Merge pull request 'update' (#38) from v0.7.4-add_vector_search into v0.7.4

Reviewed-on: #38

Manifest.toml

@@ -2,7 +2,7 @@
 
 julia_version = "1.12.6"
 manifest_format = "2.0"
-project_hash = "95dc0193a18325ca5b1e37deab8108d1b35915db"
+project_hash = "1c1379a2cec320abc347f3acb5ee815ba9855aa6"
 
 [[deps.Accessors]]
 deps = ["CompositionsBase", "ConstructionBase", "Dates", "InverseFunctions", "MacroTools"]
@@ -38,6 +38,12 @@ version = "1.1.3"
 uuid = "0dad84c5-d112-42e6-8d28-ef12dabb789f"
 version = "1.1.2"
 
+[[deps.ArnoldiMethod]]
+deps = ["LinearAlgebra", "Random", "StaticArrays"]
+git-tree-sha1 = "d57bd3762d308bded22c3b82d033bff85f6195c6"
+uuid = "ec485272-7323-5ecc-a04f-4719b315124d"
+version = "0.4.0"
+
 [[deps.ArrowTypes]]
 deps = ["Sockets", "UUIDs"]
 git-tree-sha1 = "404265cd8128a2515a81d5eae16de90fdef05101"
@@ -91,9 +97,9 @@ uuid = "944b1d66-785c-5afd-91f1-9de20f533193"
 version = "0.7.8"
 
 [[deps.CommonSolve]]
-git-tree-sha1 = "99ee296f88c12485402e37c2fd025f95ae097637"
+git-tree-sha1 = "eeaad7cef88554c2fa56b5a3f71cfd5cb708c662"
 uuid = "38540f10-b2f7-11e9-35d8-d573e4eb0ff2"
-version = "0.2.9"
+version = "0.2.11"
 
 [[deps.Compat]]
 deps = ["TOML", "UUIDs"]
@@ -181,6 +187,20 @@ git-tree-sha1 = "e98abef36d02a0ec385d68cd7dadbce9b28cbd88"
 uuid = "abce61dc-4473-55a0-ba07-351d65e31d42"
 version = "0.4.1"
 
+[[deps.Distances]]
+deps = ["LinearAlgebra", "Statistics", "StatsAPI"]
+git-tree-sha1 = "c7e3a542b999843086e2f29dac96a618c105be1d"
+uuid = "b4f34e82-e78d-54a5-968a-f98e89d6e8f7"
+version = "0.10.12"
+
+    [deps.Distances.extensions]
+    DistancesChainRulesCoreExt = "ChainRulesCore"
+    DistancesSparseArraysExt = "SparseArrays"
+
+    [deps.Distances.weakdeps]
+    ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
+    SparseArrays = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"
+
 [[deps.Distributed]]
 deps = ["Random", "Serialization", "Sockets"]
 uuid = "8ba89e20-285c-5b6f-9357-94700520ee1b"
@@ -224,11 +244,21 @@ git-tree-sha1 = "27415f162e6028e81c72b82ef756bf321213b6ec"
 uuid = "e2ba6199-217a-4e67-a87a-7c52f15ade04"
 version = "0.1.10"
 
+[[deps.EzXML]]
+deps = ["Printf", "XML2_jll"]
+git-tree-sha1 = "7ea1aa5869e2626ccae84480e4f37185bc6f41d3"
+uuid = "8f5d6c58-4d21-5cfd-889c-e3ad7ee6a615"
+version = "1.2.3"
+
 [[deps.FileIO]]
 deps = ["Pkg", "Requires", "UUIDs"]
-git-tree-sha1 = "91e0e5c68d02bcdaae76d3c8ceb4361e8f28d2e9"
+git-tree-sha1 = "6621fef488e496356c9c9625d0562c12a6070819"
 uuid = "5789e2e9-d7fb-5bc7-8068-2c6fae9b9549"
-version = "1.16.5"
+version = "1.20.0"
+weakdeps = ["HTTP"]
+
+    [deps.FileIO.extensions]
+    HTTPExt = "HTTP"
 
 [[deps.FilePathsBase]]
 deps = ["Compat", "Dates"]
@@ -250,6 +280,7 @@ deps = ["LinearAlgebra"]
 git-tree-sha1 = "2f979084d1e13948a3352cf64a25df6bd3b4dca3"
 uuid = "1a297f60-69ca-5386-bcde-b61e274b549b"
 version = "1.16.0"
+weakdeps = ["PDMats", "SparseArrays", "StaticArrays", "Statistics"]
 
     [deps.FillArrays.extensions]
     FillArraysPDMatsExt = "PDMats"
@@ -257,12 +288,6 @@ version = "1.16.0"
     FillArraysStaticArraysExt = "StaticArrays"
     FillArraysStatisticsExt = "Statistics"
 
-    [deps.FillArrays.weakdeps]
-    PDMats = "90014a1f-27ba-587c-ab20-58faa44d9150"
-    SparseArrays = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"
-    StaticArrays = "90137ffa-7385-5640-81b9-e52037218182"
-    Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
-
 [[deps.Future]]
 deps = ["Random"]
 uuid = "9fa8497b-333b-5362-9e8d-4d0656e87820"
@@ -274,18 +299,31 @@ uuid = "a0844989-3bd2-4988-8bea-c9407ab0941b"
 version = "1.1.0"
 
 [[deps.GeneralUtils]]
-deps = ["CSV", "DataFrames", "DataStructures", "Dates", "Distributions", "HTTP", "JSON", "NATS", "PrettyPrinting", "Random", "Revise", "SHA", "UUIDs"]
-git-tree-sha1 = "7c0600c166a5deb2c607018a491c04eb25969c2e"
+deps = ["CSV", "DataFrames", "DataStructures", "Dates", "Distributions", "Graphs", "HTTP", "JSON", "LibPQ", "NATS", "PrettyPrinting", "Random", "Revise", "SHA", "StringDistances", "UUIDs"]
+git-tree-sha1 = "93293126d24d3929ef6a5067f347bc28c6582c71"
 repo-rev = "main"
 repo-url = "https://git.yiem.cc/ton/GeneralUtils"
 uuid = "c6c72f09-b708-4ac8-ac7c-2084d70108fe"
-version = "0.4.9"
+version = "0.5.10"
+
+[[deps.Graphs]]
+deps = ["ArnoldiMethod", "DataStructures", "Inflate", "LinearAlgebra", "Random", "SimpleTraits", "SparseArrays", "Statistics"]
+git-tree-sha1 = "7eb45fe833a5b7c51cf6d89c5a841d5967e44be3"
+uuid = "86223c79-3864-5bf0-83f7-82e725a168b6"
+version = "1.14.0"
+
+    [deps.Graphs.extensions]
+    GraphsSharedArraysExt = "SharedArrays"
+
+    [deps.Graphs.weakdeps]
+    Distributed = "8ba89e20-285c-5b6f-9357-94700520ee1b"
+    SharedArrays = "1a1011a3-84de-559e-8e89-a11a2f7dc383"
 
