mussolini in charge of a puppet regime in northern Italy, the Italian Social Republic (Italian: Repubblica Sociale Italiana, RSI), informally known as the Salò Republic, causing a civil war. In late April 1945, in the wake of near total defeat, Mussolini and his mistress Clara Petacci attempted to flee to Switzerland, but both were captured by Italian communist partisans and summarily executed by firing squad on 28 April 1945 near Lake Como. The bodies of Mussolini and his mistress were then taken to Milan, where they were hung upside down at a service station to publicly confirm their demise.
Thought 3: Benito Mussolini was assassinated as part of the collapse of the Axis powers during World War II. So the Rome Protocols were signed by three Prime Ministers one of which was assassinated as part of World War II.
Action 3: Finish[World War II]
Reflection: I searched one of the prime ministers involved in the signing, then attemted to answer right away. I should have searched each of the prime ministers, then looked up 'death' on each of their pages in order to get more information before answering.
Previous Trial:
Question: Kam Heskin plays Paige Morgan in a 2004 film directed by who?
Thought 1: I need to search Kam Heskin and Paige Morgan, find the 2004 film they are in, then find the director of the film.
Action 1: Search[Kam Heskin]
Observation 1: Kam Erika Heskin (born May 8, 1973) is an American actress. She began her career playing Caitlin Deschanel on the NBC daytime soap opera Sunset Beach (1998–1999), before appearing in films Planet of the Apes (2001) and Catch Me If You Can (2002). Heskin went on in 2003 to play Elizabeth Bennet in an independent film Pride & Prejudice: A Latter-Day Comedy, Robin in Charmed (2004), and Paige Morgan in The Prince and Me film franchise (2006–2010).
Thought 2: Kam Heskin plays Paige Morgan in The Prince and Me film franchise. I need to search The Prince and Me film franchise and find the director of the 2004 film.
Action 2: Search[The Prince and Me film franchise]
Observation 2: Could not find [The Prince and Me film franchise]. Similar: ['Kam Heskin', 'Prince of Persia', 'Harry Potter and the Half-Blood Prince (film)', 'Prince of Persia: The Sands of Time (film)', 'The Chronicles of Narnia (film series)', 'Majestic Prince (franchise)', 'Kingsman (franchise)', 'The Little Prince (2015 film)', 'Shrek (franchise)', 'Harry Potter (film series)']
Thought 3: I need to search The Prince and Me (2004 film) instead.
Action 3: Search[The Prince and Me (2004 film)]
Observation 3: Could not find [The Prince and Me (2004 film)]. Similar: ['The Prince & Me', 'The Prince & Me 2: The Royal Wedding', 'Kam Heskin', 'Prince of Darkness (film)', 'Prince of Persia: The Sands of Time (film)', 'Rob Knox', 'Alexander (2004 film)', 'Prince of Persia', 'Brooklynn Prince', 'Prince (musician)']
Thought 4: I need to search The Prince & Me (2004 film).
Action 4: Search[The Prince & Me (2004 film)]
Observation 4: Could not find [The Prince & Me (2004 film)]. Similar: ['The Prince & Me', 'The Prince & Me 2: The Royal Wedding', 'Prince of Darkness (film)', 'Prince of Persia: The Sands of Time (film)', 'Rob Knox', 'Alexander (2004 film)', 'Prince (musician)', 'Prince of Persia', 'Kam Heskin', 'Brooklynn Prince']
Thought 5: I need to search The Prince & Me (2004 film) instead.
Action 5: Search[The Prince & Me (2004 film)]
Observation 5: Could not find [The Prince & Me (2004 film)]. Similar: ['The Prince & Me', 'The Prince & Me 2: The Royal Wedding', 'Prince of Darkness (film)', 'Prince of Persia: The Sands of Time (film)', 'Rob Knox', 'Alexander (2004 film)', 'Prince (musician)', 'Prince of Persia', 'Kam Heskin', 'Brooklynn Prince']
Thought 6: I need to search The Prince & Me (2004 film).
Action 6: Search[The Prince & Me (2004 film)]
Observation 6: Could not find [The Prince & Me (2004 film)]. Similar: ['The Prince & Me', 'The Prince & Me 2: The Royal Wedding', 'Prince of Darkness (film)', 'Prince of Persia: The Sands of Time (film)', 'Rob Knox', 'Alexander (2004 film)', 'Prince (musician)', 'Prince of Persia', 'Kam Heskin', 'Brooklynn Prince']
Reflection: I got stuck in a loop where I kept trying to search 'The Prince & Me (2004 film)' but the page could not be found. Instead I should have tried to search the similar results that had a similar name to see and they were made in 2004.
Previous Trial:
Question: The Oberoi family is part of a hotel company that has a head office in what city?
Thought 1: I need to search the Oberoi family and find the city where the hotel company's head office is located.
Action 1: Search[Oberoi family]
Observation 1: The Oberoi Group is a luxury hotel group with its head office in New Delhi, India.[2] Founded in 1934, the company owns and operates 32 luxury hotels and two river cruise ships in 7 countries, primarily under its Oberoi Hotels & Resorts and Trident brands.[3] The group also operates The Oberoi Centre for Learning and Development, which is regarded as one of Asia's top institutions for hospitality education.[4]. The foundations of the Oberoi Group date back to 1934 when The Rai Bahadur Mohan Singh Oberoi, the founder of the group, bought two properties: the Maidens in Delhi and the Clarke's in Shimla.[5] In the following years Oberoi, assisted by his two sons, Tilak Raj Singh Oberoi and Prithvi Raj Singh Oberoi (P.R.S. Oberoi
Thought 2: The Oberoi Group has its head office in New Delhi, India. I just need to finish with New Delhi.
Action 2: Finish[New Delhi]
Observation 2: Episode finished, reward = 0
Reflection: I appeared to have retrieved the correct information about The Oberoi Family and the location of it's head office, and provided a corresponding answer. However this answer does not exactly match the ground truth answer so I should try a different wording, such as Delhi.
Previous trial:
{trajectory}Reflection:'''
cot_prompt = '''
Solve a question answering task with interleaving Thought, Action, Observation steps. Thought can reason about the current situation, and Action can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
After each observation, provide the next Thought and next Action. Here are some examples:
Question: What is the elevation range for the area that the eastern sector of the Colorado orogeny extends into?
Thought 1: I need to search Colorado orogeny, find the area that the eastern sector of the Colorado orogeny extends into, then find the elevation range of the area.
Action 1: Search[Colorado orogeny]
Observation 1: The Colorado orogeny was an episode of mountain building (an orogeny) in Colorado and surrounding areas. This took place from 1780 to 1650 million years ago (Mya), during the Paleoproterozoic (Statherian Period). It is recorded in the Colorado orogen, a >500-km-wide belt of oceanic arc rock that extends southward into New Mexico. The Colorado orogeny was likely part of the larger Yavapai orogeny.
Thought 2: It does not mention the eastern sector of the Colorado orogeny. I need to look up eastern sector.
Action 2: Lookup[eastern sector]
Observation 2: (Result 1 / 1) The Colorado orogen, formerly called the Colorado province, is a >500-km-wide belt of oceanic arc rock (1.78\u20131.65 Ga) that extends southward into New Mexico and composes a major part of the Proterozoic provinces of southwestern United States. This transcontinental collisional event occurred during the Paleoproterozoic (Statherian Period).[1] The Wyoming sector of the Colorado orogeny was formerly called the Medicine Bow orogeny. The eastern sector extends into the High Plains and is called the Central Plains orogeny. The boundary between the Colorado orogeny and the Wyoming craton is the Cheyenne belt, a 5-km-wide mylonitic shear zone that verges northward. The Cheyenne belt transects and cuts off the south edge of the older Trans-Hudson orogeny.[2]
Thought 3: The eastern sector of Colorado orogeny extends into the High Plains, so High Plains is the area. I need to search High Plains and find its elevation range.
Action 3: Search[High Plains]Observation 3: High Plains refers to one of two distinct land regions:
Thought 4: I need to search High Plains (United States).
Action 4: Search[High Plains (United States)]
Observation 4: The High Plains are a subregion of the Great Plains, mainly in the Western United States, but also partly in the Midwest states of Nebraska, Kansas, and South Dakota, generally encompassing the western part of the Great Plains before the region reaches the Rocky Mountains. The High Plains are located in eastern Montana, southeastern Wyoming, southwestern South Dakota, western Nebraska, eastern Colorado, western Kansas, eastern New Mexico, western Oklahoma, and to just south of the Texas Panhandle.[4] The southern region of the Western High Plains ecology region contains the geological formation known as Llano Estacado which can be seen from a short distance or on satellite maps.[5] From east to west, the High Plains rise in elevation from around 1,800 to 7,000 ft (550 to 2,130 m).[3]
Thought 5: High Plains rise in elevation from around 1,800 to 7,000 ft, so the answer is 1,800 to 7,000 ft.
Action 5: Finish[1,800 to 7,000 ft]
Question: Guitars for Wounded Warriors is an album that was recorded in the village in which New York county?
Thought 1: I need to search Guitars for Wounded Warriors, then find in which New York county it was recorded.
Action 1: Search[Guitars for Wounded Warriors]
Observation 1: Guitars for Wounded Warriors is the sixth solo studio album by guitarist Brian Tarquin, released in August 2014 by Cleopatra Records. In 2016, it received a Best Compilation Album nomination by the Independent Music Awards. All tracks were recorded at Tarquin's Jungle Room Studios in New Paltz (village), New York. Being moved by the lack of support for returning veterans through his life Tarquin decided to compose a heavy instrumental rock album as a way to show his appreciation to all veterans. So once again he enlisted top notch players to guest with him on the album, Billy Sheehan on Black Hawk, Ron \"Bumblefoot\" Thal and Reb Beach on Taliban Terror, Steve Morse on Freedom, Chris Poland on Charlie Surfs and Hunting, Chuck Loeb on Escape Kabul, Hal Lindes on Sand & Blood, Gary Hoey on 5 Klicks To Hell and Baghdad, Alex De Rosso Dokken on Broken Arrow, and The Flyin' Ryan Brothers on Surgical Strike. The entire album was engineered, produced and composed by Tarquin especially for each one of the guest guitarists. Partial proceeds are donated to the Fisher House Foundation from sales.
Thought 2: Guitars for Wounded Warriors was recorded in New Paltz (village), New York. I need to search New Paltz (village), New York and find which county it is in
Action 2: Search[New Paltz (village), New York]
Observation 2: New Paltz is a village in Ulster County located in the U.S. state of New York. It is approximately 80 miles (130 km) north of New York City and 70 miles (110 km) south of Albany. The population was 7,324 at the 2020 census.[3]
Thought 3: New Paltz (village), New York is in Ulster County, so the answer is Ulster County.
Action 3: Finish[Ulster County]
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Observation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.
Thought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up "named after".
Action 2: Lookup[named after]
Observation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[President Richard Nixon]
{input}
'''
cot_prompt_short = '''
Solve a question answering task with interleaving Thought, Action, Observation steps. Thought can reason about the current situation, and Action can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
After each observation, provide the next Thought and next Action. Here are some examples:
Question: What is the elevation range for the area that the eastern sector of the Colorado orogeny extends into?
Thought 1: I need to search Colorado orogeny, find the area that the eastern sector of the Colorado orogeny extends into, then find the elevation range of the area.
Action 1: Search[Colorado orogeny]
Observation 1: The Colorado orogeny was an episode of mountain building (an orogeny) in Colorado and surrounding areas. This took place from 1780 to 1650 million years ago (Mya), during the Paleoproterozoic (Statherian Period). It is recorded in the Colorado orogen, a >500-km-wide belt of oceanic arc rock that extends southward into New Mexico. The Colorado orogeny was likely part of the larger Yavapai orogeny.
Thought 2: It does not mention the eastern sector of the Colorado orogeny. I need to look up eastern sector.
Action 2: Lookup[eastern sector]
Observation 2: (Result 1 / 1) The Colorado orogen, formerly called the Colorado province, is a >500-km-wide belt of oceanic arc rock (1.78\u20131.65 Ga) that extends southward into New Mexico and composes a major part of the Proterozoic provinces of southwestern United States. This transcontinental collisional event occurred during the Paleoproterozoic (Statherian Period).[1] The Wyoming sector of the Colorado orogeny was formerly called the Medicine Bow orogeny. The eastern sector extends into the High Plains and is called the Central Plains orogeny. The boundary between the Colorado orogeny and the Wyoming craton is the Cheyenne belt, a 5-km-wide mylonitic shear zone that verges northward. The Cheyenne belt transects and cuts off the south edge of the older Trans-Hudson orogeny.[2]
Thought 3: The eastern sector of Colorado orogeny extends into the High Plains, so High Plains is the area. I need to search High Plains and find its elevation range.
Action 3: Search[High Plains]Observation 3: High Plains refers to one of two distinct land regions:
Thought 4: I need to search High Plains (United States).
Action 4: Search[High Plains (United States)]
Observation 4: The High Plains are a subregion of the Great Plains, mainly in the Western United States, but also partly in the Midwest states of Nebraska, Kansas, and South Dakota, generally encompassing the western part of the Great Plains before the region reaches the Rocky Mountains. The High Plains are located in eastern Montana, southeastern Wyoming, southwestern South Dakota, western Nebraska, eastern Colorado, western Kansas, eastern New Mexico, western Oklahoma, and to just south of the Texas Panhandle.[4] The southern region of the Western High Plains ecology region contains the geological formation known as Llano Estacado which can be seen from a short distance or on satellite maps.[5] From east to west, the High Plains rise in elevation from around 1,800 to 7,000 ft (550 to 2,130 m).[3]
Thought 5: High Plains rise in elevation from around 1,800 to 7,000 ft, so the answer is 1,800 to 7,000 ft.
Action 5: Finish[1,800 to 7,000 ft]
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Observation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.
Thought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up "named after".
Action 2: Lookup[named after]
Observation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[President Richard Nixon]
{input}
'''
cot_prompt_feedback_short = '''You are also an advanced reasoning agent that can improve based on self refection. Solve a question answering task with interleaving Thought, Action, Observation steps. Thought can reason about the current situation, and Action can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
After each observation, provide the next Thought and next Action. Here are some examples:
Question: What is the elevation range for the area that the eastern sector of the Colorado orogeny extends into?
Thought 1: I need to search Colorado orogeny, find the area that the eastern sector of the Colorado orogeny extends into, then find the elevation range of the area.
Action 1: Search[Colorado orogeny]
Observation 1: The Colorado orogeny was an episode of mountain building (an orogeny) in Colorado and surrounding areas. This took place from 1780 to 1650 million years ago (Mya), during the Paleoproterozoic (Statherian Period). It is recorded in the Colorado orogen, a >500-km-wide belt of oceanic arc rock that extends southward into New Mexico. The Colorado orogeny was likely part of the larger Yavapai orogeny.
Thought 2: It does not mention the eastern sector of the Colorado orogeny. I need to look up eastern sector.
Action 2: Lookup[eastern sector]
Observation 2: (Result 1 / 1) The Colorado orogen, formerly called the Colorado province, is a >500-km-wide belt of oceanic arc rock (1.78\u20131.65 Ga) that extends southward into New Mexico and composes a major part of the Proterozoic provinces of southwestern United States. This transcontinental collisional event occurred during the Paleoproterozoic (Statherian Period).[1] The Wyoming sector of the Colorado orogeny was formerly called the Medicine Bow orogeny. The eastern sector extends into the High Plains and is called the Central Plains orogeny. The boundary between the Colorado orogeny and the Wyoming craton is the Cheyenne belt, a 5-km-wide mylonitic shear zone that verges northward. The Cheyenne belt transects and cuts off the south edge of the older Trans-Hudson orogeny.[2]
Thought 3: The eastern sector of Colorado orogeny extends into the High Plains, so High Plains is the area. I need to search High Plains and find its elevation range.
Action 3: Search[High Plains]Observation 3: High Plains refers to one of two distinct land regions:
Thought 4: I need to search High Plains (United States).
Action 4: Search[High Plains (United States)]
Observation 4: The High Plains are a subregion of the Great Plains, mainly in the Western United States, but also partly in the Midwest states of Nebraska, Kansas, and South Dakota, generally encompassing the western part of the Great Plains before the region reaches the Rocky Mountains. The High Plains are located in eastern Montana, southeastern Wyoming, southwestern South Dakota, western Nebraska, eastern Colorado, western Kansas, eastern New Mexico, western Oklahoma, and to just south of the Texas Panhandle.[4] The southern region of the Western High Plains ecology region contains the geological formation known as Llano Estacado which can be seen from a short distance or on satellite maps.[5] From east to west, the High Plains rise in elevation from around 1,800 to 7,000 ft (550 to 2,130 m).[3]
Thought 5: High Plains rise in elevation from around 1,800 to 7,000 ft, so the answer is 1,800 to 7,000 ft.
Action 5: Finish[1,800 to 7,000 ft]
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Observation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.
Thought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up "named after".
Action 2: Lookup[named after]
Observation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[President Richard Nixon]
You have attempted to answer the following question before and failed. The following reflection(s) give a plan to avoid failing to answer the question in the same way you did previously. Use them to improve your strategy of correctly answering the given question.
{trajectories}
{input}
'''
cot_prompt_feedback = '''You are also an advanced reasoning agent that can improve based on self refection. Solve a question answering task with interleaving Thought, Action, Observation steps. Thought can reason about the current situation, and Action can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
After each observation, provide the next Thought and next Action. Here are some examples:
Question: What is the elevation range for the area that the eastern sector of the Colorado orogeny extends into?
Thought 1: I need to search Colorado orogeny, find the area that the eastern sector of the Colorado orogeny extends into, then find the elevation range of the area.
Action 1: Search[Colorado orogeny]
Observation 1: The Colorado orogeny was an episode of mountain building (an orogeny) in Colorado and surrounding areas. This took place from 1780 to 1650 million years ago (Mya), during the Paleoproterozoic (Statherian Period). It is recorded in the Colorado orogen, a >500-km-wide belt of oceanic arc rock that extends southward into New Mexico. The Colorado orogeny was likely part of the larger Yavapai orogeny.
Thought 2: It does not mention the eastern sector of the Colorado orogeny. I need to look up eastern sector.
Action 2: Lookup[eastern sector]
Observation 2: (Result 1 / 1) The Colorado orogen, formerly called the Colorado province, is a >500-km-wide belt of oceanic arc rock (1.78\u20131.65 Ga) that extends southward into New Mexico and composes a major part of the Proterozoic provinces of southwestern United States. This transcontinental collisional event occurred during the Paleoproterozoic (Statherian Period).[1] The Wyoming sector of the Colorado orogeny was formerly called the Medicine Bow orogeny. The eastern sector extends into the High Plains and is called the Central Plains orogeny. The boundary between the Colorado orogeny and the Wyoming craton is the Cheyenne belt, a 5-km-wide mylonitic shear zone that verges northward. The Cheyenne belt transects and cuts off the south edge of the older Trans-Hudson orogeny.[2]
Thought 3: The eastern sector of Colorado orogeny extends into the High Plains, so High Plains is the area. I need to search High Plains and find its elevation range.
Action 3: Search[High Plains]Observation 3: High Plains refers to one of two distinct land regions:
Thought 4: I need to search High Plains (United States).
Action 4: Search[High Plains (United States)]
Observation 4: The High Plains are a subregion of the Great Plains, mainly in the Western United States, but also partly in the Midwest states of Nebraska, Kansas, and South Dakota, generally encompassing the western part of the Great Plains before the region reaches the Rocky Mountains. The High Plains are located in eastern Montana, southeastern Wyoming, southwestern South Dakota, western Nebraska, eastern Colorado, western Kansas, eastern New Mexico, western Oklahoma, and to just south of the Texas Panhandle.[4] The southern region of the Western High Plains ecology region contains the geological formation known as Llano Estacado which can be seen from a short distance or on satellite maps.[5] From east to west, the High Plains rise in elevation from around 1,800 to 7,000 ft (550 to 2,130 m).[3]
Thought 5: High Plains rise in elevation from around 1,800 to 7,000 ft, so the answer is 1,800 to 7,000 ft.
Action 5: Finish[1,800 to 7,000 ft]
Question: Guitars for Wounded Warriors is an album that was recorded in the village in which New York county?
Thought 1: I need to search Guitars for Wounded Warriors, then find in which New York county it was recorded.
Action 1: Search[Guitars for Wounded Warriors]
Observation 1: Guitars for Wounded Warriors is the sixth solo studio album by guitarist Brian Tarquin, released in August 2014 by Cleopatra Records. In 2016, it received a Best Compilation Album nomination by the Independent Music Awards. All tracks were recorded at Tarquin's Jungle Room Studios in New Paltz (village), New York. Being moved by the lack of support for returning veterans through his life Tarquin decided to compose a heavy instrumental rock album as a way to show his appreciation to all veterans. So once again he enlisted top notch players to guest with him on the album, Billy Sheehan on Black Hawk, Ron \"Bumblefoot\" Thal and Reb Beach on Taliban Terror, Steve Morse on Freedom, Chris Poland on Charlie Surfs and Hunting, Chuck Loeb on Escape Kabul, Hal Lindes on Sand & Blood, Gary Hoey on 5 Klicks To Hell and Baghdad, Alex De Rosso Dokken on Broken Arrow, and The Flyin' Ryan Brothers on Surgical Strike. The entire album was engineered, produced and composed by Tarquin especially for each one of the guest guitarists. Partial proceeds are donated to the Fisher House Foundation from sales.
Thought 2: Guitars for Wounded Warriors was recorded in New Paltz (village), New York. I need to search New Paltz (village), New York and find which county it is in
Action 2: Search[New Paltz (village), New York]
Observation 2: New Paltz is a village in Ulster County located in the U.S. state of New York. It is approximately 80 miles (130 km) north of New York City and 70 miles (110 km) south of Albany. The population was 7,324 at the 2020 census.[3]
Thought 3: New Paltz (village), New York is in Ulster County, so the answer is Ulster County.
Action 3: Finish[Ulster County]
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Observation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.
Thought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up "named after".
Action 2: Lookup[named after]
Observation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[President Richard Nixon]
You have attempted to answer the following question before and failed, either because your reasoning for the answer was incorrect or the phrasing of your response did not exactly match the answer. The following reflection(s) give a plan to avoid failing to answer the question in the same way you did previously. Use them to improve your strategy of correctly answering the given question.
{trajectories}
When providing the thought and action for the current trial, that into account these failed trajectories and make sure not to repeat the same mistakes and incorrect answers.
{input}
'''
vote_prompt = '''Analyze the trajectories of a solution to a question answering task. The trajectories are labeled by pairs of thoughts that can reason about the current situation and actions that can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Given a question and a list of trajectories, decide which trajectory is most promising. Analyze each trajectory in detail and consider possible errors, then conclude in the last line "The best trajectory is {s}", where s the integer id of the trajectory.
'''
compare_prompt = '''Analyze the trajectories of a solution to a question answering task. The trajectories are labeled by pairs of thoughts that can reason about the current situation and actions that can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Briefly analyze the correctness of the following two trajectories. Conclude in the last line "The more correct trajectory is 1", "The more correct trajectory is 2", or "The two trajectories are similarly correct".
'''
score_prompt = '''Analyze the trajectories of a solution to a question answering task. The trajectories are labeled by pairs of thoughts that can reason about the current situation and actions that can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Given a question and a trajectory, analyze the following trajectory, then at the last line conclude "Thus the correctness score is {s}", where s is an integer from 1 to 10.
'''
value_prompt = '''Analyze the trajectories of a solution to a question answering task. The trajectories are labeled by environmental observations about the situation, thoughts that can reason about the current situation and actions that can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Given a question and a trajectory, evaluate its correctness and provide your reasoning and analysis in detail. Focus on the latest thought, action, and observation. Incomplete trajectories can be correct if the thoughts and actions so far are correct, even if the answer is not found yet. Do not generate additional thoughts or actions. Then at the last line conclude "Thus the correctness score is {s}", where s is an integer from 1 to 10.
Question: Which other Mexican Formula One race car driver has held the podium besides the Force India driver born in 1990?
Thought 1: I need to search for a list of Mexican Formula One race car drivers, then eliminate the one who drove for Force India and was born in 1990.
Action 1: Search[Formula One drivers from Mexico]
Observation 1: There have been six Formula One drivers from Mexico who have taken part in races since the championship began in 1950. Sergio P\u00e9rez is the most successful, having won six Grands Prix. Since 2021, P\u00e9rez drives for the Red Bull team.. P\u00e9rez is the only Mexican F1 driver to achieve a pole position. He took his first pole position at the 2022 Saudi Arabian Grand Prix, in his 219th Grand Prix meeting (a record for the most Grands Prix before a pole).
Thought 2: Sergio P\u00e9rez, born in 1990 and drove for Force India, is not the Mexican driver we are looking for. The passage does not give me enough information about other Mexican drivers who have achieved a podium finish. I need to look up more information.
Action 2: Lookup[Formula One drivers from Mexico]
Observation 2: No more results.
Thought 3: The available information doesn't allow me to determine which other Mexican Formula One race car driver, besides Sergio P\u00e9rez, has held the podium. With the search function failing to provide a full list of Mexican Formula One drivers, I need to return different search results. Let's try searching for Mexican Grand Prix winners, as they would have held the podium.
Action 3: Search[Mexican Grand Prix winners]
Observation 3: Could not find Mexican Grand Prix winners. Similar: ['Mexican Grand Prix', 'List of Formula One Grand Prix winners', '1990 Mexican Grand Prix', '2018 Mexican Grand Prix', '2019 Mexican Grand Prix'].
Thought 4: Given the difficulties in finding a direct list of Mexican Grand Prix winners, I should search for the Mexican Grand Prix to get a broader picture of the race's history. This might include winners.