 [[deps.HTTP]]
 deps = ["Base64", "CodecZlib", "Dates", "EnumX", "PrecompileTools", "Random", "Reseau", "SHA", "URIs", "UUIDs", "Zlib_jll"]
-git-tree-sha1 = "eda1d37cb55d90a17d0957c75841138c88b361a1"
+git-tree-sha1 = "c2c808326222b6dc4bec295a83b55f79aeec98e0"
 uuid = "cd3eb016-35fb-5094-929b-558a96fad6f3"
-version = "2.5.4"
+version = "2.5.5"
 
 [[deps.HashArrayMappedTries]]
 git-tree-sha1 = "2eaa69a7cab70a52b9687c8bf950a5a93ec895ae"
@@ -310,6 +348,11 @@ git-tree-sha1 = "cf8234411cbeb98676c173f930951ea29dca3b23"
 uuid = "a303e19e-6eb4-11e9-3b09-cd9505f79100"
 version = "0.2.4"
 
+[[deps.Inflate]]
+git-tree-sha1 = "d1b1b796e47d94588b3757fe84fbf65a5ec4a80d"
+uuid = "d25df0c9-e2be-5dd7-82c8-3ad0b3e990b9"
+version = "0.1.5"
+
 [[deps.InlineStrings]]
 git-tree-sha1 = "8f3d257792a522b4601c24a577954b0a8cd7334d"
 uuid = "842dd82b-1e85-43dc-bf29-5d0ee9dffc48"
@@ -463,6 +506,12 @@ version = "1.11.3+1"
 uuid = "8f399da3-3557-5675-b5ff-fb832c97cbdb"
 version = "1.11.0"
 
+[[deps.Libiconv_jll]]
+deps = ["Artifacts", "JLLWrappers", "Libdl"]
+git-tree-sha1 = "be484f5c92fad0bd8acfef35fe017900b0b73809"
+uuid = "94ce4f54-9a6c-5748-9c1c-f9c7231a4531"
+version = "1.18.0+0"
+
 [[deps.LinearAlgebra]]
 deps = ["Libdl", "OpenBLAS_jll", "libblastrampoline_jll"]
 uuid = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
@@ -645,15 +694,17 @@ version = "0.4.2"
 
 [[deps.PrettyTables]]
 deps = ["Crayons", "LaTeXStrings", "Markdown", "PrecompileTools", "Printf", "REPL", "Reexport", "StringManipulation", "Tables"]
-git-tree-sha1 = "624de6279ab7d94fc9f672f0068107eb6619732c"
+git-tree-sha1 = "ebf455bb866ee6737030e3d3816bb6a0683c4325"
 uuid = "08abe8d2-0d0c-5749-adfa-8a2ac140af0d"
-version = "3.3.2"
+version = "3.4.0"
 
     [deps.PrettyTables.extensions]
+    PrettyTablesExcelExt = "XLSX"
     PrettyTablesTypstryExt = "Typstry"
 
     [deps.PrettyTables.weakdeps]
     Typstry = "f0ed7684-a786-439e-b1e3-3b82803b501e"
+    XLSX = "fdbf4ff8-1666-58a4-91e7-1b58723a45e0"
 
 [[deps.Printf]]
 deps = ["Unicode"]
@@ -734,9 +785,9 @@ version = "0.5.1+0"
 
 [[deps.Roots]]
 deps = ["Accessors", "CommonSolve", "Printf"]
-git-tree-sha1 = "ed45bcc7cf3c8887595b973f2b1efbe91dcc50ec"
+git-tree-sha1 = "a7caaf7ba8cf307112ca443784d1b56b4a591455"
 uuid = "f2b01f46-fcfa-551c-844a-d8ac1e96c665"
-version = "3.0.1"
+version = "3.0.5"
 
     [deps.Roots.extensions]
     RootsChainRulesCoreExt = "ChainRulesCore"
@@ -760,11 +811,11 @@ version = "0.7.0"
 
 [[deps.SQLLLM]]
 deps = ["CSV", "DataFrames", "DataStructures", "Dates", "FileIO", "GeneralUtils", "HTTP", "JSON", "LLMMCTS", "LibPQ", "PrettyPrinting", "Random", "Revise", "StatsBase", "Tables", "URIs", "UUIDs"]
-git-tree-sha1 = "8f264038c55c5bea069cccbdc057c56e27899c42"
+git-tree-sha1 = "bae2fd2e2b087753fbb3415896be41df1ae0eb90"
 repo-rev = "main"
 repo-url = "https://git.yiem.cc/ton/SQLLLM"
 uuid = "2ebc79c7-cc10-4a3a-9665-d2e1d61e63d3"
-version = "0.2.6"
+version = "0.2.8"
 
 [[deps.SQLStrings]]
 git-tree-sha1 = "55de0530689832b1d3d43491ee6b67bd54d3323c"
@@ -789,10 +840,22 @@ git-tree-sha1 = "084c47c7c5ce5cfecefa0a98dff69eb3646b5a80"
 uuid = "91c51154-3ec4-41a3-a24f-3f23e20d615c"
 version = "1.4.10"
 
+[[deps.Serde]]
+deps = ["CSV", "Dates", "EzXML", "JSON", "TOML", "UUIDs", "YAML"]
+git-tree-sha1 = "f397fc8779cc53e4677c2708f3802c6996f28d00"
+uuid = "db9b398d-9517-45f8-9a95-92af99003e0e"
+version = "3.7.2"
+
 [[deps.Serialization]]
 uuid = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
 version = "1.11.0"
 