Action 4: Search[Mexican Grand Prix]
Thus the correctness score is 3
Question: The football manager who recruited David Beckham managed Manchester United during what timeframe?Question: The football manager who recruited David Beckham managed Manchester United during what timeframe?
Thought 1: I need to search for the football manager who recruited David Beckham, and then find out the timeframe in which he managed Manchester United.
Action 1: Search[David Beckham's football manager]
Observation 1: Could not find David Beckham's football manager. Similar: ['David Beckham', 'Inter Miami CF (redirect from Miami Beckham United)', 'Victoria Beckham', 'The Beckham Experiment', 'Miami Freedom Park'].
Thought 2: I couldn't find the information on David Beckham's football manager. I need to search Manchester United and find out the timeframe of the manager.
Action 2: Search[Manchester United]
Observation 2: Manchester United Football Club, commonly referred to as Man United (often stylised as Man Utd), or simply United, is a professional football club based in Old Trafford, Greater Manchester, England. The club competes in the Premier League, the top division in the English football league system. Nicknamed the Red Devils, they were founded as Newton Heath LYR Football Club in 1878, but changed their name to Manchester United in 1902. After a spell playing in Clayton, Manchester, the club moved to their current stadium, Old Trafford, in 1910.. Domestically, Manchester United have won a record 20 league titles, 12 FA Cups, six League Cups and a record 21 FA Community Shields.
Thought 3: The information about David Beckham's football manager is not available. I will search for Manchester United's managers to find the timeframe.
Action 3: Search[Manchester United managers]
Observation 3: Manchester United Football Club is a professional football club based in Old Trafford, Greater Manchester, England. The club was formed in Newton Heath in 1878 as Newton Heath LYR F.C., and played their first competitive match in October 1886, when they entered the First Round of the 1886–87 FA Cup. The club was renamed Manchester United F.C. in 1902, and moved to Old Trafford in 1910.. From the beginning of the club's official managerial records in 1892 to the start of the 2022–23 season, Manchester United have had 23 full-time managers.
Thought 4: The information about David Beckham's football manager is not available. The question asks for the timeframe when the manager managed Manchester United, so I need to find a list of Manchester United managers.
Action 4: Search[list of Manchester United managers]
Observation 4: Manchester United Football Club is a professional football club based in Old Trafford, Greater Manchester, England. The club was formed in Newton Heath in 1878 as Newton Heath LYR F.C., and played their first competitive match in October 1886, when they entered the First Round of the 1886–87 FA Cup. The club was renamed Manchester United F.C. in 1902, and moved to Old Trafford in 1910.. From the beginning of the club's official managerial records in 1892 to the start of the 2022–23 season, Manchester United have had 23 full-time managers.
Thus the correctness score is 4
Question: Which magazine was started first Arthur's Magazine or First for Women?
Thought 1: I need to search Arthur's Magazine and First for Women, and find which was started first.
Action 1: Search[Arthur's Magazine]
Observation 1: Arthur's Magazine (1844\u00e2\u0080\u00931846) was an American literary periodical published in Philadelphia in the 19th century. Edited by Timothy Shay Arthur, it featured work by Edgar A. Poe, J.H. Ingraham, Sarah Josepha Hale, Thomas G. Spear, and others.[1][2] In May 1846 it was merged into Godey's Lady's Book.[3]
Thus the correctness score is 10
{input}
'''
value_prompt_feedback = '''Analyze the trajectories of a solution to a question answering task. The trajectories are labeled by environmental observations about the situation, thoughts that can reason about the current situation and actions that can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Given a question and a trajectory, evaluate its correctness and provide your reasoning and analysis in detail. Focus on the latest thought, action, and observation. Incomplete trajectories can be correct if the thoughts and actions so far are correct, even if the answer is not found yet. Do not generate additional thoughts or actions. Then at the last line conclude "Thus the correctness score is {s}", where s is an integer from 1 to 10.
Question: Which other Mexican Formula One race car driver has held the podium besides the Force India driver born in 1990?
Thought 1: I need to search for a list of Mexican Formula One race car drivers, then eliminate the one who drove for Force India and was born in 1990.
Action 1: Search[Formula One drivers from Mexico]
Observation 1: There have been six Formula One drivers from Mexico who have taken part in races since the championship began in 1950. Sergio P\u00e9rez is the most successful, having won six Grands Prix. Since 2021, P\u00e9rez drives for the Red Bull team.. P\u00e9rez is the only Mexican F1 driver to achieve a pole position. He took his first pole position at the 2022 Saudi Arabian Grand Prix, in his 219th Grand Prix meeting (a record for the most Grands Prix before a pole).
Thought 2: Sergio P\u00e9rez, born in 1990 and drove for Force India, is not the Mexican driver we are looking for. The passage does not give me enough information about other Mexican drivers who have achieved a podium finish. I need to look up more information.
Action 2: Lookup[Formula One drivers from Mexico]
Observation 2: No more results.
Thought 3: The available information doesn't allow me to determine which other Mexican Formula One race car driver, besides Sergio P\u00e9rez, has held the podium. With the search function failing to provide a full list of Mexican Formula One drivers, I need to return different search results. Let's try searching for Mexican Grand Prix winners, as they would have held the podium.
Action 3: Search[Mexican Grand Prix winners]
Observation 3: Could not find Mexican Grand Prix winners. Similar: ['Mexican Grand Prix', 'List of Formula One Grand Prix winners', '1990 Mexican Grand Prix', '2018 Mexican Grand Prix', '2019 Mexican Grand Prix'].
Thought 4: Given the difficulties in finding a direct list of Mexican Grand Prix winners, I should search for the Mexican Grand Prix to get a broader picture of the race's history. This might include winners.
Action 4: Search[Mexican Grand Prix]
Thus the correctness score is 3
Question: Which magazine was started first Arthur's Magazine or First for Women?
Thought 1: I need to search Arthur's Magazine and First for Women, and find which was started first.
Action 1: Search[Arthur's Magazine]
Observation 1: Arthur's Magazine (1844\u00e2\u0080\u00931846) was an American literary periodical published in Philadelphia in the 19th century. Edited by Timothy Shay Arthur, it featured work by Edgar A. Poe, J.H. Ingraham, Sarah Josepha Hale, Thomas G. Spear, and others.[1][2] In May 1846 it was merged into Godey's Lady's Book.[3]
Thus the correctness score is 10
{trajectories}
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Observation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.
Thought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up "named after".
Action 2: Lookup[named after]
Observation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[President Richard Nixon]
Thus the correctness score is 10
{input}
'''
value_prompt_reasoning = '''You are an advanced reasoning agent that can improve based on self refection. Analyze the trajectories of your previous solutions to a question answering task. The trajectories are labeled by environmental observations about the situation, thoughts that can reason about the current situation and actions that can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Given a question and a trajectory, evaluate its correctness and provide your reasoning and analysis in detail. Focus on the latest thought, action, and observation. Incomplete trajectories can be correct if the thoughts and actions so far are correct, even if the answer is not found yet. Do not generate additional thoughts or actions. Then at the last line conclude "Thus the correctness score is {s}", where s is an integer from 1 to 10.
Question: Which other Mexican Formula One race car driver has held the podium besides the Force India driver born in 1990?
Thought 1: I need to search for a list of Mexican Formula One race car drivers, then eliminate the one who drove for Force India and was born in 1990.
Action 1: Search[Formula One drivers from Mexico]
Observation 1: There have been six Formula One drivers from Mexico who have taken part in races since the championship began in 1950. Sergio P\u00e9rez is the most successful, having won six Grands Prix. Since 2021, P\u00e9rez drives for the Red Bull team.. P\u00e9rez is the only Mexican F1 driver to achieve a pole position. He took his first pole position at the 2022 Saudi Arabian Grand Prix, in his 219th Grand Prix meeting (a record for the most Grands Prix before a pole).
Thought 2: Sergio P\u00e9rez, born in 1990 and drove for Force India, is not the Mexican driver we are looking for. The passage does not give me enough information about other Mexican drivers who have achieved a podium finish. I need to look up more information.
Action 2: Lookup[Formula One drivers from Mexico]
Observation 2: No more results.
Thought 3: The available information doesn't allow me to determine which other Mexican Formula One race car driver, besides Sergio P\u00e9rez, has held the podium. With the search function failing to provide a full list of Mexican Formula One drivers, I need to return different search results. Let's try searching for Mexican Grand Prix winners, as they would have held the podium.
Action 3: Search[Mexican Grand Prix winners]
Observation 3: Could not find Mexican Grand Prix winners. Similar: ['Mexican Grand Prix', 'List of Formula One Grand Prix winners', '1990 Mexican Grand Prix', '2018 Mexican Grand Prix', '2019 Mexican Grand Prix'].
Thought 4: Given the difficulties in finding a direct list of Mexican Grand Prix winners, I should search for the Mexican Grand Prix to get a broader picture of the race's history. This might include winners.
Action 4: Search[Mexican Grand Prix]
This trajectory is incorrect as my search should be related to Mexican Formula One race car drivers, not winners of the Mexican Grand Prix, a seperate event. A better search would have been for the List of Formula One Grand Prix winners, as suggested.
Thus the correctness score is 3
Question: Which magazine was started first Arthur's Magazine or First for Women?
Thought 1: I need to search Arthur's Magazine and First for Women, and find which was started first.
Action 1: Search[Arthur's Magazine]
Observation 1: Arthur's Magazine (1844\u00e2\u0080\u00931846) was an American literary periodical published in Philadelphia in the 19th century. Edited by Timothy Shay Arthur, it featured work by Edgar A. Poe, J.H. Ingraham, Sarah Josepha Hale, Thomas G. Spear, and others.[1][2] In May 1846 it was merged into Godey's Lady's Book.[3]
This trajectory is correct as it is reasonable to search for the first magazine provided in the question. It is also better to have simple searches corresponding to a single entity, making this the best action.
Thus the correctness score is 10
Question: The football manager who recruited David Beckham managed Manchester United during what timeframe?Question: The football manager who recruited David Beckham managed Manchester United during what timeframe?
Thought 1: I need to search for the football manager who recruited David Beckham, and then find out the timeframe in which he managed Manchester United.
Action 1: Search[David Beckham's football manager]
Observation 1: Could not find David Beckham's football manager. Similar: ['David Beckham', 'Inter Miami CF (redirect from Miami Beckham United)', 'Victoria Beckham', 'The Beckham Experiment', 'Miami Freedom Park'].
Thought 2: I couldn't find the information on David Beckham's football manager. I need to search Manchester United and find out the timeframe of the manager.
Action 2: Search[Manchester United]
Observation 2: Manchester United Football Club, commonly referred to as Man United (often stylised as Man Utd), or simply United, is a professional football club based in Old Trafford, Greater Manchester, England. The club competes in the Premier League, the top division in the English football league system. Nicknamed the Red Devils, they were founded as Newton Heath LYR Football Club in 1878, but changed their name to Manchester United in 1902. After a spell playing in Clayton, Manchester, the club moved to their current stadium, Old Trafford, in 1910.. Domestically, Manchester United have won a record 20 league titles, 12 FA Cups, six League Cups and a record 21 FA Community Shields.
Thought 3: The information about David Beckham's football manager is not available. I will search for Manchester United's managers to find the timeframe.
Action 3: Search[Manchester United managers]
Observation 3: Manchester United Football Club is a professional football club based in Old Trafford, Greater Manchester, England. The club was formed in Newton Heath in 1878 as Newton Heath LYR F.C., and played their first competitive match in October 1886, when they entered the First Round of the 1886–87 FA Cup. The club was renamed Manchester United F.C. in 1902, and moved to Old Trafford in 1910.. From the beginning of the club's official managerial records in 1892 to the start of the 2022–23 season, Manchester United have had 23 full-time managers.
Thought 4: The information about David Beckham's football manager is not available. The question asks for the timeframe when the manager managed Manchester United, so I need to find a list of Manchester United managers.
Action 4: Search[list of Manchester United managers]
Observation 4: Manchester United Football Club is a professional football club based in Old Trafford, Greater Manchester, England. The club was formed in Newton Heath in 1878 as Newton Heath LYR F.C., and played their first competitive match in October 1886, when they entered the First Round of the 1886–87 FA Cup. The club was renamed Manchester United F.C. in 1902, and moved to Old Trafford in 1910.. From the beginning of the club's official managerial records in 1892 to the start of the 2022–23 season, Manchester United have had 23 full-time managers.
This trajectory is mostly incorrect as I was not able to retrieve the relevant information to answer the question. The searches are too broad and not relevant to the specific player recruited, David Beckham. The last two actions are also too similar. It would be better to first search for David Beckham and lookup information related to his manager.
Thus the correctness score is 4
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Observation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.
Thought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up "named after".
Action 2: Lookup[named after]
Observation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[President Richard Nixon]
This trajectory is correct as all of my thoughts and actions are correct. It makes sense to search for Milhouse first as it is the central subject of the question. It is also correct to directly look up the relevant information in the article, instead of trying another search.
Thus the correctness score is 10
{input}
'''
value_prompt_reasoning_feedback = '''Analyze the trajectories of a solution to a question answering task. The trajectories are labeled by environmental observations about the situation, thoughts that can reason about the current situation and actions that can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Given a question and a trajectory, evaluate its correctness and provide your reasoning and analysis in detail. Focus on the latest thought, action, and observation. Incomplete trajectories can be correct if the thoughts and actions so far are correct, even if the answer is not found yet. Do not generate additional thoughts or actions. Then at the last line conclude "Thus the correctness score is {s}", where s is an integer from 1 to 10.
Question: Which other Mexican Formula One race car driver has held the podium besides the Force India driver born in 1990?
Thought 1: I need to search for a list of Mexican Formula One race car drivers, then eliminate the one who drove for Force India and was born in 1990.
Action 1: Search[Formula One drivers from Mexico]
Observation 1: There have been six Formula One drivers from Mexico who have taken part in races since the championship began in 1950. Sergio P\u00e9rez is the most successful, having won six Grands Prix. Since 2021, P\u00e9rez drives for the Red Bull team.. P\u00e9rez is the only Mexican F1 driver to achieve a pole position. He took his first pole position at the 2022 Saudi Arabian Grand Prix, in his 219th Grand Prix meeting (a record for the most Grands Prix before a pole).
Thought 2: Sergio P\u00e9rez, born in 1990 and drove for Force India, is not the Mexican driver we are looking for. The passage does not give me enough information about other Mexican drivers who have achieved a podium finish. I need to look up more information.
Action 2: Lookup[Formula One drivers from Mexico]
Observation 2: No more results.
Thought 3: The available information doesn't allow me to determine which other Mexican Formula One race car driver, besides Sergio P\u00e9rez, has held the podium. With the search function failing to provide a full list of Mexican Formula One drivers, I need to return different search results. Let's try searching for Mexican Grand Prix winners, as they would have held the podium.
Action 3: Search[Mexican Grand Prix winners]
Observation 3: Could not find Mexican Grand Prix winners. Similar: ['Mexican Grand Prix', 'List of Formula One Grand Prix winners', '1990 Mexican Grand Prix', '2018 Mexican Grand Prix', '2019 Mexican Grand Prix'].
Thought 4: Given the difficulties in finding a direct list of Mexican Grand Prix winners, I should search for the Mexican Grand Prix to get a broader picture of the race's history. This might include winners.
Action 4: Search[Mexican Grand Prix]
This trajectory is incorrect as my search should be related to Mexican Formula One race car drivers, not winners it is reasonable to checkof the Mexican Grand Prix, a seperate event. A better search would have been for the List of Formula One Grand Prix winners, as suggested.
Thus the correctness score is 3
Question: Which magazine was started first Arthur's Magazine or First for Women?
Thought 1: I need to search Arthur's Magazine and First for Women, and find which was started first.
Action 1: Search[Arthur's Magazine]
Observation 1: Arthur's Magazine (1844\u00e2\u0080\u00931846) was an American literary periodical published in Philadelphia in the 19th century. Edited by Timothy Shay Arthur, it featured work by Edgar A. Poe, J.H. Ingraham, Sarah Josepha Hale, Thomas G. Spear, and others.[1][2] In May 1846 it was merged into Godey's Lady's Book.[3]
This trajectory is correct as it is reasonable to search for the first magazine provided in the question. It is also better to have simple searches corresponding to a single entity, making this the best action.
Thus the correctness score is 10
Question: The football manager who recruited David Beckham managed Manchester United during what timeframe?Question: The football manager who recruited David Beckham managed Manchester United during what timeframe?
Thought 1: I need to search for the football manager who recruited David Beckham, and then find out the timeframe in which he managed Manchester United.
Action 1: Search[David Beckham's football manager]
Observation 1: Could not find David Beckham's football manager. Similar: ['David Beckham', 'Inter Miami CF (redirect from Miami Beckham United)', 'Victoria Beckham', 'The Beckham Experiment', 'Miami Freedom Park'].
Thought 2: I couldn't find the information on David Beckham's football manager. I need to search Manchester United and find out the timeframe of the manager.
Action 2: Search[Manchester United]
Observation 2: Manchester United Football Club, commonly referred to as Man United (often stylised as Man Utd), or simply United, is a professional football club based in Old Trafford, Greater Manchester, England. The club competes in the Premier League, the top division in the English football league system. Nicknamed the Red Devils, they were founded as Newton Heath LYR Football Club in 1878, but changed their name to Manchester United in 1902. After a spell playing in Clayton, Manchester, the club moved to their current stadium, Old Trafford, in 1910.. Domestically, Manchester United have won a record 20 league titles, 12 FA Cups, six League Cups and a record 21 FA Community Shields.
Thought 3: The information about David Beckham's football manager is not available. I will search for Manchester United's managers to find the timeframe.
Action 3: Search[Manchester United managers]
Observation 3: Manchester United Football Club is a professional football club based in Old Trafford, Greater Manchester, England. The club was formed in Newton Heath in 1878 as Newton Heath LYR F.C., and played their first competitive match in October 1886, when they entered the First Round of the 1886–87 FA Cup. The club was renamed Manchester United F.C. in 1902, and moved to Old Trafford in 1910.. From the beginning of the club's official managerial records in 1892 to the start of the 2022–23 season, Manchester United have had 23 full-time managers.
Thought 4: The information about David Beckham's football manager is not available. The question asks for the timeframe when the manager managed Manchester United, so I need to find a list of Manchester United managers.
Action 4: Search[list of Manchester United managers]
Observation 4: Manchester United Football Club is a professional football club based in Old Trafford, Greater Manchester, England. The club was formed in Newton Heath in 1878 as Newton Heath LYR F.C., and played their first competitive match in October 1886, when they entered the First Round of the 1886–87 FA Cup. The club was renamed Manchester United F.C. in 1902, and moved to Old Trafford in 1910.. From the beginning of the club's official managerial records in 1892 to the start of the 2022–23 season, Manchester United have had 23 full-time managers.
This trajectory is mostly incorrect as I was not able to retrieve the relevant information to answer the question. The searches are too broad and not relevant to the specific player recruited, David Beckham. The last two actions are also too similar. It would be better to first search for David Beckham and lookup information related to his manager.
Thus the correctness score is 4
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Observation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.
Thought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up "named after".
Action 2: Lookup[named after]
Observation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[President Richard Nixon]
This trajectory is correct as all of my thoughts and actions are correct. It makes sense to search for Milhouse first as it is the central subject of the question. It is also correct to directly look up the relevant information in the article, instead of trying another search.
Thus the correctness score is 10
{trajectories}
{input}
'''
value_prompt_reasoning_feedback_short = '''Analyze the trajectories of a solution to a question answering task. The trajectories are labeled by environmental observations about the situation, thoughts that can reason about the current situation and actions that can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Given a question and a trajectory, evaluate its correctness and provide your reasoning and analysis in detail. Focus on the latest thought, action, and observation. Incomplete trajectories can be correct if the thoughts and actions so far are correct, even if the answer is not found yet. Do not generate additional thoughts or actions. Then at the last line conclude "Thus the correctness score is {s}", where s is an integer from 1 to 10.
Question: Which other Mexican Formula One race car driver has held the podium besides the Force India driver born in 1990?
Thought 1: I need to search for a list of Mexican Formula One race car drivers, then eliminate the one who drove for Force India and was born in 1990.
Action 1: Search[Formula One drivers from Mexico]
Observation 1: There have been six Formula One drivers from Mexico who have taken part in races since the championship began in 1950. Sergio P\u00e9rez is the most successful, having won six Grands Prix. Since 2021, P\u00e9rez drives for the Red Bull team.. P\u00e9rez is the only Mexican F1 driver to achieve a pole position. He took his first pole position at the 2022 Saudi Arabian Grand Prix, in his 219th Grand Prix meeting (a record for the most Grands Prix before a pole).
Thought 2: Sergio P\u00e9rez, born in 1990 and drove for Force India, is not the Mexican driver we are looking for. The passage does not give me enough information about other Mexican drivers who have achieved a podium finish. I need to look up more information.
Action 2: Lookup[Formula One drivers from Mexico]
Observation 2: No more results.
Thought 3: The available information doesn't allow me to determine which other Mexican Formula One race car driver, besides Sergio P\u00e9rez, has held the podium. With the search function failing to provide a full list of Mexican Formula One drivers, I need to return different search results. Let's try searching for Mexican Grand Prix winners, as they would have held the podium.
Action 3: Search[Mexican Grand Prix winners]
Observation 3: Could not find Mexican Grand Prix winners. Similar: ['Mexican Grand Prix', 'List of Formula One Grand Prix winners', '1990 Mexican Grand Prix', '2018 Mexican Grand Prix', '2019 Mexican Grand Prix'].
Thought 4: Given the difficulties in finding a direct list of Mexican Grand Prix winners, I should search for the Mexican Grand Prix to get a broader picture of the race's history. This might include winners.
Action 4: Search[Mexican Grand Prix]
This trajectory is incorrect as my search should be related to Mexican Formula One race car drivers, not winners of the Mexican Grand Prix, a seperate event. A better search would have been for the List of Formula One Grand Prix winners, as suggested.
Thus the correctness score is 3
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Observation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.
Thought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up "named after".
Action 2: Lookup[named after]
Observation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[President Richard Nixon]
This trajectory is correct as all of my thoughts and actions are correct. It makes sense to search for Milhouse first as it is the central subject of the question. It is also correct to directly look up the relevant information in the article, instead of trying another search.
Thus the correctness score is 10
{trajectories}
{input}
'''
rap_prompt = '''
Solve a question answering task with interleaving Thought and Action steps. Thought can reason about the current situation, and Action can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Provide the next Thought and next Action. Here are some examples:
Question: What is the elevation range for the area that the eastern sector of the Colorado orogeny extends into?
Thought 1: I need to search Colorado orogeny, find the area that the eastern sector of the Colorado orogeny extends into, then find the elevation range of the area.
Action 1: Search[Colorado orogeny]
Thought 2: Then I need to look up eastern sector.
Action 2: Lookup[eastern sector]
Thought 3: The eastern sector of Colorado orogeny extends into the High Plains, so High Plains is the area. I need to search High Plains and find its elevation range.
Action 3: Search[High Plains]
Thought 4: I need to search High Plains (United States).
Action 4: Search[High Plains (United States)]
Thought 5: High Plains rise in elevation from around 1,800 to 7,000 ft, so the answer is 1,800 to 7,000 ft.
Action 5: Finish[1,800 to 7,000 ft]
Question: Guitars for Wounded Warriors is an album that was recorded in the village in which New York county?
Thought 1: I need to search Guitars for Wounded Warriors, then find in which New York county it was recorded.
Action 1: Search[Guitars for Wounded Warriors]
Thought 2: I need to search New Paltz (village), New York and find which county it is in
Action 2: Search[New Paltz (village), New York]
Thought 3: New Paltz (village), New York is in Ulster County, so the answer is Ulster County.
Action 3: Finish[Ulster County]
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Thought 2: I can look up "named after" for finding the specific individual Milhouse is named after.
Action 2: Lookup[named after]
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[President Richard Nixon]
{input}
'''