+[[deps.SimpleTraits]]
+deps = ["InteractiveUtils", "MacroTools"]
+git-tree-sha1 = "7ddb0b49c109481b046972c0e4ab02b2127d6a75"
+uuid = "699a6c99-e7fa-54fc-8d76-47d257e15c1d"
+version = "0.9.6"
+
 [[deps.Sockets]]
 uuid = "6462fe0b-24de-5631-8697-dd941f90decc"
 version = "1.11.0"
@@ -826,6 +889,25 @@ version = "2.8.0"
     [deps.SpecialFunctions.weakdeps]
     ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
 
+[[deps.StaticArrays]]
+deps = ["LinearAlgebra", "PrecompileTools", "Random", "StaticArraysCore"]
+git-tree-sha1 = "246a8bb2e6667f832eea063c3a56aef96429a3db"
+uuid = "90137ffa-7385-5640-81b9-e52037218182"
+version = "1.9.18"
+
+    [deps.StaticArrays.extensions]
+    StaticArraysChainRulesCoreExt = "ChainRulesCore"
+    StaticArraysStatisticsExt = "Statistics"
+
+    [deps.StaticArrays.weakdeps]
+    ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
+    Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
+
+[[deps.StaticArraysCore]]
+git-tree-sha1 = "6ab403037779dae8c514bad259f32a447262455a"
+uuid = "1e83bf80-4336-4d27-bf5d-d5a4f845583c"
+version = "1.4.4"
+
 [[deps.Statistics]]
 deps = ["LinearAlgebra"]
 git-tree-sha1 = "ae3bb1eb3bba077cd276bc5cfc337cc65c3075c0"
@@ -862,6 +944,18 @@ version = "2.2.0"
     ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
     InverseFunctions = "3587e190-3f89-42d0-90ee-14403ec27112"
 
+[[deps.StringDistances]]
+deps = ["Distances", "StatsAPI"]
+git-tree-sha1 = "cd83a04baf746e3b43b83c61b7de77ab0409b80a"
+uuid = "88034a9c-02f8-509d-84a9-84ec65e18404"
+version = "1.0.0"
+
+[[deps.StringEncodings]]
+deps = ["Libiconv_jll"]
+git-tree-sha1 = "b765e46ba27ecf6b44faf70df40c57aa3a547dcb"
+uuid = "69024149-9ee7-55f6-a4c4-859efe599b68"
+version = "0.3.7"
+
 [[deps.StringManipulation]]
 deps = ["PrecompileTools"]
 git-tree-sha1 = "d05693d339e37d6ab134c5ab53c29fce5ee5d7d5"
@@ -982,11 +1076,23 @@ git-tree-sha1 = "cd1659ba0d57b71a464a29e64dbc67cfe83d54e7"
 uuid = "76eceee3-57b5-4d4a-8e66-0e911cebbf60"
 version = "1.6.1"
 
+[[deps.XML2_jll]]
+deps = ["Artifacts", "JLLWrappers", "Libdl", "Libiconv_jll", "Zlib_jll"]
+git-tree-sha1 = "3f3315d89fc954a28f5b471bce698ed6e27481be"
+uuid = "02c8fc9c-b97f-50b9-bbe4-9be30ff0a78a"
+version = "2.15.3+0"
+
+[[deps.YAML]]
+deps = ["Base64", "Dates", "Printf", "StringEncodings"]
+git-tree-sha1 = "a1c0c7585346251353cddede21f180b96388c403"
+uuid = "ddb6d928-2868-570f-bddf-ab3f9cf99eb6"
+version = "0.4.16"
+
 [[deps.YiemAgent]]
-deps = ["CSV", "DataFrames", "DataStructures", "Dates", "GeneralUtils", "HTTP", "JSON", "LLMMCTS", "LibPQ", "NATS", "PrettyPrinting", "Random", "Revise", "Serialization", "URIs", "UUIDs"]
+deps = ["Base64", "CSV", "DataFrames", "DataStructures", "Dates", "HTTP", "JSON", "LLMMCTS", "LibPQ", "NATS", "PrettyPrinting", "Random", "Revise", "SQLLLM", "Serde", "Serialization", "URIs", "UUIDs"]
 path = "."
 uuid = "e012c34b-7f78-48e0-971c-7abb83b6f0a2"
-version = "0.4.1"
+version = "0.7.4"
 
 [[deps.Zlib_jll]]
 deps = ["Libdl"]

Project.toml

@@ -1,9 +1,10 @@
 name = "YiemAgent"
 uuid = "e012c34b-7f78-48e0-971c-7abb83b6f0a2"
-version = "0.4.2"
+version = "0.7.4"
 authors = ["narawat lamaiin <narawat@outlook.com>"]
 
 [deps]
+Base64 = "2a0f44e3-6c83-55bd-87e4-b1978d98bd5f"
 CSV = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 DataStructures = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
@@ -18,16 +19,19 @@ PrettyPrinting = "54e16d92-306c-5ea0-a30b-337be88ac337"
 Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 Revise = "295af30f-e4ad-537b-8983-00126c2a3abe"
 SQLLLM = "2ebc79c7-cc10-4a3a-9665-d2e1d61e63d3"
+Serde = "db9b398d-9517-45f8-9a95-92af99003e0e"
 Serialization = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
 URIs = "5c2747f8-b7ea-4ff2-ba2e-563bfd36b1d4"
 UUIDs = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
 
 [compat]
+Base64 = "1.11.0"
 CSV = "0.10.15"
 DataFrames = "1.7.0"
-GeneralUtils = "0.4.9"
+GeneralUtils = "0.5.10"
 HTTP = "2.4.0"
 JSON = "1.6.1"
 LLMMCTS = "0.1.5"
 NATS = "0.1.0"
-SQLLLM = "0.2.6"
+SQLLLM = "0.2.8"
+Serde = "3.7.2"

aisystemprompt.md

@@ -54,7 +54,7 @@ Your name is $(newAgent.name). You are a helpful sommelier for website-based $(n
 # Available Actions
 
 - **CHAT_BOX** which you can use to talk with the user.
-- **CHECK_WINE** allows you to check information about wines you want in your inventory's database. The input is text that specify supported search criteria includeing: retailer_name, wine price, winery, name, vintage, region, country, type, grape varietal, tasting notes, occasion, food pairing, intensity, tannin, sweetness, and acidity.
+- **SEARCH_WINE_DATABASE** allows you to check information about wines you want in your inventory's database. The input is text that specify supported search criteria includeing: retailer_name, wine price, winery, name, vintage, region, country, type, grape varietal, tasting notes, occasion, food pairing, intensity, tannin, sweetness, and acidity.
     - Example query 1: "Dry, full-bodied red wine from 1) region: Burgundy, country: France or 2) region: Tuscany, country: Italy. Grape varietal: Merlot or Syrah. price 100 to 1000 USD."
     - Example query 2: "Red or white wine, medium tannin, price under 700 USD"
     - Example query 3: "white wine, region: Tuscany or Bordeaux, country: Italy or France

appconfig.json

@@ -6,6 +6,7 @@
   "testingOrProduction": "testing",
   "agentId": "2b74b87a-5413-4fe2-a4d3-405891051680",
   "agentCentralConfigSubject": "/yiem/hq/agent/sommelier/backend/config/api/v1.1",
+  "this_service_name": "agent_backend",
   "this_service_input_channel": {
     "mqtt": [
         "/yiem/hq/agent/sommpanion/backend/db/api_v1"
@@ -16,7 +17,7 @@
   },
   "agentRole": "sommelier",
   "organization": "yiem_hq",
-  "externalService": {
+  "externalservice": {
     "servicesloadbalancer": {
       "nats": "sommpanion.backend.servicesloadbalancer.v1.inbox" 
     },
@@ -35,15 +36,15 @@
       "description": "A database connection info for LibPQ client",
       "url": "192.168.88.106:5432",
       "dbname": "winedb",
-      "user": "yiemtechnologies@gmail.com",
-      "password": "yiemtechnologies@Postgres_0.0"
+      "user": "admin",
+      "password": "admin@Sommpanion_0.0"
     },
     "sommpanion_vectordb" : {
       "description": "A wine database connection info for LibPQ client",
       "url": "192.168.88.106:5433",
       "dbname": "vectordb",
-      "user": "yiemtechnologies@gmail.com",
-      "password": "yiemtechnologies@Postgres_0.0"
+      "user": "admin",
+      "password": "admin@Sommpanion_0.0"
     },
     "fileserver": {
     "description": "temporary file server",

etc.jl

@@ -1,13 +1,10 @@
-
-
-
-d = Dict(
-  "hello"=> 555,
-  "world"=> Dict(
-    "name"=> "ton"
-  )
-)
-
-x = 55
-
-@info "YiemAgent think() 1 " d x @__LINE__
+# check if this column has vector embedding. if there is one, seach vector version instead
+              column_name_embedding = column_name * "_embedding"
+              if occursin(column_name_embedding, tables_schema[column_name_embedding])
+                vector_column = Dict(
+                  "table_name"=> table_name,
+                  "column_name"=> column_name_embedding,
+                  "operator"=> "vector_similarity",
+                  "value"=> column_obj["value"]
+                )
+              end

src/interface.jl

@@ -4,7 +4,7 @@ export addNewMessage, conversation, decisionMaker, reflector, generatechat,
   generalconversation, detectWineryName, generateSituationReport
 
 using JSON, DataStructures, Dates, UUIDs, HTTP, Random, PrettyPrinting, Serialization,
-      DataFrames, CSV
+      DataFrames, Serde
 using GeneralUtils
 using ..type, ..util, ..llmfunction
 
@@ -68,49 +68,18 @@ julia> result = decisionMaker(agent)
 