47
previousversion/0.2/src/YiemAgent.jl Normal file
View File

@@ -0,0 +1,47 @@
module YiemAgent
# export agent
""" Order by dependencies of each file. The 1st included file must not depend on any other
files and each file can only depend on the file included before it.
"""
include("type.jl")
using .type
include("util.jl")
using .util
include("llmfunction.jl")
using .llmfunction
include("interface.jl")
using .interface
# ---------------------------------------------- 100 --------------------------------------------- #
end # module YiemAgent_v1

0
src/interface BACKUP 2.jl → previousversion/0.2/src/interface BACKUP 2.jl
View File

1335
previousversion/0.2/src/interface.jl Normal file
View File

File diff suppressed because it is too large Load Diff

1065
previousversion/0.2/src/llmfunction.jl Normal file
View File

File diff suppressed because it is too large Load Diff

268
previousversion/0.2/src/type.jl Normal file
View File

@@ -0,0 +1,268 @@
module type
export agent, sommelier, companion
using Dates, UUIDs, DataStructures, JSON3
using GeneralUtils
# ---------------------------------------------- 100 --------------------------------------------- #
abstract type agent end
mutable struct companion <: agent
name::String # agent name
id::String # agent id
maxHistoryMsg::Integer # e.g. 21th and earlier messages will get summarized
""" Memory
Ref: Chat prompt format https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/discussions/3
NO "system" message in chathistory because I want to add it at the inference time
chathistory= [
Dict(:name=>"user", :text=> "Wassup!", :timestamp=> Dates.now()),
Dict(:name=>"assistant", :text=> "Hi I'm your assistant.", :timestamp=> Dates.now()),
]
"""
chathistory::Vector{Dict{Symbol, Any}}
memory::Dict{Symbol, Any}
# communication function
text2textInstructLLM::Function
end
function companion(
text2textInstructLLM::Function
;
name::String= "Assistant",
id::String= string(uuid4()),
maxHistoryMsg::Integer= 20,
chathistory::Vector{Dict{Symbol, String}} = Vector{Dict{Symbol, String}}(),
)
memory = Dict{Symbol, Any}(
:chatbox=> "",
:shortmem=> Vector{Dict{Symbol, String}}(),
:events=> Vector{Dict{Symbol, Any}}()
)
newAgent = companion(
name,
id,
maxHistoryMsg,
chathistory,
memory,
text2textInstructLLM
)
return newAgent
end
""" A sommelier agent.
# Arguments
- `mqttClient::Client`
MQTTClient's client
- `msgMeta::Dict{Symbol, Any}`
A dict contain info about a message.
- `config::Dict{Symbol, Any}`
Config info for an agent. Contain mqtt topic for internal use and other info.
# Keyword Arguments
- `name::String`
Agent's name
- `id::String`
Agent's ID
- `tools::Dict{Symbol, Any}`
Agent's tools
- `maxHistoryMsg::Integer`
max history message
# Return
- `nothing`
# Example
```jldoctest
julia> using YiemAgent, MQTTClient, GeneralUtils
julia> msgMeta = GeneralUtils.generate_msgMeta(
"N/A",
replyTopic = "/testtopic/prompt"
)
julia> tools= Dict(
:chatbox=>Dict(
:name => "chatbox",
:description => "Useful only for when you need to ask the user for more info or context. Do not ask the user their own question.",
:input => "Input should be a text.",
:output => "" ,
:func => nothing,
),
)
julia> agentConfig = Dict(
:receiveprompt=>Dict(
:mqtttopic=> "/testtopic/prompt", # topic to receive prompt i.e. frontend send msg to this topic
),
:receiveinternal=>Dict(
:mqtttopic=> "/testtopic/internal", # receive topic for model's internal
),
:text2text=>Dict(
:mqtttopic=> "/text2text/receive",
),
)
julia> client, connection = MakeConnection("test.mosquitto.org", 1883)
julia> agent = YiemAgent.bsommelier(
client,
msgMeta,
agentConfig,
name= "assistant",
id= "555", # agent instance id
tools=tools,
)
```
# TODO
- [] update docstring
- [x] implement the function
# Signature
"""
mutable struct sommelier <: agent
name::String # agent name
id::String # agent id
retailername::String
tools::Dict
maxHistoryMsg::Integer # e.g. 21th and earlier messages will get summarized
""" Memory
Ref: Chat prompt format https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/discussions/3
NO "system" message in chathistory because I want to add it at the inference time
chathistory= [
Dict(:name=>"user", :text=> "Wassup!", :timestamp=> Dates.now()),
Dict(:name=>"assistant", :text=> "Hi I'm your assistant.", :timestamp=> Dates.now()),
]
"""
chathistory::Vector{Dict{Symbol, Any}}
memory::Dict{Symbol, Any}
# communication function
text2textInstructLLM::Function
executeSQL::Function
querySQLVectorDB::Function
addSQLVectorDB::Function
end
function sommelier(
text2textInstructLLM::Function,
executeSQL::Function,
querySQLVectorDB::Function,
addSQLVectorDB::Function
;
name::String= "Assistant",
id::String= string(uuid4()),
retailername::String= "retailer_name",
maxHistoryMsg::Integer= 20,
chathistory::Vector{Dict{Symbol, String}} = Vector{Dict{Symbol, String}}(),
)
tools = Dict( # update input format
"chatbox"=> Dict(
:description => "<askbox tool description>Useful for when you need to ask the user for more context. Do not ask the user their own question.</askbox tool description>",
:input => """<input>Input is a text in JSON format.</input><input example>{\"Q1\": \"How are you doing?\", \"Q2\": \"How may I help you?\"}</input example>""",
:output => "" ,
),
"winestock"=> Dict(
:description => "<winestock tool description>A handy tool for searching wine in your inventory that match the user preferences.</winestock tool description>",
:input => """<input>Input is a JSON-formatted string that contains a detailed and precise search query.</input><input example>{\"wine type\": \"rose\", \"price\": \"max 35\", \"sweetness level\": \"sweet\", \"intensity level\": \"light bodied\", \"Tannin level\": \"low\", \"Acidity level\": \"low\"}</input example>""",
:output => """<output>Output are wines that match the search query in JSON format.""",
),
# "finalanswer"=> Dict(
# :description => "<tool description>Useful for when you are ready to recommend wines to the user.</tool description>",
# :input => """<input format>{\"finalanswer\": \"some text\"}.</input format><input example>{\"finalanswer\": \"I recommend Zena Crown Vista\"}</input example>""",
# :output => "" ,
# :func => nothing,
# ),
)
memory = Dict{Symbol, Any}(
:chatbox=> "",
:shortmem=> Vector{Dict{Symbol, String}}(),
:events=> Vector{Dict{Symbol, Any}}()
)
newAgent = sommelier(
name,
id,
retailername,
tools,
maxHistoryMsg,
chathistory,
memory,
text2textInstructLLM,
executeSQL,
querySQLVectorDB,
addSQLVectorDB
)
return newAgent
end
end # module type