 OrderedDict{String, Any} with 4 entries:
   "plan"          => "The user provided an image of a sparkling white wine (Asolo Prosecco Bella Principessa from Italy) and requested a search for similar wines in the inventory. According to store guidelines, I must st…
-  "action_name"   => "CHECK_WINE"
+  "action_name"   => "SEARCH_WINE_DATABASE"
   "action_input"  => "Sparkling white wine from Italy"
   "action_result" => "1) winery: Terrazze dell Etna, wine_name: Rose Brut.
 ```
 """
-function decisionMaker(a::T; recentevents::Integer=20, maxattempt=10
+function decisionMaker(a::T; recentevents::Integer=20, maxattempt=3
   ) where {T<:agent}
+  @info "YiemAgent decisionMaker() start " @__LINE__
 
-  # lessonDict = copy(JSON.parsefile("lesson.json"))
-
-  # lesson =
-  # if isempty(lessonDict)
-  #   ""
-  # else
-  #   lessons = Dict{String, Any}()
-  #   for (k, v) in lessonDict
-  #     lessons[k] = lessonDict[k][:lesson]
-  #   end
-
-  #   """
-  #   You have attempted to help the user before and failed, either because your reasoning for the 
-  #   recommendation was incorrect or your response did not exactly match the user expectation. 
-  #   The following lesson(s) give a plan to avoid failing to help the user in the same way you 
-  #   did previously. Use them to improve your strategy to help the user.
-
-  #   Here are some lessons in JSON format:
-  #   $(JSON.json(lessons))
-
-  #   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. 
-  #   """
-  # end
-
-  # recentevents_ind = GeneralUtils.recentElementsIndex(
-  #   length(a.memory["events"]), recentevents; includelatest=true)
-
-  requiredKeys = ["plan", "action_name", "action_input"]
   context = 
     """
     <internal_context_for_assistant>
-      <assistant_action_history>
-        $(GeneralUtils.dict_to_string_html(a.memory["shortmem"]))
-      </assistant_action_history>
     </internal_context_for_assistant>
     """
 
@@ -125,68 +94,129 @@ function decisionMaker(a::T; recentevents::Integer=20, maxattempt=10
   errornote = "N/A"
   response = nothing # placeholder for show when error msg show up
 
-  for attempt in 1:maxattempt
-    if attempt > 1
-      println("\nYiemAgent decisionMaker() attempt $attempt/$maxattempt ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
-    end
+  """
+    {
+    "model": "your-model.gguf",
+    "messages": [ ... ],
+    "response_format": {
+      "type": "json_schema",
+      "json_schema": {
+        "name": "agent_action",
+        "strict": true,
+        "schema": {
+          "type": "object",
+          "properties": {
+            "think": {
+              "type": "string",
+              "description": "Your step-by-step reasoning process. Explain why you are choosing this action."
+            },
+            "action_name": {
+              "type": "string",
+              "enum": ["search_web", "get_weather", "calculate_math"],
+              "description": "The exact name of the action to execute."
+            },
+            "action_input": {
+              "type": "object",
+              "properties": {
+                "query": { "type": ["string", "null"], "description": "For search_web" },
+                "location": { "type": ["string", "null"], "description": "For get_weather" },
+                "equation": { "type": ["string", "null"], "description": "For calculate_math" }
+              },
+              "required": ["query", "location", "equation"],
+              "additionalProperties": false
+            }
+          },
+          "required": ["think", "action_name", "action_input"],
+          "additionalProperties": false
+          }
+        }
+      }
+    }
+  """
 
-    msg = Dict(
-      "model" => "gemma-4-E4B-it-UD-Q4_K_XL",
-      "messages" => a.chathistory,
-      "temperature" => 0.7
+  # strict output format
+  response_format = Dict(
+      "type"=> "json_schema",
+      "json_schema"=> Dict(
+        "name"=> "user_profile",
+        "strict"=> true,
+        "schema"=> Dict(
+          "type"=> "object",
+          "properties"=> Dict(
+            "think"=> Dict(
+              "type"=> "string",
+              "description"=> "Your step-by-step reasoning process. Explain why you are choosing this action."
+              ),
+            "action_name"=> Dict(
+              "type"=> "string",
+              "enum"=> ["CHAT_BOX", "SEARCH_WINE_DATABASE", "WINE_PRESENTATION_GUIDELINE", "END_CONVER_GUIDELINE"],
+              "description"=> "one of the available actions"
+              ),
+            "action_input"=> Dict(
+              "type"=> "object",
+              "properties"=> Dict(
+                "dialogue"=> Dict("type"=> "string", "description"=> "for CHAT_BOX"),
+                "query"=> Dict("type"=> "string", "description"=> "for SEARCH_WINE_DATABASE"),
+                "present_guide"=> Dict("type"=> "null", "description"=> "for WINE_PRESENTATION_GUIDELINE"),
+                "endconv_guide"=> Dict("type"=> "null", "description"=> "for END_CONVER_GUIDELINE"),
+                )
+              ),
+          ),
+          "required"=> ["think", "action_name", "action_input"],
+          "additionalProperties"=> false
+        )
+      )
     )
 
+  msg = Dict(
+      "model"=> "gemma-4-E4B-it-UD-Q4_K_XL",
+      "messages"=> a.chathistory,
+      "temperature"=> 0.7,
+      "response_format"=> response_format,
+    )
+
+  for attempt in 1:maxattempt
     response = a.context.text2textInstructLLM(a.id, msg)
-    response = GeneralUtils.clean_json_response(response)
     response = GeneralUtils.remove_french_accents(response)
-    think, response = GeneralUtils.extractthink(response)
-    response = String(split(response, ", observation")[1])  # in case LLM generate observation key which it isn't supposed to
-    response = strip(response)
 
-    responsedict = nothing
-    if occursin(requiredKeys[2], response) 
-      try
-        _responsedict = JSON.parse(response)
-        responsedict = GeneralUtils.dictify(_responsedict; keytype=String, sort_order=requiredKeys)
-      catch
-        println("\nERROR YiemAgent decisionMaker() failed to parse response: $response ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
-        continue
-      end
-
-    # fall back to normal text because LLM default to natural chat when it didn't use action_call
-    else  
-      try
-        responsedict = OrderedDict(
-          "plan"=> "I will talk to the user",
-          "action_name"=> "CHAT_BOX",
-          "action_input"=> response[2:end-1]  # remove { } at the front and back that added by clean_json_response
-          )
-      catch e
-        println("\nERROR YiemAgent decisionMaker(). $e --(not qualify response)-> $response", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
-        continue
-      end
+    # dollar sign in Julia means string interpolation
+    while occursin('$', response)
+      response = replace(response, '$' => "USD")
     end
 
-    # check whether all answer's key points are in responsedict
-    ispass, errormsg = GeneralUtils.checkAgentResponse_JSON(responsedict, requiredKeys)
-    if !ispass
-      errornote = errormsg
-      println("\nERROR YiemAgent decisionMaker() $errornote --(not qualify response)-> $responsedict", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
-      continue
-    end
-
-    # if responsedict["action_name"] ∉ ["CHAT_BOX", "CHECK_WINE", "PRESENT_WINE_GUIDELINE", "END_CONVER_GUIDELINE"]
-    #   errornote = "Your previous attempt didn't use the given functions"
-    #   println("\nERROR YiemAgent decisionMaker() $errornote --(not qualify response)--> $(responsedict["action_name"])", @__FILE__, ":", @__LINE__, " $(Dates.now())")
-    #   continue
-    # end
-
+    responsedict = JSON.parse(response)
     # println("\nYiem decisionMaker() ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
     # pprintln(responsedict)
 
+    # for decision that use a single action. make it simpler
+    for (k, v) in responsedict["action_input"]
+      responsedict["action_input"] = v
+    end
+
+    if occursin("CHAT_BOX", responsedict["action_input"])
+      println("\nERROR YiemAgent decisionMaker() --(not qualify response)> $responsedict ", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
+      continue
+    end
+
+    if responsedict["action_name"] ∉ ["WINE_PRESENTATION_GUIDELINE", "END_CONVER_GUIDELINE"] &&
+      length(responsedict["action_input"]) < 20
+      println("\nERROR YiemAgent decisionMaker() --(not qualify response)> $responsedict ", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
+      continue
+    end
+
+    println("\nYiem decisionMaker() ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+    pprintln(responsedict)
+    @info "YiemAgent decisionMaker() end " @__LINE__
     return responsedict
   end
-  error("DecisionMaker failed to generate a thought ", response)
+
+  # in case decisionMaker failed, force to use generatechat!()
+  responsedict = OrderedDict(
+    "think"=> "N/A",
+    "action_name"=> "CHAT_BOX",
+    "action_input"=> "N/A"
+  )
+  return responsedict
 end
 
 
@@ -315,7 +345,7 @@ function evaluator(a::T1, timeline, decisiondict, evaluateecontext
     ispass, errormsg = checkAgentResponse_JSON(responsedict, requiredKeys)
     if !ispass
       errornote = errormsg
-      println("\nERROR YiemAgent evaluator() $errornote --(not qualify response)> $responsedict", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
+      println("\nERROR YiemAgent evaluator() $errornote --(not qualify response)> $responsedict ", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
       continue
     end
 
@@ -358,7 +388,7 @@ message => Dict(
 function conversation(a::sommelier; userinput::Union{Dict{String, Any}, JSON.Object{String, Any}},
                       maximumMsg=50, max_think_loop::Integer=3)
   
-  @info "YiemAgent conversation() 1" @__LINE__
+  @info "YiemAgent conversation() start " @__LINE__
   userinput = GeneralUtils.dictify(userinput; keytype=String, sort_order=["text"])
 
   # find text in usermsg
@@ -374,7 +404,7 @@ function conversation(a::sommelier; userinput::Union{Dict{String, Any}, JSON.Obj
     clearhistory(a)
     return "Okay. What shall we talk about?"
   else
-    @info "YiemAgent conversation() 2" @__LINE__
+
     # add usermsg to a.chathistory but how do I handle images?
     addNewMessage(a, "user", userinput; maximumMsg=maximumMsg)
 
@@ -382,23 +412,130 @@ function conversation(a::sommelier; userinput::Union{Dict{String, Any}, JSON.Obj
     loopcount = 0
     while true
       loopcount += 1
-      @info "YiemAgent conversation() 2-0 count $loopcount" @__LINE__
-      thoughtdict, _ = think(a)
-      if thoughtdict["action_name"] ∈ ["CHAT_BOX"]
-        @info "YiemAgent conversation() 2-1" @__LINE__
+      if loopcount > max_think_loop
+
+        thoughtdict, result_raw = generatechat!(a)
         assistant_response = Dict{String, Any}(
           "role" => "assistant",
           "content" => [Dict("type" => "text", "text" => thoughtdict["action_input"]),]
         )
         addNewMessage(a, "assistant", assistant_response; maximumMsg=maximumMsg)
-        return thoughtdict["action_input"]
+
+        items_info = []
+        send_item_ind = []  # index of the item being send to frontend
+        if haskey(a.memory["shortmem"], "items_info")
+          for (i, item) in enumerate(a.memory["shortmem"]["items_info"])
+            @info "YiemAgent conversation() shortmem: $(length(a.memory["shortmem"]["items_info"])), items_info: $(length(items_info)), item name: $(item["wine_name"])  " @__LINE__
+            if haskey(item, "wine_name") && occursin(item["wine_name"], thoughtdict["action_input"])
+              push!(items_info, deepcopy(item))
+              push!(send_item_ind, i)
+              @info "YiemAgent conversation() shortmem: $(length(a.memory["shortmem"]["items_info"])), items_info: $(length(items_info)) " @__LINE__
+            end
+          end
+          # remove sent items
+          deleteat!(a.memory["shortmem"]["items_info"], send_item_ind)
+          @info "YiemAgent conversation() shortmem: $(length(a.memory["shortmem"]["items_info"])), items_info: $(length(items_info)) " @__LINE__
+        end
+        
+        response_to_frontend = Dict{String, Any}(
+          "role" => "assistant",
+          "content" => [
+              Dict("type" => "text", "text" => thoughtdict["action_input"]),
+              Dict(
+                "type" => "items_info",
+                "items_info" => items_info
+              ),
+            ]
+        )
+
+        return response_to_frontend
       end
 
-      if loopcount > max_think_loop
-        @info "YiemAgent conversation() 2-2" @__LINE__
-        r = generatechat(a)
-        @info "YiemAgent conversation() 2-3" @__LINE__
-        return r
+
+      thoughtdict, result_raw = think(a)
+
+      if thoughtdict["action_name"] ∈ ["CHAT_BOX"]
+        assistant_response = Dict{String, Any}(
+          "role" => "assistant",
+          "content" => [Dict("type" => "text", "text" => thoughtdict["action_input"]),]
+        )
+        addNewMessage(a, "assistant", assistant_response; maximumMsg=maximumMsg)
+
+        items_info = []
+        send_item_ind = []  # index of the item being send to frontend
+        if haskey(a.memory["shortmem"], "items_info")
+          for (i, item) in enumerate(a.memory["shortmem"]["items_info"])
+            @info "YiemAgent conversation() shortmem: $(length(a.memory["shortmem"]["items_info"])), items_info: $(length(items_info)), item name: $(item["wine_name"])  " @__LINE__
+            if haskey(item, "wine_name") && occursin(item["wine_name"], thoughtdict["action_input"])
+              push!(items_info, deepcopy(item))
+              push!(send_item_ind, i)
+              @info "YiemAgent conversation() shortmem: $(length(a.memory["shortmem"]["items_info"])), items_info: $(length(items_info)) " @__LINE__
+            end
+          end
+          # remove sent items
+          deleteat!(a.memory["shortmem"]["items_info"], send_item_ind)
+          @info "YiemAgent conversation() shortmem: $(length(a.memory["shortmem"]["items_info"])), items_info: $(length(items_info)) " @__LINE__
+        end
+        
+        response_to_frontend = Dict{String, Any}(