450
previousversion/0.2/src/util.jl Normal file
View File

@@ -0,0 +1,450 @@
module util
export clearhistory, addNewMessage, vectorOfDictToText, eventdict, noises
using UUIDs, Dates, DataStructures, HTTP, MQTTClient, JSON3
using GeneralUtils
using ..type
# ---------------------------------------------- 100 --------------------------------------------- #
""" Clear agent chat history.
# Arguments
- `a::agent`
an agent
# Return
- nothing
# Example
```jldoctest
julia> using YiemAgent, MQTTClient, GeneralUtils
julia> client, connection = MakeConnection("test.mosquitto.org", 1883)
julia> connect(client, connection)
julia> msgMeta = GeneralUtils.generate_msgMeta("testtopic")
julia> agentConfig = Dict(
:receiveprompt=>Dict(
:mqtttopic=> "testtopic/receive",
),
:receiveinternal=>Dict(
:mqtttopic=> "testtopic/internal",
),
:text2text=>Dict(
:mqtttopic=> "testtopic/text2text",
),
)
julia> a = YiemAgent.sommelier(
client,
msgMeta,
agentConfig,
)
julia> YiemAgent.addNewMessage(a, "user", "hello")
julia> YiemAgent.clearhistory(a)
```
# TODO
- [PENDING] clear memory
# Signature
"""
function clearhistory(a::T) where {T<:agent}
empty!(a.chathistory)
empty!(a.memory[:shortmem])
empty!(a.memory[:events])
a.memory[:chatbox] = ""
end
""" Add new message to agent.
Arguments\n
-----
a::agent
an agent
role::String
message sender role i.e. system, user or assistant
text::String
message text
Return\n
-----
nothing
Example\n
-----
```jldoctest
julia> using YiemAgent, MQTTClient, GeneralUtils
julia> client, connection = MakeConnection("test.mosquitto.org", 1883)
julia> connect(client, connection)
julia> msgMeta = GeneralUtils.generate_msgMeta("testtopic")
julia> agentConfig = Dict(
:receiveprompt=>Dict(
:mqtttopic=> "testtopic/receive",
),
:receiveinternal=>Dict(
:mqtttopic=> "testtopic/internal",
),
:text2text=>Dict(
:mqtttopic=> "testtopic/text2text",
),
)
julia> a = YiemAgent.sommelier(
client,
msgMeta,
agentConfig,
)
julia> YiemAgent.addNewMessage(a, "user", "hello")
```
Signature\n
-----
"""
function addNewMessage(a::T1, name::String, text::T2;
maximumMsg::Integer=20) where {T1<:agent, T2<:AbstractString}
if name ∉ ["system", "user", "assistant"] # guard against typo
error("name is not in agent.availableRole $(@__LINE__)")
end
#[] summarize the oldest 10 message
if length(a.chathistory) > maximumMsg
summarize(a.chathistory)
else
d = Dict(:name=> name, :text=> text, :timestamp=> Dates.now())
push!(a.chathistory, d)
end
end
"""
# Arguments
- `v::Integer`
dummy variable
# Return
# Example
```jldoctest
julia>
```
# TODO
- [] update docstring
- [x] implement the function
# Signature
"""
function vectorOfDictToText(vecd::Vector; withkey=true)
text = ""
if withkey
for d in vecd
name = d[:name]
_text = d[:text]
text *= "$name> $_text \n"
end
else
for d in vecd
for (k, v) in d
text *= "$v \n"
end
end
end
return text
end
function eventdict(;
event_description::Union{String, Nothing}=nothing,
timestamp::Union{DateTime, Nothing}=nothing,
subject::Union{String, Nothing}=nothing,
action_or_dialogue::Union{String, Nothing}=nothing,
location::Union{String, Nothing}=nothing,
equipment_used::Union{String, Nothing}=nothing,
material_used::Union{String, Nothing}=nothing,
outcome::Union{String, Nothing}=nothing,
note::Union{String, Nothing}=nothing,
)
return Dict{Symbol, Any}(
:event_description=> event_description,
:timestamp=> timestamp,
:subject=> subject,
:action_or_dialogue=> action_or_dialogue,
:location=> location,
:equipment_used=> equipment_used,
:material_used=> material_used,
:outcome=> outcome,
:note=> note,
)
end
noise(n::Integer) = String(rand('a':'z', n))
function noises(totalword::Integer, wordlength::Integer)
noises = ""
for i in 1:totalword
noises *= noise(wordlength) * " "
end
noises = strip(noises)
return noises
end
# """ Convert a single chat dictionary into LLM model instruct format.
# # Llama 3 instruct format example
# <|system|>
# You are a helpful AI assistant.<|end|>
# <|user|>
# I am going to Paris, what should I see?<|end|>
# <|assistant|>
# Paris, the capital of France, is known for its stunning architecture, art museums."<|end|>
# <|user|>
# What is so great about #1?<|end|>
# <|assistant|>
# # Arguments
# - `name::T`
# message owner name e.f. "system", "user" or "assistant"
# - `text::T`
# # Return
# - `formattedtext::String`
# text formatted to model format
# # Example
# ```jldoctest
# julia> using Revise
# julia> using YiemAgent
# julia> d = Dict(:name=> "system",:text=> "You are a helpful, respectful and honest assistant.",)
# julia> formattedtext = YiemAgent.formatLLMtext_phi3instruct(d[:name], d[:text])
# ```
# Signature
# """
# function formatLLMtext_phi3instruct(name::T, text::T) where {T<:AbstractString}
# formattedtext =
# """
# <|$name|>
# $text<|end|>\n
# """
# return formattedtext
# end
# """ Convert a single chat dictionary into LLM model instruct format.
# # Llama 3 instruct format example
# <|begin_of_text|>
# <|start_header_id|>system<|end_header_id|>
# You are a helpful assistant.
# <|eot_id|>
# <|start_header_id|>user<|end_header_id|>
# Get me an icecream.
# <|eot_id|>
# <|start_header_id|>assistant<|end_header_id|>
# Go buy it yourself at 7-11.
# <|eot_id|>
# # Arguments
# - `name::T`
# message owner name e.f. "system", "user" or "assistant"
# - `text::T`
# # Return
# - `formattedtext::String`
# text formatted to model format
# # Example
# ```jldoctest
# julia> using Revise
# julia> using YiemAgent
# julia> d = Dict(:name=> "system",:text=> "You are a helpful, respectful and honest assistant.",)
# julia> formattedtext = YiemAgent.formatLLMtext_llama3instruct(d[:name], d[:text])
# "<|begin_of_text|>\n <|start_header_id|>system<|end_header_id|>\n You are a helpful, respectful and honest assistant.\n <|eot_id|>\n"
# ```
# Signature
# """
# function formatLLMtext_llama3instruct(name::T, text::T) where {T<:AbstractString}
# formattedtext =
# if name == "system"
# """
# <|begin_of_text|>
# <|start_header_id|>$name<|end_header_id|>
# $text
# <|eot_id|>
# """
# else
# """
# <|start_header_id|>$name<|end_header_id|>
# $text
# <|eot_id|>
# """
# end
# return formattedtext
# end
# """ Convert a chat messages in vector of dictionary into LLM model instruct format.
# # Arguments
# - `messages::Vector{Dict{Symbol, T}}`
# message owner name e.f. "system", "user" or "assistant"
# - `formatname::T`
# format name to be used
# # Return
# - `formattedtext::String`
# text formatted to model format
# # Example
# ```jldoctest
# julia> using Revise
# julia> using YiemAgent
# julia> chatmessage = [
# Dict(:name=> "system",:text=> "You are a helpful, respectful and honest assistant.",),
# Dict(:name=> "user",:text=> "list me all planets in our solar system.",),
# Dict(:name=> "assistant",:text=> "I'm sorry. I don't know. You tell me.",),
# ]
# julia> formattedtext = YiemAgent.formatLLMtext(chatmessage, "llama3instruct")
# "<|begin_of_text|>\n <|start_header_id|>system<|end_header_id|>\n You are a helpful, respectful and honest assistant.\n <|eot_id|>\n <|start_header_id|>user<|end_header_id|>\n list me all planets in our solar system.\n <|eot_id|>\n <|start_header_id|>assistant<|end_header_id|>\n I'm sorry. I don't know. You tell me.\n <|eot_id|>\n"
# ```
# # Signature
# """
# function formatLLMtext(messages::Vector{Dict{Symbol, T}},
# formatname::String="llama3instruct") where {T<:Any}
# f = if formatname == "llama3instruct"
# formatLLMtext_llama3instruct
# elseif formatname == "mistral"
# # not define yet
# elseif formatname == "phi3instruct"
# formatLLMtext_phi3instruct
# else
# error("$formatname template not define yet")
# end
# str = ""
# for t in messages
# str *= f(t[:name], t[:text])
# end
# # add <|assistant|> so that the model don't generate it and I don't need to clean it up later
# if formatname == "phi3instruct"
# str *= "<|assistant|>\n"
# end
# return str
# end
# """
# Arguments\n
# -----
# Return\n
# -----
# Example\n
# -----
# ```jldoctest
# julia>
# ```
# TODO\n
# -----
# [] update docstring
# [PENDING] implement the function
# Signature\n
# -----
# """
# function iterativeprompting(a::T, prompt::String, verification::Function) where {T<:agent}
# msgMeta = GeneralUtils.generate_msgMeta(
# a.config[:externalService][:text2textinstruct],
# senderName= "iterativeprompting",
# senderId= a.id,
# receiverName= "text2textinstruct",
# )
# outgoingMsg = Dict(
# :msgMeta=> msgMeta,
# :payload=> Dict(
# :text=> prompt,
# )
# )
# success = nothing
# result = nothing
# critique = ""
# # iteration loop
# while true
# # send prompt to LLM
# response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
# error("--> iterativeprompting")
# # check for correctness and get feedback
# success, _critique = verification(response)
# if success
# result = response
# break
# else
# # add critique to prompt
# critique *= _critique * "\n"
# replace!(prompt, "Critique: ..." => "Critique: $critique")
# end
# end
# return (success=success, result=result)
# end
end # module util

9
previousversion/0.2/test/etc.jl Normal file
View File

@@ -0,0 +1,9 @@
using GeneralUtils
response = "trajectory_evaluation:\nThe trajectory is correct so far. The thought accurately reflects the user's question, and the action taken is a valid attempt to retrieve data from the database that matches the specified criteria.\n\nanswer_evaluation:\nThe observation provides information about two red wines from Bordeaux rive droite in France, which partially answers the question. However, it does not provide a complete answer as it only lists the wine names and characteristics, but does not explicitly state whether there are any other wines that match the criteria.\n\naccepted_as_answer: No\n\nscore: 6\nThe trajectory is mostly correct, but the observation does not fully address the question.\n\nsuggestion: Consider adding more filters or parameters to the database query to retrieve a complete list of wines that match the specified criteria."
responsedict = GeneralUtils.textToDict(response,
["trajectory_evaluation", "answer_evaluation", "accepted_as_answer", "score", "suggestion"],
rightmarker=":", symbolkey=true)

159
previousversion/0.2/test/prompttest.jl Normal file
View File

@@ -0,0 +1,159 @@
using Revise
using YiemAgent, GeneralUtils, JSON3, DataStructures
thoughtDict = OrderedDict(
:Question=> "Hello, I would like a get a bottle of wine",
:Thought_1=> "The customer wants to buy a bottle of wine, but we need more information about their preferences.",
:Action_1=> Dict(
:name=> "chatbox",
:input=> "What occasion are you buying the wine for?",
),
:Observation_1=> "We are having a wedding pary this weekend.",
:Thought_2=> "A wedding party is a great occasion to have a good bottle of wine.",
:Action_2=> Dict(
:name=> "chatbox",
:input=> "What type of food will you be serving with the wine?",
),
:Observation_2=> "I think it is Thai dishes",
:Thought_3=> "Now that I know the occasion and food, I need to ask about the budget.",
:Action_3=> Dict(
:name=> "chatbox",
:input=> "What is your budget for this wine?",
),
:Observation_3=> "50 bucks",
:Thought_4=> "With a budget of \$50, we have a wide range of options. Now that I know it's a wedding party and Thai dishes, I need to ask about the type of wine they prefer.",
:Action_4=> Dict(
:name=> "chatbox",
:input=> "What type of wine are you looking for? (Red, White, Sparkling, Rose, Dessert, Fortified)",
),
:Observation_4=> "Sparkling please.",
:Thought_5=> "Now that I know the occasion, food, budget and preferred type of wine, it's time to check our inventory for the best matching wine.",
:Action_5=> Dict(
:name=> "winestock",
:input=> "wine with budget \$50, Thai dishes, sparkling, wedding party",
),
:Observation_5=> "I found the following wine in stock {1 : Zena Crown Vista, 2 : Schrader Cabernet Sauvignon}",
:Thought_6=> "Now that I have all the information, it's time to recommend a wine that fits their preferences.",
:Action_6=> Dict(
:name=> "recommendation",
:input=> "I recommend Zena Crown Vista for its sparkling and affordable price.",
),
:Observation_6=> "I don't like it. Do you have another option?",
)
_thoughtJsonStr = JSON3.write(thoughtDict)
thoughtJsonStr = _thoughtJsonStr[1:end-1] # remove } at the end
# @show thoughtJsonStr
_, latestThoughtIndice = GeneralUtils.findHighestIndexKey(thoughtDict, "Thought")
nextThoughtIndice = latestThoughtIndice + 1
_prompt =
"""
You are a helpful sommelier working for a wine store.
Your goal is to reccommend the best wine from your inventory that match the user preferences.
You must follow the following criteria:
1) Get to know what occasion the user is buying wine for
2) Get to know what food the user will have with wine
3) Get to know how much the user willing to spend
4) Get to know type of wine the user is looking for e.g. Red, White, Sparkling, Rose, Dessert, Fortified
5) Get to know what characteristics of wine the user is looking for
e.g. tannin, sweetness, intensity, acidity
6) Check your inventory for the best wine that match the user preference
7) Recommend wine to the user
You should only respond with interleaving Thought, Action, Observation steps.
Thought can reason about the current situation, and Action can be three types:
1) winestock[query], which you can use to find wine in your inventory. The more input data the better.
2) chatbox[text], which you can use to interact with the user.
3) recommendation[answer], which returns your wine reccommendation to the user.
You should only respond in JSON format as describe below:
{
"Thought": "your reasoning",
"Action": {"name": "action to take", "input": "Action input"},
"Observation": "result of the action"
}
Here are some examples:
{
"Question": "I would like to buy a sedan with 8 seats.",
"Thought_1": "Our showroom carries various vehicle model. But I'm not sure whether we have a models that fits the user demand, I need to check our inventory.",
"Action_1": {"name": "inventory", "input": "sedan with 8 seats."},
"Observation_1": "Several model has 8 seats. Available color are black, red green"
}
{
"Thought_2": "I have to ask the user what color he likes.",
"Action_2": {"name": "chatbox", "input": "Which color do you like?"}
"Observation_2": "I'll take black."
}
{
"Thought_3": "There is only one model that fits the user preference. It's Yiem model A",
"Action_3": {"name": "recommendation", "input": "I recommend a Yiem model A"}
}
Let's begin!
$(JSON3.write(thoughtDict))
{Thought_$nextThoughtIndice
"""
prompt = YiemAgent.formatLLMtext_llama3instruct("system", _prompt)
@show prompt
msgMeta = Dict(:requestResponse => nothing,
:msgPurpose => nothing,
:receiverId => nothing,
:getPost => nothing,
:msgId => "4c7111e0-c30e-44c3-8f85-1c8b3f03a8be",
:acknowledgestatus => nothing,
:replyToMsgId => nothing,
:msgFormatVersion => nothing,
:mqttServerInfo => Dict(:port => 1883, :broker => "mqtt.yiem.cc"),
:sendTopic => "/loadbalancer/requestingservice",
:receiverName => "text2textinstruct",
:replyTopic => nothing,
:senderName => "decisionMaker",
:senderSelfnote => nothing,
:senderId => "testingSessionID",
:timeStamp => "2024-05-04T08:06:23.561"
)
outgoingMsg = Dict(
:msgMeta=> msgMeta,
:payload=> Dict(
:text=> prompt,
)
)
_response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
thoughtJsonStr = _response[:response][:text]