+          "role" => "assistant",
+          "content" => [
+              Dict("type" => "text", "text" => thoughtdict["action_input"]),
+              Dict(
+                "type" => "items_info",
+                "items_info" => items_info
+              ),
+            ]
+        )
+
+        """ intended message to send to frontend should have the following format. 
+        response_to_frontend = Dict{String, Any}(
+          "role" => "assistant",
+          "content" => [
+            Dict("type" => "text", "text" => "assistant_text_response"),
+            Dict(
+              "type" => "items_info",
+              "items_info" => [
+                          Dict(
+                            "wine_name"=> "wine name 1",
+                            "wine_id"=> "...",
+                            "image"=> base64 encoded image,
+                            ...
+                          ),
+                          Dict(
+                            "wine_name"=> "wine name 2",
+                            "wine_id"=> "...",
+                            "image"=> base64 encoded image,
+                            ...
+                          ),
+                        ]
+            ),
+          ]
+        )
+        """
+        
+
+        return response_to_frontend
+      else  # still in action
+
+        action_name = thoughtdict["action_name"]
+        action_input = thoughtdict["action_input"]
+
+        action_call = Dict{String, Any}(
+            "role" => "action_call",
+            "content" => [Dict("type" => "text", "text" => "{action_name: $action_name, action_input: $action_input}"),]
+          )
+
+        addNewMessage(a, "action_call", action_call; maximumMsg=maximumMsg)
+
+        action_result = thoughtdict["action_result"]
+        actionresult = Dict{String, Any}(
+            "role" => "action_result",
+            "content" => [Dict("type" => "text", "text" => "$action_result"),]
+          )
+
+        addNewMessage(a, "actionresult", actionresult; maximumMsg=maximumMsg)
+        @info "YiemAgent conversation() end think count $loopcount " @__LINE__
       end
     end
   end
@@ -418,44 +555,51 @@ julia>
 """
 function think(a::T)::NamedTuple{(:thoughtdict, :result_raw), Tuple{OrderedDict, Any}} where {T<:agent}
   # a.memory[:recap] = generateSituationReport(a, a.context["text"2textInstructLLM]; skiprecent=0)
+  @info "YiemAgent think() start " @__LINE__
   thoughtdict = decisionMaker(a)
-  @info "YiemAgent think() 1" @__LINE__
-  # pprintln(thoughtdict)
+  @info "YiemAgent think() 1 " @__LINE__
+  @show thoughtdict
+  println("---\n")
 
   result_raw = nothing
   if thoughtdict["action_name"] ∈ ["CHAT_BOX"]
-    @info "YiemAgent think() 2" @__LINE__
-    thoughtdict, result_raw = chatbox!(a, thoughtdict)
+
+    # sometime CHAT_BOX input is too short. 
+    # if thoughtdict["action_input] < 20 character, use generatechat!()
+    if length(thoughtdict["action_input"]) < 20 
+      thoughtdict, result_raw = generatechat!(a)   
+    else
+      thoughtdict["action_result"] = "Action result is the next user dialogue."
+      result_raw = thoughtdict["action_input"]
+    end 
 
   elseif thoughtdict["action_name"] == "END_CONVER_GUIDELINE"
-    @info "YiemAgent think() 3" @__LINE__
+
     thoughtdict, result_raw = end_conversation_guideline!(a, thoughtdict)
     
   elseif thoughtdict["action_name"] ∈ ["WINE_PRESENTATION_GUIDELINE"]
-    @info "YiemAgent think() 4" @__LINE__
+
     thoughtdict, result_raw =  wine_presentation_guideline!(a, thoughtdict)
 
+  elseif thoughtdict["action_name"] == "SEARCH_WINE_DATABASE" 
 
-  elseif thoughtdict["action_name"] == "CHECK_WINE" 
-    @info "YiemAgent think() 5" @__LINE__
-    thoughtdict, result_raw = checkwine!(a, thoughtdict)
+    thoughtdict, result_raw = search_wine_database!(a, thoughtdict; useSQLLLM=false)
+    if result_raw !== nothing && result_raw isa Vector
+      if haskey(a.memory["shortmem"], "items_info")
+        append!(a.memory["shortmem"]["items_info"], result_raw)
+      else
+        a.memory["shortmem"]["items_info"] = result_raw
+      end
+    end
     
   else
-    @info "YiemAgent think() 6" @__LINE__
+
     error("condition is not defined ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
   end
 
-  max_ind =
-    if length(a.memory["shortmem"]) == 0
-      0
-    else
-      k = keys(a.memory["shortmem"])
-      maximum(parse.(Int, k))
-    end
-  a.memory["shortmem"]["$(max_ind + 1)"] = thoughtdict
-
-  @info "YiemAgent think() 7" @__LINE__
-  pprintln(thoughtdict)
+  @info "YiemAgent think() end " @__LINE__
+  # @show thoughtdict
+  println("---\n")
   return (thoughtdict=thoughtdict, result_raw=result_raw)
 end
 
@@ -530,9 +674,9 @@ end
 
 
 #PENDING
-function generatechat(a::T; recentevents::Integer=20, maxattempt=10
-  )::String where {T<:agent}
-
+function generatechat!(a::T; maxattempt::Integer=10
+  )::NamedTuple{(:thoughtdict, :result_raw), Tuple{OrderedDict, Any}} where {T<:agent}
+  @info "YiemAgent generatechat!() start " @__LINE__
   # lessonDict = copy(JSON.parsefile("lesson.json"))
 
   # lesson =
@@ -604,16 +748,14 @@ function generatechat(a::T; recentevents::Integer=20, maxattempt=10
       - Processing sales orders or engaging in any other sales-related activities. These are the job of our sales team at the store.
       - Answering questions or offering additional services beyond those related to your store's wine recommendations such as discounts, quantity, rewards programs, promotions, delivery options, shipping, boxes, gift wrapping, packaging, personalized messages or something similar. These are the job of our sales team at the store.
 
-    # you should then respond to the user with interleaving plan, action_name, action_input
-      1) **plan**, Based on the current situation, state a complete action plan to complete the task and rationale. Be specific.
-      2) **action_name**, (Typically corresponds to the execution of the first step in your plan). Must be "CHAT_BOX
-      3) **action_input**, Dialogue you want to chat with the user according to your plan.
+    # you should then respond to the user with interleaving think, action_name, action_input  in JSON format
+      1) "think", Your step-by-step reasoning process. Explain why you are choosing this action.
+      2) "action_name", Can be one of the available_actions name.
+      3) "action_input", Dialogue you want to chat with the user according to your plan.
       After the action is executed you gets "action_result". It is the output from the action you selected.
      
-    # you should only respond in JSON format as described below
-      "plan": "...",
-      "action_name": "...",
-      "action_input": "..."
+    # available actions
+      "CHAT_BOX", which you can use to talk with the user. The input is dialogue you want to chat with the user according to your plan.
     """
 
   system_msg = Dict(
@@ -623,27 +765,11 @@ function generatechat(a::T; recentevents::Integer=20, maxattempt=10
       ]
     )
 
-  chathistory = deepcopy(a.chathistory[2:end])
+  chathistory = deepcopy(a.chathistory[2:end])  # use deep copy because I want to replace system msg