87
previousversion/0.2/test/prompttest_1.jl Normal file
View File

@@ -0,0 +1,87 @@
using Revise # remove when this package is completed
using YiemAgent, GeneralUtils, JSON3, MQTTClient, Dates, UUIDs, DataStructures
using Base.Threads
# ---------------------------------------------- 100 --------------------------------------------- #
config = copy(JSON3.read("config.json"))
instanceInternalTopic = config[:serviceInternalTopic][:mqtttopic] * "/1"
client, connection = MakeConnection(config[:mqttServerInfo][:broker],
config[:mqttServerInfo][:port])
receiveUserMsgChannel = Channel{Dict}(4)
receiveInternalMsgChannel = Channel{Dict}(4)
msgMeta = GeneralUtils.generate_msgMeta(
"N/A",
replyTopic = config[:servicetopic][:mqtttopic] # ask frontend reply to this instance_chat_topic
)
agentConfig = Dict(
:mqttServerInfo=> config[:mqttServerInfo],
:receivemsg=> Dict(
:prompt=> config[:servicetopic][:mqtttopic], # topic to receive prompt i.e. frontend send msg to this topic
:internal=> instanceInternalTopic,
),
:externalservice=> config[:externalservice],
)
# Instantiate an agent
tools=Dict( # update input format
"askbox"=> Dict(
:description => "<askbox tool description>Useful for when you need to ask the user for more context. Do not ask the user their own question.</askbox tool description>",
:input => """<input>Input is a text in JSON format.</input><input example>{\"Q1\": \"How are you doing?\", \"Q2\": \"How may I help you?\"}</input example>""",
:output => "" ,
:func => nothing,
),
# "winestock"=> Dict(
# :description => "<winestock tool description>A handy tool for searching wine in your inventory that match the user preferences.</winestock tool description>",
# :input => """<input>Input is a JSON-formatted string that contains a detailed and precise search query.</input><input example>{\"wine type\": \"rose\", \"price\": \"max 35\", \"sweetness level\": \"sweet\", \"intensity level\": \"light bodied\", \"Tannin level\": \"low\", \"Acidity level\": \"low\"}</input example>""",
# :output => """<output>Output are wines that match the search query in JSON format.""",
# :func => ChatAgent.winestock,
# ),
"finalanswer"=> Dict(
:description => "<tool description>Useful for when you are ready to recommend wines to the user.</tool description>",
:input => """<input format>{\"finalanswer\": \"some text\"}.</input format><input example>{\"finalanswer\": \"I recommend Zena Crown Vista\"}</input example>""",
:output => "" ,
:func => nothing,
),
)
a = YiemAgent.sommelier(
receiveUserMsgChannel,
receiveInternalMsgChannel,
agentConfig,
name= "assistant",
id= "testingSessionID", # agent instance id
tools=tools,
)
input =
OrderedDict{Symbol, Any}(:question => "Hello, I would like a get a bottle of wine", :thought_1 => "It's great that the user is looking for a bottle of wine. To give them a personalized recommendation, I need to know more about their preferences.", :action_1 => Dict{Symbol, Any}(:name => "chatbox", :input => "What occasion are you planning to use this wine for?"), :observation_1 => "We are holding a wedding party", :thought_2 => "A wedding party is a great occasion for a special bottle of wine. I need to know what type of food will be served, and how much the user is willing to spend.", :action_2 => Dict{Symbol, Any}(:name => "chatbox", :input => "What type of food will you be serving at the wedding?"), :observation_2 => "It will be Thai dishes.", :thought_3 => "The type of wine that pairs well with Thai dishes is usually a crisp and refreshing white wine, but I also need to consider the budget and personal preferences.", :action_3 => Dict{Symbol, Any}(:name => "chatbox", :input => "How much are you willing to spend on this bottle of wine?"), :observation_3 => "I would spend up to 50 bucks.", :thought_4 => "I have a good idea of the occasion, food, and budget. Now I need to know what type of wine the user is looking for.", :action_4 => Dict{Symbol, Any}(:name => "chatbox", :input => "What type of wine are you usually looking for? Red, White, Sparkling, Rose, Dessert or Fortified?"), :observation_4 => "I like full-bodied Red wine with low tannin.", :thought_5 => "Now that I have all the necessary information, I can start searching for a suitable wine in our inventory.", :action_5 => Dict{Symbol, Any}(:name => "winestock", :input => "red wine with low tannins"), :observation_5 => "I found the following wines in our stock: \n{\n 1: El Enemigo Cabernet Franc 2019\n2: Tantara Chardonnay 2017\n\n}\n", :thought_6 => "Now that I have the information about the wine, it's time to make a recommendation.", :action_6 => Dict{Symbol, Any}(:name => "recommendbox", :input => "El Enemigo Cabernet Franc 2019"), :observation_6 => "I don't like the one you recommend. I want dry wine.")
result = YiemAgent.jsoncorrection(a, input)

119
previousversion/0.2/test/prompttest_2.jl Normal file
View File

@@ -0,0 +1,119 @@
using Revise
using YiemAgent, GeneralUtils, JSON3, DataStructures, LibPQ
using SQLLLM
# _prompt =
# """
# You are a helpful assistant.
# answer the following question:
# From the following CSV text:
# "{\"tabledescription\":[\"The customer table stores information about customers. It includes details such as first name, last name, display name, username, password, gender, country, telephone number, email, birthdate, additional_search_term, other attributes (in JSON format) and a description.\",\"The wine table stores information about different wines. It includes details namely id, name, brand, manufacturer, region, country, wine_type, grape_variety, serving_temperature, intensity, sweetness, tannin, acidity, fizziness, additional_search_term, other attributes (in JSON format) and a description.\",\"The wine_food table represents the association between wines and food items. It estab" ⋯ 477 bytes ⋯ "ed to retailer names, usernames, passwords, addresses, contact persons, telephone numbers, email addresses, additional_search_term, other attributes (in JSON format) and a description.\",\"The retailer_wine table represents the relationship between retailers and wines. It stores information about the wines available from which retailers, including vintage, their price, and the currency.\",\"The retailer_food table represents the relationship between retailers and food items. It stores information about the food items available from which retailers, including their price and the currency.\"],\"tablename\":[\"customer\",\"wine\",\"wine_food\",\"food\",\"retailer\",\"retailer_wine\",\"retailer_food\"]}"
# What is the description of table wine?
# """
# prompt = YiemAgent.formatLLMtext_llama3instruct("system", _prompt)
# @show prompt
# msgMeta = Dict(:requestResponse => nothing,
# :msgPurpose => nothing,
# :receiverId => nothing,
# :getPost => nothing,
# :msgId => "4c7111e0-c30e-44c3-8f85-1c8b3f03a8be",
# :acknowledgestatus => nothing,
# :replyToMsgId => nothing,
# :msgFormatVersion => nothing,
# :mqttServerInfo => Dict(:port => 1883, :broker => "mqtt.yiem.cc"),
# :sendTopic => "/loadbalancer/requestingservice",
# :receiverName => "text2textinstruct",
# :replyTopic => nothing,
# :senderName => "decisionMaker",
# :senderSelfnote => nothing,
# :senderId => "testingSessionID",
# :timeStamp => "2024-05-04T08:06:23.561"
# )
# outgoingMsg = Dict(
# :msgMeta=> msgMeta,
# :payload=> Dict(
# :text=> prompt,
# )
# )
# _response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
# result = _response[:response][:text]
DBconnection = LibPQ.Connection("host=192.168.88.12 port=5432 dbname=yiem_wine_assistant user=yiem password=yiem@Postgres_0.0")
tableinfo, df1, df2, df3 = SQLLLM.tableinfo(DBconnection, "wine")
_prompt =
"""
You are a helpful assistant helping to answer user question from a database table.
$tableinfo
Are there any chardonnay?
"""
prompt = YiemAgent.formatLLMtext_llama3instruct("system", _prompt)
@show prompt
msgMeta = Dict(:requestResponse => nothing,
:msgPurpose => nothing,
:receiverId => nothing,
:getPost => nothing,
:msgId => "4c7111e0-c30e-44c3-8f85-1c8b3f03a8be",
:acknowledgestatus => nothing,
:replyToMsgId => nothing,
:msgFormatVersion => nothing,
:mqttServerInfo => Dict(:port => 1883, :broker => "mqtt.yiem.cc"),
:sendTopic => "/loadbalancer/requestingservice",
:receiverName => "text2textinstruct",
:replyTopic => nothing,
:senderName => "decisionMaker",
:senderSelfnote => nothing,
:senderId => "testingSessionID",
:timeStamp => "2024-05-04T08:06:23.561"
)
outgoingMsg = Dict(
:msgMeta=> msgMeta,
:payload=> Dict(
:text=> prompt,
)
)
_response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
result2 = _response[:response][:text]

288
previousversion/0.2/test/runtest.jl Normal file
View File

@@ -0,0 +1,288 @@
using Revise # remove when this package is completed
using YiemAgent, GeneralUtils, JSON3, MQTTClient, Dates, UUIDs, LibPQ, Base64, DataFrames
using Base.Threads
# ---------------------------------------------- 100 --------------------------------------------- #
config = copy(JSON3.read("config.json"))
# instanceInternalTopic = config[:serviceInternalTopic][:mqtttopic] * "/1"
# client, connection = MakeConnection(config[:mqttServerInfo][:broker],
# config[:mqttServerInfo][:port])
receiveUserMsgChannel = Channel{Dict}(4)
# receiveInternalMsgChannel = Channel{Dict}(4)
# println(typeof(connection))
# msgMeta = GeneralUtils.generate_msgMeta(
# "N/A",
# replyTopic = config[:servicetopic][:mqtttopic] # ask frontend reply to this instance_chat_topic
# )
function executeSQL(sql::T) where {T<:AbstractString}
DBconnection = LibPQ.Connection("host=192.168.88.12 port=5432 dbname=yiem_wine_assistant user=yiem password=yiem@Postgres_0.0")
result = LibPQ.execute(DBconnection, sql)
close(DBconnection)
return result
end
function text2textInstructLLM(prompt::String)
msgMeta = GeneralUtils.generate_msgMeta(
config[:externalservice][:text2textinstruct][:mqtttopic];
msgPurpose= "inference",
senderName= "yiemagent",
senderId= string(uuid4()),
receiverName= "text2textinstruct",
mqttBrokerAddress= config[:mqttServerInfo][:broker],
mqttBrokerPort= config[:mqttServerInfo][:port],
)
outgoingMsg = Dict(
:msgMeta=> msgMeta,
:payload=> Dict(
:text=> prompt,
:kwargs=> Dict(
:max_tokens=> 2048,
:stop=> ["<|eot_id|>"],
:temperature=> 0.2,
)
)
)
_response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg; timeout=120)
response = _response[:response][:text]
return response
end
function executeSQLVectorDB(sql)
DBconnection = LibPQ.Connection("host=192.168.88.12 port=5433 dbname=SQLVectorDB user=yiemtechnologies@gmail.com password=yiem@Postgres_0.0")
result = LibPQ.execute(DBconnection, sql)
close(DBconnection)
return result
end
function addSQLVectorDB(state)
# get embedding of the query
query = [state[:thoughtHistory][:question]]
msgMeta = GeneralUtils.generate_msgMeta(
config[:externalservice][:text2textinstruct][:mqtttopic];
msgPurpose= "embedding",
senderName= "yiemagent",
senderId= string(uuid4()),
receiverName= "text2textinstruct",
mqttBrokerAddress= config[:mqttServerInfo][:broker],
mqttBrokerPort= config[:mqttServerInfo][:port],
)
outgoingMsg = Dict(
:msgMeta=> msgMeta,
:payload=> Dict(
:text=> query
)
)
response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
embedding = response[:response][:embeddings][1]
# check whether there is close enough vector already store in vectorDB. if no, add, else skip
sql =
"""
SELECT *, embedding <-> '$embedding' as distance
FROM sql_statement_repository
ORDER BY distance LIMIT 1;
"""
response = executeSQLVectorDB(sql)
df = DataFrame(response)
row, col = size(df)
distance = row == 0 ? Inf : df[1, :distance]
if row == 0 || distance > 10 # no close enough SQL stored in the database
latestKey, _ = GeneralUtils.findHighestIndexKey(state[:thoughtHistory], :action_input)
_sqlStatement = state[:thoughtHistory][latestKey]
if occursin("SELECT", _sqlStatement) # make sure it is an SQL statement before adding into DB
sqlStatementBase64 = base64encode(_sqlStatement)
sqlStatement = replace(_sqlStatement, "'"=>"")
sql =
"""
INSERT INTO sql_statement_repository (question, sql_statement, sql_statement_base64, embedding) VALUES ('$query', '$sqlStatement', '$sqlStatementBase64', '$embedding');
"""
_ = executeSQLVectorDB(sql)
println("--> added new SQL statement to vectorDB ", @__FILE__, " ", @__LINE__)
println(sqlStatement)
end
end
end
function querySQLVectorDB(state)
# provide similarSQL at the first time thinking only
latestKey, _ = GeneralUtils.findHighestIndexKey(state[:thoughtHistory], :action_input)
if latestKey === nothing
# get embedding of the query
query = [state[:thoughtHistory][:question]]
msgMeta = GeneralUtils.generate_msgMeta(
config[:externalservice][:text2textinstruct][:mqtttopic];
msgPurpose= "embedding",
senderName= "yiemagent",
senderId= string(uuid4()),
receiverName= "text2textinstruct",
mqttBrokerAddress= config[:mqttServerInfo][:broker],
mqttBrokerPort= config[:mqttServerInfo][:port],
)
outgoingMsg = Dict(
:msgMeta=> msgMeta,
:payload=> Dict(
:text=> query
)
)
response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
embedding = response[:response][:embeddings][1]
# check whether there is close enough vector already store in vectorDB. if no, add, else skip
sql =
"""
SELECT *, embedding <-> '$embedding' as distance
FROM sql_statement_repository
ORDER BY distance LIMIT 1;
"""
response = executeSQLVectorDB(sql)
df = DataFrame(response)
row, col = size(df)
distance = row == 0 ? Inf : df[1, :distance]
if row != 0 && distance < 100
# if there is usable SQL, return it.
sqlStatementBase64 = df[1, :sql_statement_base64]
sqlStatement = String(base64decode(sqlStatementBase64))
println("--> getting SQL statement from vectorDB ", @__FILE__, " ", @__LINE__)
println(sqlStatement)
return sqlStatement
else
return nothing
end
end
return nothing
end
# Instantiate an agent
a = YiemAgent.sommelier(
text2textInstructLLM,
executeSQL,
querySQLVectorDB,
addSQLVectorDB;
name= "Jene",
id= "tempId", # agent instance id
)
function main()
for i in 1:10
userinput = ""
for i in 1:3
if userinput == ""
println("")
println("--> user input:")
userinput = readline()
else
break
end
end
response = YiemAgent.conversation(a, Dict(:text=> userinput))
println("")
println("--> assistant response: \n", response)
end
end
main()
"""
I'm joining a graduation party this evening. I want to get a bottle of white wine from the US to celebrate. I'm ok with any price range.
Well, the party is small casual with close friends and no food serving.
I'm open to suggestion since I have no specific idea.
I'm ok with any region.
The input is instructions on how you want the presentation to be conducted.
"""
wines =
"""
Summary: This table contains two wine records, both from the United States, with white wine types, moderate sweetness (2), and high intensity (5).
More details: 1) wine_id: add9824f-81b0-47da-a08a-ee20498bc6c8, wine_name: Belle Cote Chardonnay, brand: Peter Michael, manufacturer: Peter Michael, region: Californian, country: United States, wine_type: white, grape_variety: Chardonnay, serving_temperature: 11 to 13 Celsius, intensity: 5, sweetness: 2, tannin: missing, acidity: 3, fizziness: missing, tasting_notes: oak, butter, vanilla, cream, oil, lemon curd, pear, peach, apple
2) wine_id: ff9a494c-e916-44c4-9385-1c18b23aa825, wine_name: Ma Belle-Fille Chardonnay, brand: Peter Michael, manufacturer: Peter Michael, region: Californian, country: United States, wine_type: white, grape_variety: Chardonnay, serving_temperature: 11 to 13 Celsius, intensity: 5, sweetness: 2, tannin: missing, acidity: 3, fizziness: missing, tasting_notes: oak, butter, vanilla, cream, banana, cheese, apricot, peach, apple
"""
# response = YiemAgent.conversation(a, Dict(:text=> "newtopic",) )
# response = YiemAgent.conversation(a, Dict(:text=> "Hello, I would like a get a bottle of wine."))
# println("---> YiemAgent: ", response)
# response = YiemAgent.conversation(a, Dict(:text=> "I'm having a graduation party this evening. I'll pay at most 30 bucks."))
# # input = "query=\"off dry, medium tannin, French Rosé\""
# input = "Search the database for wine type: white, country: France, sweetness level: 1"
# YiemAgent.winestock(a, input)
# input = "French dry white wines with medium body"
# input = "query=\"medium-bodied dry white wine\""
# # input = "the customer is looking for a medium-bodied, dry white wine."
# result = YiemAgent.checkinventory(a, input)
error("test done")
function run_with_timeout(f, args...; timeout=5)
result = Ref{Any}()
task = Threads.@spawn try
result[] = f(args...)
catch e
println("Task interrupted: ", e)
end
Timer(timeout) do _
if !istaskdone(task)
schedule(task, InterruptException())
println("Task did not complete in time. Aborting.")
else
println("Task completed within the timeout.")
end
end
return result[]
end
# Example function that takes arguments and returns a value
function example_function(x, y)
sleep(10) # Simulate a long-running task
return x + y
end
# Example usage
result = run_with_timeout(example_function, 3, 4; timeout=5)
println("Result: ", result)
a = `$"hello\nworld"`
a = $"hello\nworld"
a = """$("hello\nworld")"""

0
test/test_1.jl → previousversion/0.2/test/test_1.jl
View File

0
test/test_2.jl → previousversion/0.2/test/test_2.jl
View File

1196
src/interface BACKUP.jl
View File

File diff suppressed because it is too large Load Diff

576
src/interface.jl
View File

@@ -4,7 +4,7 @@ export addNewMessage, conversation, decisionMaker, evaluator, reflector, generat
generalconversation
using JSON3, DataStructures, Dates, UUIDs, HTTP, Random, MQTTClient, PrettyPrinting, Serialization
using GeneralUtils, LLMMCTS
using GeneralUtils
using ..type, ..util, ..llmfunction
# ------------------------------------------------------------------------------------------------ #
@@ -123,71 +123,7 @@ function decisionMaker(a::T; recent::Integer=5)::Dict{Symbol,Any} where {T<:agen
# """
# end
systemmsg =
"""
Your name is $(a.name). You are a helpful English-speaking assistant, acting as a polite, website-based sommelier for $(a.retailername)'s online store.
Your goal includes:
1) Get to know the user preferences about wine
2) Help them select the best wines from your inventory that align with their preferences
Your responsibility includes:
1) Make an informed decision about what you need to do to achieve the goal
2) Thanks the user when they don't need any further assistance and invite them to comeback next time
Your responsibility do not include:
1) Asking or guiding the user to make a purchase
2) Processing sales orders or engaging in any other sales-related activities
At each round of conversation, you will be given the current situation:
Recap: ...
Context: ...
You must follow the following guidelines:
- Generally speaking, your inventory has some wines from France, the United States, Australia, Spain, and Italy, but you won't know which wines your store carries until you check your inventory.
- All wines in your inventory are always in stock.
- If the user interrupts, prioritize the user
- Do not ask the user about wine's flavor e.g. floral, citrusy, nutty or some thing similar as these terms cannot be used to search the database.
- Once the user has selected their wine, ask the user if they need any further assistance. Do not offer any additional services. If the user doesn't need any further assistance, say goodbye and invite them to come back next time.
You should follow the following guidelines:
- Identifying at least four preferences before checking inventory significantly improves search results
- Sometimes, the item a user desires might not be available in your inventory. In such cases, inform the user that the item is unavailable and suggest an alternative instead.
For your information:
- vintage 0 means non-vintage.
You should then respond to the user with interleaving Understanding, Reasoning, Plan, Action:
1) Understanding:
- State your understanding about the current situation.
2) Reasoning:
- State your step by step reasoning about the current situation.
3) Plan: Based on the current situation, state a complete plan to complete the task. Be specific.
4) Action_name (Must be aligned with your plan): The name of the action. Typically corresponds to the execution of the first step in your plan.
Can be one of the following functions:
- CHATBOX which you can use to talk with the user. The input is your intentions for the dialogue. Be specific.
- CHECKINVENTORY which you can use to check info about wine in your inventory. The input is a search term in verbal English.
Good query example: black car, a stereo, 200 mile range, electric motor.
- PRESENTBOX which you can use to introduce wine brand (e.g. Domaine du Collier) from your inventory to the user when it hasn't been introduced before.
The input is instructions on how you want the presentation to be conducted.
Here are some input examples,
"First, provide detailed introductions of Zena Crown, Schrader Cabernet Sauvignon.
Second, if there are multiple wines, offer a thorough comparison of each option, highlighting their differences.
Third, explain the potential impact each option could bring to the user."
- ENDCONVERSATION which you can use when you believe the user has concluded their interaction, to properly end the conversation with them. Input is "NA".
5) Action_input: input of the action
6) Mentioned_brand: Are there any specific brand mentioned in your response? The answer can be the names of the brand or "None".
You should only respond in format as described below:
Understanding: ...
Reasoning: ...
Plan: ...
Action_name: ...
Action_input: ...
Mentioned_brand: ...
Let's begin!
"""
# check vectorDB for similar cached decision. USE combined event T, T-1
totalevents = length(a.memory[:events])
ind =
if totalevents > recent
@@ -197,6 +133,8 @@ function decisionMaker(a::T; recent::Integer=5)::Dict{Symbol,Any} where {T<:agen
1:totalevents
end
chathistory = vectorOfDictToText(a.chathistory)
timeline = ""
for (i, event) in enumerate(a.memory[:events][ind])
if event[:outcome] === nothing
@@ -206,125 +144,196 @@ function decisionMaker(a::T; recent::Integer=5)::Dict{Symbol,Any} where {T<:agen
end
end
shortmem =
if length(a.memory[:shortmem]) > 0
vectorOfDictToText(a.memory[:shortmem], withkey=false)
else
""
# query similar result from vectorDB
similarDecision = a.func[:similarSommelierDecision](timeline)
if similarDecision !== nothing
responsedict = similarDecision
return responsedict
else
systemmsg =
"""
Your name is $(a.name). You are a helpful English-speaking assistant, acting as a polite, website-based sommelier for $(a.retailername)'s online store.
Your goal includes:
1) Get to know the user preferences about wine
2) Help them select the best wines from your inventory that align with their preferences
Your responsibility includes:
1) Make an informed decision about what you need to do to achieve the goal
2) Thanks the user when they don't need any further assistance and invite them to comeback next time
Your responsibility do not include:
1) Asking or guiding the user to make a purchase
2) Processing sales orders or engaging in any other sales-related activities
At each round of conversation, you will be given the current situation:
Your status: your current status
Your recent events: latest 5 events of the situation
Your Q&A: the question and answer you have asked yourself
You must follow the following guidelines:
- Generally speaking, your inventory has some wines from France, the United States, Australia, Spain, and Italy, but you won't know which wines your store carries until you check your inventory.
- All wines in your inventory are always in stock.
- If the user interrupts, prioritize the user
- Do not ask the user about wine's flavor e.g. floral, citrusy, nutty or some thing similar as these terms cannot be used to search the database.
- Once the user has selected their wine, ask the user if they need any further assistance. Do not offer any additional services. If the user doesn't need any further assistance, say goodbye and invite them to come back next time.
You should follow the following guidelines:
- Identifying at least four preferences before checking inventory significantly improves search results
- Sometimes, the item a user desires might not be available in your inventory. In such cases, inform the user that the item is unavailable and suggest an alternative instead.
For your information:
- vintage 0 means non-vintage.
You should then respond to the user with interleaving Understanding, Reasoning, Plan, Action:
1) Understanding:
- State your understanding about the current situation.
2) Reasoning:
- State your step by step reasoning about the current situation.
3) Plan: Based on the current situation, state a complete plan to complete the task. Be specific.
4) Action_name (Must be aligned with your plan): The name of the action. Typically corresponds to the execution of the first step in your plan.
Can be one of the following functions:
- CHATBOX which you can use to talk with the user. The input is your intentions for the dialogue. Be specific.
- CHECKINVENTORY which you can use to check info about wine in your inventory. The input is a search term in verbal English.
Good query example: black car, a stereo, 200 mile range, electric motor.
- ENDCONVERSATION which you can use when you believe the user has concluded their interaction, to properly end the conversation with them. Input is "NA".
5) Action_input: input of the action
You should only respond in format as described below:
Understanding: ...
Reasoning: ...
Plan: ...
Action_name: ...
Action_input: ...
Let's begin!
"""
# check if winename in shortmem occurred in chathistory. if not, skip decision and imediately use PRESENTBOX
if haskey(a.memory[:shortmem], :available_wine)
# check if wine name mentioned in timeline, only check first wine name is enough
# because agent will recommend every wines it found each time.
df = a.memory[:shortmem][:available_wine]
winename = df[1, :wine_name]
if !occursin(winename, chathistory)
return Dict(:action_name=> "PRESENTBOX",
:action_input=> """
1) Provide detailed introductions of the wines you just found to help the user make an informed choice.
2) If there are multiple wines, offer thorough comparison of each option, highlighting their differences.
3) Explain the potential impact each option could bring to the user.
""")
end
end
errornote = ""
response = nothing # placeholder for show when error msg show up
errornote = ""
response = nothing # placeholder for show when error msg show up
for attempt in 1:10
usermsg = """
Recap: $(a.memory[:recap])
Your recent events: $timeline
Your Q&A: $(a.memory[:QandA])
$errornote
"""
for attempt in 1:10
QandA = generatequestion(a, a.func[:text2textInstructLLM]; recent=3)
_prompt =
[
Dict(:name => "system", :text => systemmsg),
Dict(:name => "user", :text => usermsg)
]
usermsg =
"""
Your status: $(GeneralUtils.dict_to_string(a.memory[:state]))
Your recent events: $timeline
Your Q&A: $QandA)
$errornote
"""
# put in model format
prompt = GeneralUtils.formatLLMtext(_prompt; formatname="llama3instruct")
prompt *= """
<|start_header_id|>assistant<|end_header_id|>
"""
_prompt =
[
Dict(:name => "system", :text => systemmsg),
Dict(:name => "user", :text => usermsg)
]
try
response = a.text2textInstructLLM(prompt)
responsedict = GeneralUtils.textToDict(response,
["Understanding", "Reasoning", "Plan", "Action_name", "Action_input", "Mentioned_brand"],
rightmarker=":", symbolkey=true, lowercasekey=true)
# put in model format
prompt = GeneralUtils.formatLLMtext(_prompt; formatname="llama3instruct")
prompt *= """
<|start_header_id|>assistant<|end_header_id|>
"""
if responsedict[:action_name] ∉ ["CHATBOX", "PRESENTBOX", "CHECKINVENTORY", "ENDCONVERSATION"]
errornote = "You must use the given functions"
error("You must use the given functions ", @__FILE__, " ", @__LINE__)
end
try
response = a.func[:text2textInstructLLM](prompt)
responsedict = GeneralUtils.textToDict(response,
["Understanding", "Reasoning", "Plan", "Action_name", "Action_input"],
rightmarker=":", symbolkey=true, lowercasekey=true)
for i ∈ [:understanding, :plan, :action_name]
if length(responsedict[i]) == 0
error("$i is empty ", @__FILE__, " ", @__LINE__)
if responsedict[:action_name] ∉ ["CHATBOX", "PRESENTBOX", "CHECKINVENTORY", "ENDCONVERSATION"]
errornote = "You must use the given functions"
error("You must use the given functions ", @__FILE__, " ", @__LINE__)
end
end
# check if there are more than 1 key per categories
for i ∈ [:understanding, :plan, :action_name, :action_input, :mentioned_brand]
matchkeys = GeneralUtils.findMatchingDictKey(responsedict, i)
if length(matchkeys) > 1
error("DecisionMaker has more than one key per categories")
end
end
println("\n~~~ Yiem decisionMaker() ", @__FILE__, " ", @__LINE__)
pprintln(Dict(responsedict))
# check whether an agent recommend wines before checking inventory or
# recommend wines outside its inventory
mentioned_brand = responsedict[:mentioned_brand]
if mentioned_brand != "None"
mentioned_brand = strip.(split(responsedict[:mentioned_brand], ","))
isWineInTimeline = false
for i in mentioned_brand
isWineInTimeline = occursin(i, timeline)
if !isWineInTimeline
break
for i ∈ [:understanding, :plan, :action_name]
if length(responsedict[i]) == 0
error("$i is empty ", @__FILE__, " ", @__LINE__)
end
end
isWineInShortmem = false
for i in mentioned_brand
isWineInShortmem = occursin(i, shortmem)
if !isWineInShortmem
break
# check if there are more than 1 key per categories
for i ∈ [:understanding, :plan, :action_name, :action_input]
matchkeys = GeneralUtils.findMatchingDictKey(responsedict, i)
if length(matchkeys) > 1
error("DecisionMaker has more than one key per categories")
end
end
if responsedict[:action_name] != "CHATBOX" && !isWineInShortmem
errornote = "Note: Before recommending a wine, ensure it's in your inventory. Check your stock first."
error("Before recommending a wine, ensure it's in your inventory. Check your stock first.")
elseif responsedict[:action_name] != "CHATBOX" && !isWineInTimeline && isWineInShortmem
errornote = "Note: You should introduce the wines to the user before taling about them."
error("You should introduce the wines to the user before taling about them.")
println("\n~~~ Yiem decisionMaker() ", @__FILE__, " ", @__LINE__)
pprintln(Dict(responsedict))
# check whether an agent recommend wines before checking inventory or recommend wines
# outside its inventory
# ask LLM whether there are any winery mentioned in the response
mentioned_winery = detectWineryName(a, response)
if mentioned_winery != "None"
mentioned_winery = String.(strip.(split(mentioned_winery, ",")))
# check whether the wine is in event
isWineInEvent = false
for winename in mentioned_winery
for event in a.memory[:events]
if event[:outcome] !== nothing && occursin(winename, event[:outcome])
isWineInEvent = true
break
end
end
end
# if wine is mentioned but not in timeline or shortmem,
# then the agent is not supposed to recommend the wine
if responsedict[:action_name] == "CHATBOX" &&
isWineInEvent == false
errornote = "Note: Before recommending a wine, ensure it's in your inventory. Check your stock first."
error("Before recommending a wine, ensure it's in your inventory. Check your stock first.")
end
end
if responsedict[:action_name] == "PRESENTBOX" && !isWineInShortmem
errornote = "Note: Before recommending a wine, ensure it's in your inventory. Check your stock first."
error("Before recommending a wine, ensure it's in your inventory. Check your stock first.")
elseif responsedict[:action_name] == "PRESENTBOX" && !isWineInTimeline
errornote = "Note: You already presented these wines."
error("You already presented these wines.")
if occursin("--|", response)
errornote = "Note: tables are not allowed. Do not include them your response."
error("your response contain tables which is not allowed.")
end
else
if responsedict[:action_name] == "PRESENTBOX"
errornote = "Note: You don't have wines to present."
error("You don't have wines to present.")
delete!(responsedict, :mentioned_winery)
# cache decision dict into vectorDB, this should be after new message is added to a.memory[:events]
println("\n~~~ Do you want to cache decision dict? (y/n)")
user_answer = readline()
if user_answer == "y"
timeline = timeline
decisiondict = responsedict
a.func[:insertSommelierDecision](timeline, decisiondict)
end
return responsedict
catch e
io = IOBuffer()
showerror(io, e)
errorMsg = String(take!(io))
st = sprint((io, v) -> show(io, "text/plain", v), stacktrace(catch_backtrace()))
println("\nAttempt $attempt. \nError occurred: $errorMsg\n$st \nPrompt $prompt", @__FILE__, " ", @__LINE__)
end
if occursin("--|", response)
errornote = "Note: tables are not allowed. Do not include them your response."
error("your response contain tables which is not allowed.")
end
delete!(responsedict, :mentioned_brand)
return responsedict
catch e
io = IOBuffer()
showerror(io, e)
errorMsg = String(take!(io))
st = sprint((io, v) -> show(io, "text/plain", v), stacktrace(catch_backtrace()))
println("\nAttempt $attempt. \nError occurred: $errorMsg\n$st \nPrompt $prompt", @__FILE__, " ", @__LINE__)
end
error("DecisionMaker failed to generate a thought ", response)
end
error("DecisionMaker failed to generate a thought ", response)
end
@@ -685,26 +694,17 @@ function conversation(a::sommelier, userinput::Dict)
)
# thinking loop until AI wants to communicate with the user
chatresponse = nothing
for i in 1:3
actionname, result = think(a)
if actionname == "CHATBOX" || actionname == "PRESENTBOX" || actionname == "ENDCONVERSATION"
if actionname ∈ ["CHATBOX", "PRESENTBOX", "ENDCONVERSATION"]
chatresponse = result
break
end
end
# thought will be added to chat model via context
chatresponse = generatechat(a)
addNewMessage(a, "assistant", chatresponse)
push!(a.memory[:events],
eventdict(;
event_description="the assistant talks to the user.",
timestamp=Dates.now(),
subject="assistant",
action_or_dialogue=chatresponse,
)
)
return chatresponse
end
end
@@ -762,9 +762,7 @@ julia>
"""
function think(a::T)::NamedTuple{(:actionname, :result),Tuple{String,String}} where {T<:agent}
a.memory[:recap] = generateSituationReport(a, a.text2textInstructLLM; skiprecent=3)
a.memory[:QandA] = generatequestion(a, a.text2textInstructLLM; recent=3)
a.memory[:recap] = generateSituationReport(a, a.func[:text2textInstructLLM]; skiprecent=3)
thoughtDict = decisionMaker(a; recent=3)
actionname = thoughtDict[:action_name]
@@ -778,16 +776,6 @@ function think(a::T)::NamedTuple{(:actionname, :result),Tuple{String,String}} wh
elseif actionname == "CHECKINVENTORY"
checkinventory(a, actioninput)
elseif actionname == "PRESENTBOX"
x =
"""
1) Provide detailed introductions of the wines to help the user make an informed choice.
2) If there are multiple wines, offer a thorough comparison of each option, highlighting their differences.
3) Explain the potential impact each option could bring to the user.
"""
# x = """
# 1) Introduce $actioninput in details for the user to choose."
# 2) Compare each option against the others in details and explain why each one is a suitable match for the user's specific needs.
# """
(result=actioninput, errormsg=nothing, success=true)
elseif actionname == "ENDCONVERSATION"
x = "Conclude the conversation, thanks the user then goodbye and inviting them to return next time."
@@ -798,6 +786,7 @@ function think(a::T)::NamedTuple{(:actionname, :result),Tuple{String,String}} wh
# this section allow LLM functions above to have different return values.
result = haskey(response, :result) ? response[:result] : nothing
rawresponse = haskey(response, :rawresponse) ? response[:rawresponse] : nothing
select = haskey(response, :select) ? response[:select] : nothing
reward::Integer = haskey(response, :reward) ? response[:reward] : 0
isterminal::Bool = haskey(response, :isterminal) ? response[:isterminal] : false
@@ -805,18 +794,44 @@ function think(a::T)::NamedTuple{(:actionname, :result),Tuple{String,String}} wh
success::Bool = haskey(response, :success) ? response[:success] : false
# manage memory (pass msg to generatechat)
if actionname == "CHATBOX"
a.memory[:CHATBOX] = result
if actionname ∈ ["CHATBOX", "PRESENTBOX", "ENDCONVERSATION"]
chatresponse = generatechat(a, result)
push!(a.memory[:events],
eventdict(;
event_description="the assistant talks to the user.",
timestamp=Dates.now(),
subject="assistant",
action_or_dialogue=chatresponse,
)
)
result = chatresponse
if actionname == "PRESENTBOX"
df = a.memory[:shortmem][:available_wine]
winename = join(df[:, :wine_name], ", ")
if a.memory[:state][:wine_presented_to_user] == "None"
a.memory[:state][:wine_presented_to_user] = winename
else
a.memory[:state][:wine_presented_to_user] *= ", $winename"
end
delete!(a.memory[:shortmem], :available_wine)
end
elseif actionname == "CHECKINVENTORY"
push!(a.memory[:shortmem], Dict(Symbol(actionname) => result))
elseif actionname == "PRESENTBOX" # tell the generatechat()
a.memory[:CHATBOX] = result
elseif actionname == "ENDCONVERSATION"
a.memory[:CHATBOX] = result
a.memory[:shortmem][:available_wine] = rawresponse
push!(a.memory[:events],
eventdict(;
event_description= "the assistant searched the database.",
timestamp= Dates.now(),
subject= "assistant",
action_or_dialogue= "I searched the database with this query: $actioninput",
outcome= "This is what I found in the database, $result"
)
)
else
error("condition is not defined")
error("condition is not defined ", @__FILE__, " ", @__LINE__)
end
return (actionname=actionname, result=result)
end
@@ -841,7 +856,7 @@ julia>
# Signature
"""
function generatechat(a::sommelier)
function generatechat(a::sommelier, thought::T) where {T<:AbstractString}
systemmsg =
"""
Your name is $(a.name). You are a helpful English-speaking assistant, acting as a polite, website-based sommelier for an online wine store.
@@ -858,8 +873,8 @@ function generatechat(a::sommelier)
At each round of conversation, you will be given the current situation:
Your ongoing conversation with the user: ...
Your thoughts: Your current thoughts in your mind
Context: ...
Your thoughts: Your current thoughts in your mind
You MUST follow the following guidelines:
- Do not offer additional services you didn't thought.
@@ -869,21 +884,20 @@ function generatechat(a::sommelier)
- If the user interrupts, prioritize the user
You should then respond to the user with:
1) Mentioned_brand: Are there any specific brand mentioned in your response? The answer can be the names of the brand or "None".
2) Chat: Given the situation, How would you respond to the user to express your thoughts honestly and keep the conversation going smoothly?
1) Chat: Given the situation, How would you respond to the user to express your thoughts honestly and keep the conversation going smoothly?
You should only respond in format as described below:
Mentioned_brand: ...
Chat: ...
Let's begin!
"""
# a.memory[:shortmem][:available_wine] is a dataframe.
context =
if length(a.memory[:shortmem]) > 0
vectorOfDictToText(a.memory[:shortmem], withkey=false)
if haskey(a.memory[:shortmem], :available_wine)
"Available wine $(GeneralUtils.dfToString(a.memory[:shortmem][:available_wine]))"
else
""
"None"
end
chathistory = vectorOfDictToText(a.chathistory)
@@ -893,8 +907,8 @@ function generatechat(a::sommelier)
for attempt in 1:10
usermsg = """
Your ongoing conversation with the user: $chathistory
$context
Your thoughts: $(a.memory[:CHATBOX])
Contex: $context
Your thoughts: $thought
$errornote
"""
@@ -911,8 +925,8 @@ function generatechat(a::sommelier)
"""
try
response = a.text2textInstructLLM(prompt)
responsedict = GeneralUtils.textToDict(response, ["Mentioned_brand", "Chat"],
response = a.func[:text2textInstructLLM](prompt)
responsedict = GeneralUtils.textToDict(response, ["Chat"],
rightmarker=":", symbolkey=true, lowercasekey=true)
for i ∈ [:chat]
@@ -937,30 +951,33 @@ function generatechat(a::sommelier)
println("\n~~~ generatechat() ", @__FILE__, " ", @__LINE__)
pprintln(Dict(responsedict))
# check if LLM recommend wine before checking inventory
ind = 1:length(a.memory[:events])
timeline = ""
for (i, event) in enumerate(a.memory[:events][ind])
if event[:outcome] === nothing
timeline *= "$i) $(event[:subject])> $(event[:action_or_dialogue])\n"
else
timeline *= "$i) $(event[:subject])> $(event[:action_or_dialogue]) $(event[:outcome])\n"
end
end
# check whether an agent recommend wines before checking inventory or
# recommend wines outside its inventory
mentioned_brand = strip.(split(responsedict[:mentioned_brand], ","))
for i in mentioned_brand
if i != "None" && i != "" && (!occursin(i, timeline) || !occursin(i, context)) &&
responsedict[:action_name] != "CHECKINVENTORY" # OK if the agent is checking inventory
#[WORKING] check whether an agent recommend wines before checking inventory or recommend wines
# outside its inventory
# ask LLM whether there are any winery mentioned in the response
mentioned_winery = detectWineryName(a, responsedict[:chat])
if mentioned_winery != "None"
mentioned_winery = String.(strip.(split(mentioned_winery, ",")))
errornote = "Note: Before recommending a wine, ensure it's in your inventory. Check your stock first."
error("Before recommending a wine, ensure it's in your inventory. Check your stock first.")
# check whether the wine is in event
isWineInEvent = false
for winename in mentioned_winery
for event in a.memory[:events]
if event[:outcome] !== nothing && occursin(winename, event[:outcome])
isWineInEvent = true
break
end
end
end
# if wine is mentioned but not in timeline or shortmem,
# then the agent is not supposed to recommend the wine
if isWineInEvent == false
errornote = "Note: You are not supposed to recommend a wine that is not in your inventory."
error("Note: You are not supposed to recommend a wine that is not in your inventory.")
end
end
a.memory[:CHATBOX] = "" # delete content because it no longer used.
delete!(responsedict, :mentioned_brand)
result = responsedict[:chat]
return result
@@ -972,7 +989,7 @@ function generatechat(a::sommelier)
println("\nAttempt $attempt. Error occurred: $errorMsg\n$st ", @__FILE__, " ", @__LINE__)
end
end
error("generatechat failed to generate an evaluation")
error("generatechat failed to generate a response")
end
@@ -1002,12 +1019,10 @@ function generatechat(a::companion)
chathistory = vectorOfDictToText(a.chathistory)
response = nothing # placeholder for show when error msg show up
noise = ""
for attempt in 1:10
usermsg = """
Your ongoing conversation with the user: $chathistory
$noise
"""
_prompt =
@@ -1023,7 +1038,7 @@ function generatechat(a::companion)
"""
try
response = a.text2textInstructLLM(prompt)
response = a.func[:text2textInstructLLM](prompt)
println("\n~~~ generatechat() ", @__FILE__, " ", @__LINE__)
pprintln(response)
@@ -1039,10 +1054,9 @@ function generatechat(a::companion)
errorMsg = String(take!(io))
st = sprint((io, v) -> show(io, "text/plain", v), stacktrace(catch_backtrace()))
println("\n Attempt $attempt. Error occurred: $errorMsg\n$st ", @__FILE__, " ", @__LINE__)
noise = GeneralUtils.randstrings(3, 5)
end
end
error("generatechat failed to generate an evaluation")
error("generatechat failed to generate a response")
end
@@ -1050,7 +1064,7 @@ function generatequestion(a, text2textInstructLLM::Function; recent=nothing)::St
systemmsg =
"""
Your name is $(a.name). You are a helpful English-speaking assistant, acting as a polite, website-based sommelier for $(a.retailername)'s online store.
Your name is $(a.name). You are a helpful English-speaking, website-based sommelier for $(a.retailername)'s online store.
Your goal includes:
1) Help the user select the best wines from your inventory that align with the user's preferences
2) Thanks the user when they don't need any further assistance and invite them to comeback next time
@@ -1062,12 +1076,13 @@ function generatequestion(a, text2textInstructLLM::Function; recent=nothing)::St
1) Processing sales orders or engaging in any other sales-related activities.
At each round of conversation, you will be given the current situation:
Your recent events: ...
Context: ...
Your status: your current status
Recap: recap of what has happened so far
Your recent events: latest 5 events of the situation
You must follow the following guidelines:
- Your question should be specific, self-contained and not require any additional context.
- Once the user has selected their wine, ask the user if they need any further assistance. Do not offer any additional services. If the user doesn't need any further assistance, say goodbye and invite them to come back next time.
- Once the user has chose their wine, your task almost done. Ask the user if they need any further assistance. Do not offer any additional services. If the user doesn't need any further assistance, say goodbye and invite them to come back next time.
You should follow the following guidelines:
- Focus on the latest conversation
@@ -1151,16 +1166,16 @@ function generatequestion(a, text2textInstructLLM::Function; recent=nothing)::St
end
end
errornote = ""
noise = ""
response = nothing # store for show when error msg show up
for attempt in 1:10
usermsg = """
Recap: $(a.memory[:recap])
Your recent events: $timeline
$errornote
$noise
"""
usermsg =
"""
Your status: $(GeneralUtils.dict_to_string(a.memory[:state]))
Recap: $(a.memory[:recap])
Your recent events: $timeline
$errornote
"""
_prompt =
[
@@ -1187,7 +1202,8 @@ function generatequestion(a, text2textInstructLLM::Function; recent=nothing)::St
q_number = count("Q", response)
# check for valid response
if q_number < 3
q_atleast = length(a.memory[:events]) <= 2 ? 1 : 3
if q_number < q_atleast
error("too few questions only $q_number questions are generated ", @__FILE__, " ", @__LINE__)
# check whether "A1" is in the response, if not error.
elseif !occursin("A1:", response)
@@ -1207,10 +1223,9 @@ function generatequestion(a, text2textInstructLLM::Function; recent=nothing)::St
errorMsg = String(take!(io))
st = sprint((io, v) -> show(io, "text/plain", v), stacktrace(catch_backtrace()))
println("\nAttempt $attempt. Error occurred: $errorMsg\n$st ", @__FILE__, " ", @__LINE__)
noise = GeneralUtils.randstrings(3, 5)
end
end
error("generatequestion failed to generate a thought ", response)
error("generatequestion failed to generate a response ", response)
end
@@ -1219,7 +1234,7 @@ function generateSituationReport(a, text2textInstructLLM::Function; skiprecent::
systemmsg =
"""
You are the assistant being in the given events.
You are an assistant being in the given events.
Your task is to writes a summary for each event in an ongoing, interleaving series.
At each round of conversation, you will be given the situation:
@@ -1288,11 +1303,74 @@ function generateSituationReport(a, text2textInstructLLM::Function; skiprecent::
return Dict(:recap => response)
end
error("generateSituationReport failed to generate a thought ", response)
error("generateSituationReport failed to generate a response ", response)
end
function detectWineryName(a, text)
systemmsg =
"""
You are a sommelier of a wine store.
Your task is to identify and list any winery names mentioned in the provided text.
At each round of conversation, you will be given the situation:
Text: a text describing the situation.
You should then respond to the user with:
Winery_names: A list of winery names mentioned in the text or "None" if no winery name is mentioned.
You must only respond in format as described below:
Winery_names: ...
Here are some examples:
Winery_names: Domaine Courbis, Chateau Lafite Rothschild, Matarromera Domaine Roulot
Let's begin!
"""
response = nothing # placeholder for show when error msg show up
for attempt in 1:10
usermsg = """
Text: $text
"""
_prompt =
[
Dict(:name => "system", :text => systemmsg),
Dict(:name => "user", :text => usermsg)
]
# put in model format
prompt = GeneralUtils.formatLLMtext(_prompt; formatname="llama3instruct")
prompt *= """
<|start_header_id|>assistant<|end_header_id|>
"""
try
response = a.func[:text2textInstructLLM](prompt)
println("\n~~~ detectWineryName() ", @__FILE__, " ", @__LINE__)
pprintln(response)
responsedict = GeneralUtils.textToDict(response, ["winery_names"],
rightmarker=":", symbolkey=true, lowercasekey=true)
result = responsedict[:winery_names]
return result
catch e
io = IOBuffer()
showerror(io, e)
errorMsg = String(take!(io))
st = sprint((io, v) -> show(io, "text/plain", v), stacktrace(catch_backtrace()))
println("\n Attempt $attempt. Error occurred: $errorMsg\n$st ", @__FILE__, " ", @__LINE__)
end
end
error("detectWineryName failed to generate a response")
end

36
src/llmfunction.jl
View File

@@ -288,32 +288,24 @@ julia> result = checkinventory(agent, input)
# Signature
"""
function checkinventory(a::T1, input::T2
)::NamedTuple{(:result, :success, :errormsg), Tuple{String, Bool, Union{String, Nothing}}} where {T1<:agent, T2<:AbstractString}
) where {T1<:agent, T2<:AbstractString}
println("\n~~~ checkinventory order: $input ", @__FILE__, " ", @__LINE__)
wineattributes_1 = extractWineAttributes_1(a, input)
wineattributes_2 = extractWineAttributes_2(a, input)
inventoryquery = "retailer name: $(a.retailername), $wineattributes_1, $wineattributes_2"
_inventoryquery = "retailer name: $(a.retailername), $wineattributes_1, $wineattributes_2"
inventoryquery = "Retrieves winery, wine_name, vintage, region, country, wine_type, grape, serving_temperature, sweetness, intensity, tannin, acidity, tasting_notes, price and currency of wines that match the following criteria - {$_inventoryquery}"
println("~~~ checkinventory input: $inventoryquery ", @__FILE__, " ", @__LINE__)
result = SQLLLM.query(inventoryquery, a.executeSQL, a.text2textInstructLLM,
addSQLVectorDB=a.addSQLVectorDB,
querySQLVectorDB=a.querySQLVectorDB)
push!(a.memory[:events],
eventdict(;
event_description= "the assistant searched the database.",
timestamp= Dates.now(),
subject= "assistant",
action_or_dialogue= "I searched the database with this query: $inventoryquery",
outcome= "This is what I found in the database, $result"
)
)
# add suppport for similarSQLVectorDB
textresult, rawresponse = SQLLLM.query(inventoryquery, a.func[:executeSQL],
a.func[:text2textInstructLLM],
addSQLVectorDB=a.func[:insertSQLVectorDB],
similarSQLVectorDB=a.func[:similarSQLVectorDB])
println("\n~~~ checkinventory result ", @__FILE__, " ", @__LINE__)
println(result)
println(textresult)
return (result=result, success=true, errormsg=nothing)
return (result=textresult, rawresponse=rawresponse, success=true, errormsg=nothing)
end
@@ -425,13 +417,11 @@ function extractWineAttributes_1(a::T1, input::T2)::String where {T1<:agent, T2<
"""
try
response = a.text2textInstructLLM(prompt)
response = a.func[:text2textInstructLLM](prompt)
# check wheter all attributes are in the response
for word in attributes
if !occursin(word, response)
noise = String(rand('a':'z', 5))
errornote = "Background noise $noise"
error("$word attribute is missing")
end
end
@@ -611,7 +601,7 @@ function extractWineAttributes_2(a::T1, input::T2)::String where {T1<:agent, T2<
for attempt in 1:5
try
response = a.text2textInstructLLM(prompt)
response = a.func[:text2textInstructLLM](prompt)
responsedict = GeneralUtils.textToDict(response, attributes, rightmarker=":", symbolkey=true)
for i ∈ attributes
@@ -746,7 +736,7 @@ end
# """
# try
# response = a.text2textInstructLLM(prompt)
# response = a.func[:text2textInstructLLM](prompt)
# responsedict = GeneralUtils.textToDict(response, attributes, rightmarker=":", symbolkey=true)
# for i ∈ attributes

30
src/type.jl
View File

@@ -42,8 +42,9 @@ function companion(
memory = Dict{Symbol, Any}(
:chatbox=> "",
:shortmem=> Vector{Dict{Symbol, String}}(),
:events=> Vector{Dict{Symbol, Any}}()
:shortmem=> OrderedDict{Symbol, Any}(),
:events=> Vector{Dict{Symbol, Any}}(),
:state=> Dict{Symbol, Any}(),
)
newAgent = companion(
@@ -146,18 +147,11 @@ mutable struct sommelier <: agent
chathistory::Vector{Dict{Symbol, Any}}
memory::Dict{Symbol, Any}
# communication function
text2textInstructLLM::Function
executeSQL::Function
querySQLVectorDB::Function
addSQLVectorDB::Function
func # NamedTuple of functions
end
function sommelier(
text2textInstructLLM::Function,
executeSQL::Function,
querySQLVectorDB::Function,
addSQLVectorDB::Function
func, # NamedTuple of functions
;
name::String= "Assistant",
id::String= string(uuid4()),
@@ -185,10 +179,13 @@ function sommelier(
# ),
)
memory = Dict{Symbol, Any}(
memory = Dict{Symbol, Any}(
:chatbox=> "",
:shortmem=> Vector{Dict{Symbol, String}}(),
:events=> Vector{Dict{Symbol, Any}}()
:shortmem=> OrderedDict{Symbol, Any}(),
:events=> Vector{Dict{Symbol, Any}}(),
:state=> Dict{Symbol, Any}(
:wine_presented_to_user=> "None",
),
)
newAgent = sommelier(
@@ -199,10 +196,7 @@ function sommelier(
maxHistoryMsg,
chathistory,
memory,
text2textInstructLLM,
executeSQL,
querySQLVectorDB,
addSQLVectorDB
func
)
return newAgent

63
src/util.jl
View File

@@ -116,42 +116,55 @@ function addNewMessage(a::T1, name::String, text::T2;
end
"""
""" Converts a vector of dictionaries to a formatted string.
This function takes in a vector of dictionaries and outputs a single string where each dictionary's keys are prefixed by their values.
# Arguments
- `v::Integer`
dummy variable
- `vecd::Vector`
a vector of dictionaries
- `withkey::Bool`
whether to include the key in the output text. Default is true
# Return
a string with the formatted dictionaries
# Example
```jldoctest
julia>
julia> using Revise
julia> using GeneralUtils
julia> vecd = [Dict(:name => "John", :text => "Hello"), Dict(:name => "Jane", :text => "Goodbye")]
julia> GeneralUtils.vectorOfDictToText(vecd, withkey=true)
"John> Hello\nJane> Goodbye\n"
```
# TODO
- [] update docstring
- [x] implement the function
# Signature
"""
function vectorOfDictToText(vecd::Vector; withkey=true)
function vectorOfDictToText(vecd::Vector; withkey=true)::String
# Initialize an empty string to hold the final text
text = ""
# Determine whether to include the key in the output text or not
if withkey
for d in vecd
name = d[:name]
_text = d[:text]
text *= "$name> $_text \n"
end
else
for d in vecd
for (k, v) in d
text *= "$v \n"
# Loop through each dictionary in the input vector
for d in vecd
# Extract the 'name' and 'text' keys from the dictionary
name = d[:name]
_text = d[:text]
# Append the formatted string to the text variable
text *= "$name> $_text \n"
end
else
# Loop through each dictionary in the input vector
for d in vecd
# Iterate over all key-value pairs in the dictionary
for (k, v) in d
# Append the formatted string to the text variable
text *= "$v \n"
end
end
end
end
# Return the final text
return text
end
@@ -181,16 +194,6 @@ function eventdict(;
end
noise(n::Integer) = String(rand('a':'z', n))
function noises(totalword::Integer, wordlength::Integer)
noises = ""
for i in 1:totalword
noises *= noise(wordlength) * " "
end
noises = strip(noises)
return noises
end
# """ Convert a single chat dictionary into LLM model instruct format.

410
test/runtest.jl
View File

@@ -1,227 +1,255 @@
using Revise # remove when this package is completed
using YiemAgent, GeneralUtils, JSON3, MQTTClient, Dates, UUIDs, LibPQ, Base64, DataFrames
using Revise
using JSON, JSON3, MQTTClient, Dates, UUIDs, PrettyPrinting, LibPQ, Base64, DataFrames
using YiemAgent, GeneralUtils
using Base.Threads
# ---------------------------------------------- 100 --------------------------------------------- #
config = copy(JSON3.read("config.json"))
# instanceInternalTopic = config[:serviceInternalTopic][:mqtttopic] * "/1"
# client, connection = MakeConnection(config[:mqttServerInfo][:broker],
# config[:mqttServerInfo][:port])
receiveUserMsgChannel = Channel{Dict}(4)
# receiveInternalMsgChannel = Channel{Dict}(4)
# println(typeof(connection))
# msgMeta = GeneralUtils.generate_msgMeta(
# "N/A",
# replyTopic = config[:servicetopic][:mqtttopic] # ask frontend reply to this instance_chat_topic
# )
# load config
config = copy(JSON3.read("../mountvolume/config.json"))
function executeSQL(sql::T) where {T<:AbstractString}
DBconnection = LibPQ.Connection("host=192.168.88.12 port=5432 dbname=yiem_wine_assistant user=yiem password=yiem@Postgres_0.0")
DBconnection = LibPQ.Connection("host=192.168.88.12 port=10201 dbname=wineDB user=yiemtechnologies password=yiemtechnologies@Postgres_0.0")
result = LibPQ.execute(DBconnection, sql)
close(DBconnection)
return result
end
function executeSQLVectorDB(sql)
DBconnection = LibPQ.Connection("host=192.168.88.12 port=10203 dbname=SQLVectorDB user=yiemtechnologies password=yiemtechnologies@Postgres_0.0")
result = LibPQ.execute(DBconnection, sql)
close(DBconnection)
return result
end
function text2textInstructLLM(prompt::String)
msgMeta = GeneralUtils.generate_msgMeta(
config[:externalservice][:text2textinstruct][:mqtttopic];
msgPurpose= "inference",
senderName= "yiemagent",
senderId= string(uuid4()),
receiverName= "text2textinstruct",
mqttBrokerAddress= config[:mqttServerInfo][:broker],
mqttBrokerPort= config[:mqttServerInfo][:port],
msgPurpose="inference",
senderName="yiemagent",
senderId=string(uuid4()),
receiverName="text2textinstruct",
mqttBrokerAddress=config[:mqttServerInfo][:broker],
mqttBrokerPort=config[:mqttServerInfo][:port],
)
outgoingMsg = Dict(
:msgMeta=> msgMeta,
:payload=> Dict(
:text=> prompt,
:kwargs=> Dict(
:max_tokens=> 2048,
:stop=> ["<|eot_id|>"],
:temperature=> 0.2,
)
:msgMeta => msgMeta,
:payload => Dict(
:text => prompt,
:kwargs => Dict(
:num_ctx => 16384,
:temperature => 0.2,
)
)
)
_response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg; timeout=120)
_response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg; timeout=6000)
response = _response[:response][:text]
return response
end
function executeSQLVectorDB(sql)
DBconnection = LibPQ.Connection("host=192.168.88.12 port=5433 dbname=SQLVectorDB user=yiemtechnologies@gmail.com password=yiem@Postgres_0.0")
result = LibPQ.execute(DBconnection, sql)
close(DBconnection)
return result
end
function addSQLVectorDB(state)
# get embedding of the query
query = [state[:thoughtHistory][:question]]
# get text embedding from a LLM service
function getEmbedding(text::T) where {T<:AbstractString}
msgMeta = GeneralUtils.generate_msgMeta(
config[:externalservice][:text2textinstruct][:mqtttopic];
msgPurpose= "embedding",
senderName= "yiemagent",
senderId= string(uuid4()),
receiverName= "text2textinstruct",
mqttBrokerAddress= config[:mqttServerInfo][:broker],
mqttBrokerPort= config[:mqttServerInfo][:port],
msgPurpose="embedding",
senderName="yiemagent",
senderId=string(uuid4()),
receiverName="text2textinstruct",
mqttBrokerAddress=config[:mqttServerInfo][:broker],
mqttBrokerPort=config[:mqttServerInfo][:port],
)
outgoingMsg = Dict(
:msgMeta=> msgMeta,
:payload=> Dict(
:text=> query
)
:msgMeta => msgMeta,
:payload => Dict(
:text => [text] # must be a vector of string
)
)
response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
embedding = response[:response][:embeddings][1]
embedding = response[:response][:embeddings]
return embedding
end
function findSimilarTextFromVectorDB(text::T1, tablename::T2, embeddingColumnName::T3,
vectorDB::Function; limit::Integer=1
)::DataFrame where {T1<:AbstractString, T2<:AbstractString, T3<:AbstractString}
# get embedding from LLM service
embedding = getEmbedding(text)[1]
# check whether there is close enough vector already store in vectorDB. if no, add, else skip
sql =
"""
SELECT *, embedding <-> '$embedding' as distance
FROM sql_statement_repository
ORDER BY distance LIMIT 1;
"""
response = executeSQLVectorDB(sql)
sql = """
SELECT *, $embeddingColumnName <-> '$embedding' as distance
FROM $tablename
ORDER BY distance LIMIT $limit;
"""
response = vectorDB(sql)
df = DataFrame(response)
return df
end
function similarSQLVectorDB(query; maxdistance::Integer=100)
tablename = "sqlllm_decision_repository"
# get embedding of the query
df = findSimilarTextFromVectorDB(query, tablename,
"function_input_embedding", executeSQLVectorDB)
row, col = size(df)
distance = row == 0 ? Inf : df[1, :distance]
if row == 0 || distance > 10 # no close enough SQL stored in the database
latestKey, _ = GeneralUtils.findHighestIndexKey(state[:thoughtHistory], :action_input)
_sqlStatement = state[:thoughtHistory][latestKey]
if occursin("SELECT", _sqlStatement) # make sure it is an SQL statement before adding into DB
sqlStatementBase64 = base64encode(_sqlStatement)
sqlStatement = replace(_sqlStatement, "'"=>"")
sql =
"""
INSERT INTO sql_statement_repository (question, sql_statement, sql_statement_base64, embedding) VALUES ('$query', '$sqlStatement', '$sqlStatementBase64', '$embedding');
"""
_ = executeSQLVectorDB(sql)
println("--> added new SQL statement to vectorDB ", @__FILE__, " ", @__LINE__)
println(sqlStatement)
end
if row != 0 && distance < maxdistance
# if there is usable SQL, return it.
output_b64 = df[1, :function_output_base64] # pick the closest match
output_str = String(base64decode(output_b64))
rowid = df[1, :id]
println("\n~~~ found similar sql. row id $rowid, distance $distance ", @__FILE__, " ", @__LINE__)
return (dict=output_str, distance=distance)
else
println("\n~~~ similar sql not found, max distance $maxdistance ", @__FILE__, " ", @__LINE__)
return (dict=nothing, distance=nothing)
end
end
function querySQLVectorDB(state)
# provide similarSQL at the first time thinking only
latestKey, _ = GeneralUtils.findHighestIndexKey(state[:thoughtHistory], :action_input)
if latestKey === nothing
# get embedding of the query
query = [state[:thoughtHistory][:question]]
msgMeta = GeneralUtils.generate_msgMeta(
config[:externalservice][:text2textinstruct][:mqtttopic];
msgPurpose= "embedding",
senderName= "yiemagent",
senderId= string(uuid4()),
receiverName= "text2textinstruct",
mqttBrokerAddress= config[:mqttServerInfo][:broker],
mqttBrokerPort= config[:mqttServerInfo][:port],
)
function insertSQLVectorDB(query::T1, SQL::T2; maxdistance::Integer=1) where {T1<:AbstractString, T2<:AbstractString}
tablename = "sqlllm_decision_repository"
# get embedding of the query
# query = state[:thoughtHistory][:question]
df = findSimilarTextFromVectorDB(query, tablename,
"function_input_embedding", executeSQLVectorDB)
row, col = size(df)
distance = row == 0 ? Inf : df[1, :distance]
if row == 0 || distance > maxdistance # no close enough SQL stored in the database
query_embedding = getEmbedding(query)[1]
query = replace(query, "'" => "")
sql_base64 = base64encode(SQL)
sql_ = replace(SQL, "'" => "")
outgoingMsg = Dict(
:msgMeta=> msgMeta,
:payload=> Dict(
:text=> query
)
)
response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
embedding = response[:response][:embeddings][1]
# check whether there is close enough vector already store in vectorDB. if no, add, else skip
sql =
"""
SELECT *, embedding <-> '$embedding' as distance
FROM sql_statement_repository
ORDER BY distance LIMIT 1;
"""
response = executeSQLVectorDB(sql)
df = DataFrame(response)
row, col = size(df)
distance = row == 0 ? Inf : df[1, :distance]
if row != 0 && distance < 100
# if there is usable SQL, return it.
sqlStatementBase64 = df[1, :sql_statement_base64]
sqlStatement = String(base64decode(sqlStatementBase64))
println("--> getting SQL statement from vectorDB ", @__FILE__, " ", @__LINE__)
println(sqlStatement)
return sqlStatement
else
return nothing
end
sql = """
INSERT INTO $tablename (function_input, function_output, function_output_base64, function_input_embedding) VALUES ('$query', '$sql_', '$sql_base64', '$query_embedding');
"""
println("\n~~~ added new decision to vectorDB ", @__FILE__, " ", @__LINE__)
println(sql)
_ = executeSQLVectorDB(sql)
end
return nothing
end
# Instantiate an agent
function similarSommelierDecision(recentevents::T1; maxdistance::Integer=5
)::Union{AbstractDict, Nothing} where {T1<:AbstractString}
tablename = "sommelier_decision_repository"
# find similar
println("\n~~~ search vectorDB for this: $recentevents ", @__FILE__, " ", @__LINE__)
df = findSimilarTextFromVectorDB(recentevents, tablename,
"function_input_embedding", executeSQLVectorDB)
row, col = size(df)
distance = row == 0 ? Inf : df[1, :distance]
if row != 0 && distance < maxdistance
# if there is usable decision, return it.
rowid = df[1, :id]
println("\n~~~ found similar decision. row id $rowid, distance $distance ", @__FILE__, " ", @__LINE__)
output_b64 = df[1, :function_output_base64] # pick the closest match
_output_str = String(base64decode(output_b64))
output = copy(JSON3.read(_output_str))
return output
else
println("\n~~~ similar decision not found, max distance $maxdistance ", @__FILE__, " ", @__LINE__)
return nothing
end
end
function insertSommelierDecision(recentevents::T1, decision::T2; maxdistance::Integer=5
) where {T1<:AbstractString, T2<:AbstractDict}
tablename = "sommelier_decision_repository"
# find similar
df = findSimilarTextFromVectorDB(recentevents, tablename,
"function_input_embedding", executeSQLVectorDB)
row, col = size(df)
distance = row == 0 ? Inf : df[1, :distance]
if row == 0 || distance > maxdistance # no close enough SQL stored in the database
recentevents_embedding = a.func[:getEmbedding](recentevents)[1]
recentevents = replace(recentevents, "'" => "")
decision_json = JSON3.write(decision)
decision_base64 = base64encode(decision_json)
decision = replace(decision_json, "'" => "")
sql = """
INSERT INTO $tablename (function_input, function_output, function_output_base64, function_input_embedding) VALUES ('$recentevents', '$decision', '$decision_base64', '$recentevents_embedding');
"""
println("\n~~~ added new decision to vectorDB ", @__FILE__, " ", @__LINE__)
println(sql)
_ = executeSQLVectorDB(sql)
else
println("~~~ similar decision previously cached, distance $distance ", @__FILE__, " ", @__LINE__)
end
end
sessionId = "12345"
externalFunction = (
getEmbedding=getEmbedding,
text2textInstructLLM=text2textInstructLLM,
executeSQL=executeSQL,
similarSQLVectorDB=similarSQLVectorDB,
insertSQLVectorDB=insertSQLVectorDB,
similarSommelierDecision=similarSommelierDecision,
insertSommelierDecision=insertSommelierDecision,
)
a = YiemAgent.sommelier(
text2textInstructLLM,
executeSQL,
querySQLVectorDB,
addSQLVectorDB;
name= "Jene",
id= "tempId", # agent instance id
externalFunction;
name="Ton",
id=sessionId, # agent instance id
retailername="Yiem",
)
function main()
for i in 1:10
userinput = ""
for i in 1:3
if userinput == ""
println("")
println("--> user input:")
userinput = readline()
else
break
end
end
response = YiemAgent.conversation(a, Dict(:text=> userinput))
println("")
println("--> assistant response: \n", response)
end
while true
println("your respond: ")
user_answer = readline()
response = YiemAgent.conversation(a, Dict(:text=> user_answer))
println("\n$response")
end
main()
"""
I'm joining a graduation party this evening. I want to get a bottle of white wine from the US to celebrate. I'm ok with any price range.
Well, the party is small casual with close friends and no food serving.
I'm open to suggestion since I have no specific idea.
I'm ok with any region.
The input is instructions on how you want the presentation to be conducted.
"""
wines =
"""
Summary: This table contains two wine records, both from the United States, with white wine types, moderate sweetness (2), and high intensity (5).
More details: 1) wine_id: add9824f-81b0-47da-a08a-ee20498bc6c8, wine_name: Belle Cote Chardonnay, brand: Peter Michael, manufacturer: Peter Michael, region: Californian, country: United States, wine_type: white, grape_variety: Chardonnay, serving_temperature: 11 to 13 Celsius, intensity: 5, sweetness: 2, tannin: missing, acidity: 3, fizziness: missing, tasting_notes: oak, butter, vanilla, cream, oil, lemon curd, pear, peach, apple
2) wine_id: ff9a494c-e916-44c4-9385-1c18b23aa825, wine_name: Ma Belle-Fille Chardonnay, brand: Peter Michael, manufacturer: Peter Michael, region: Californian, country: United States, wine_type: white, grape_variety: Chardonnay, serving_temperature: 11 to 13 Celsius, intensity: 5, sweetness: 2, tannin: missing, acidity: 3, fizziness: missing, tasting_notes: oak, butter, vanilla, cream, banana, cheese, apricot, peach, apple
"""
# response = YiemAgent.conversation(a, Dict(:text=> "newtopic",) )
# response = YiemAgent.conversation(a, Dict(:text=> "Hello, I would like a get a bottle of wine."))
# println("---> YiemAgent: ", response)
# response = YiemAgent.conversation(a, Dict(:text=> "I'm having a graduation party this evening. I'll pay at most 30 bucks."))
# response = YiemAgent.conversation(a, Dict(:text=> "I want to get a French red wine under 100."))
@@ -229,60 +257,16 @@ More details: 1) wine_id: add9824f-81b0-47da-a08a-ee20498bc6c8, wine_name: Belle
# # input = "query=\"off dry, medium tannin, French Rosé\""
# input = "Search the database for wine type: white, country: France, sweetness level: 1"
# YiemAgent.winestock(a, input)
# input = "French dry white wines with medium body"
# input = "query=\"medium-bodied dry white wine\""
# # input = "the customer is looking for a medium-bodied, dry white wine."
# result = YiemAgent.checkinventory(a, input)
error("test done")
function run_with_timeout(f, args...; timeout=5)
result = Ref{Any}()
task = Threads.@spawn try
result[] = f(args...)
catch e
println("Task interrupted: ", e)
end
Timer(timeout) do _
if !istaskdone(task)
schedule(task, InterruptException())
println("Task did not complete in time. Aborting.")
else
println("Task completed within the timeout.")
end
end
return result[]
end
# Example function that takes arguments and returns a value
function example_function(x, y)
sleep(10) # Simulate a long-running task
return x + y
end
# Example usage
result = run_with_timeout(example_function, 3, 4; timeout=5)
println("Result: ", result)
a = `$"hello\nworld"`
a = $"hello\nworld"
a = """$("hello\nworld")"""