   pushfirst!(chathistory, system_msg)
 
   requiredKeys = ["plan", "action_name", "action_input"]
-  context = 
-    """
-    <internal_context_for_assistant>
-      <assistant_action_history>
-        $(GeneralUtils.dict_to_string_html(a.memory["shortmem"]))
-      </assistant_action_history>
-    </internal_context_for_assistant>
-    """
 
-  # add context to text of the latest message (in the front). 
-  # use for loop because in openai format, each msg may contain both text and image. 
-  for d in chathistory[end]["content"]
-    if d["type"] == "text"
-      d["text"] = context * d["text"]
-      break
-    end
-  end
   errornote = "N/A"
   response = nothing # placeholder for show when error msg show up
 
@@ -652,64 +778,67 @@ function generatechat(a::T; recentevents::Integer=20, maxattempt=10
       println("\nYiemAgent generatechat() attempt $attempt/$maxattempt ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
     end
 
+    response_format = Dict(
+      "type"=> "json_schema",
+      "json_schema"=> Dict(
+        "name"=> "user_profile",
+        "strict"=> true,
+        "schema"=> Dict(
+          "type"=> "object",
+          "properties"=> Dict(
+            "think"=> Dict(
+              "type"=> "string",
+              "description" => "Your step-by-step reasoning process. Explain why you are choosing this action.",
+              ),
+            "action_name"=> Dict(
+              "type"=> "string",
+              "enum"=> ["CHAT_BOX"],
+              "description" => "one of the available actions",
+              ),
+            "action_input"=> Dict(
+              "type"=> "string",
+              "description" => "Dialogue you want to chat with the user according to your plan.",
+              ),
+          ),
+          "required"=> ["think", "action_name", "action_input"],
+          "additionalProperties"=> false
+        )
+      )
+    )
+    
     msg = Dict(
       "model" => "gemma-4-E4B-it-UD-Q4_K_XL",
-      "messages" => a.chathistory,
-      "temperature" => 0.7
+      "messages" => chathistory,
+      "temperature" => 0.7,
+      "response_format"=> response_format,
     )
 
     response = a.context.text2textInstructLLM(a.id, msg)
-    response = GeneralUtils.clean_json_response(response)
     response = GeneralUtils.remove_french_accents(response)
-    think, response = GeneralUtils.extractthink(response)
-    response = String(split(response, ", observation")[1])  # in case LLM generate observation key which it isn't supposed to
 
-    response = strip(response)
-    @show response
-
-    responsedict = nothing
-    if occursin(requiredKeys[2], response) 
-      try
-        _responsedict = JSON.parse(response)
-        responsedict = GeneralUtils.dictify(_responsedict; keytype=String, sort_order=requiredKeys)
-      catch
-        println("\nERROR YiemAgent generatechat() failed to parse response: $response ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
-        continue
-      end
-
-    # fall back to normal text because LLM default to natural chat when it didn't use action_call
-    else  
-      try
-        responsedict = OrderedDict(
-          "plan"=> "I will talk to the user",
-          "action_name"=> "CHAT_BOX",
-          "action_input"=> response[2:end-1]  # remove { } at the front and back that added by clean_json_response
-          )
-      catch e
-        println("\nERROR YiemAgent decisionMaker(). $e --(not qualify response)-> $response", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
-        continue
-      end
+    # dollar sign in Julia means string interpolation
+    while occursin('$', response)
+      response = replace(response, '$' => "USD")
     end
 
-    # check whether all answer's key points are in responsedict
-    ispass, errormsg = GeneralUtils.checkAgentResponse_JSON(responsedict, requiredKeys)
-    if !ispass
-      errornote = errormsg
-      println("\nERROR YiemAgent generatechat() $errornote --(not qualify response)> $responsedict", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
+    responsedict = JSON.parse(response)
+
+    if occursin("CHAT_BOX", responsedict["action_input"]) ||
+      length(responsedict["action_input"]) < 20
+      println("\nERROR YiemAgent generatechat() --(not qualify response)> $responsedict ", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
       continue
     end
 
-    # if responsedict["action_name"] ∉ ["CHAT_BOX", "CHECK_WINE", "PRESENT_WINE_GUIDELINE", "END_CONVER_GUIDELINE"]
-    #   errornote = "Your previous attempt didn't use the given functions"
-    #   println("\nERROR YiemAgent decisionMaker() $errornote --(not qualify response)--> $(responsedict["action_name"])", @__FILE__, ":", @__LINE__, " $(Dates.now())")
-    #   continue
-    # end
+    println("\nYiem generatechat!() ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+    pprintln(responsedict)
+    responsedict["action_result"] = "Action result is the next user dialogue."
+    @info "YiemAgent generatechat!() end " @__LINE__
 
-    # println("\nYiem decisionMaker() ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
-    # pprintln(responsedict)
-
-    return responsedict["action_input"]
+    responsedict["action_result"] = "Action result is the next user dialogue."
+    @info "YiemAgent generatechat!() end " @__LINE__
+    return (thoughtdict=responsedict, result_raw=responsedict["action_input"])
   end
+  @info "YiemAgent generatechat() failed to generate a thought " @__LINE__
   error("YiemAgent generatechat() failed to generate a thought ", response)
 end
 

src/type.jl

@@ -16,83 +16,18 @@ mutable struct agentcontext
   insertSQLVectorDB::Function
   similarSommelierDecision::Function
   insertSommelierDecision::Function
+  find_related_tables_for_user_question::Function
+  pg_conn_str::String
+  agentconfig::AbstractDict
 end
 
 abstract type agent end
 
-mutable struct companion <: agent
-  name::String  # agent name
-  id::String    # agent id
-  systemmsg::String # system message
-  tools::Dict  # tools
-  maxHistoryMsg::Integer  # e.g. 21th and earlier messages will get summarized
-  chathistory::Vector{Dict{String, Any}}
-  memory::Dict{String, Any}
-  context::NamedTuple  # NamedTuple of functions 
-  llmFormatName::String
-end
-
-function companion(
-  context::agentcontext  # NamedTuple of functions
-  ;
-  name::String= "Assistant",
-  id::String= GeneralUtils.uuid4snakecase(), 
-  maxHistoryMsg::Integer= 20,
-  chathistory::Vector{Dict{String, String}} = Vector{Dict{String, String}}(),
-  llmFormatName::String= "granite3",
-  systemmsg::String=
-    """
-      Your name: $name
-      Your sex: Female
-      Your role: You are a helpful assistant.
-      You should follow the following guidelines:
-      - Focus on the latest conversation.
-      - Your like to be short and concise.
-
-      Let's begin!
-      """,
-  )
-
-  tools = Dict( # update input format
-      "CHAT_BOX"=> Dict(
-        "description" => "- CHAT_BOX which you can use to talk with the user. The input is your intentions for the dialogue. Be specific.",
-      ),
-    )
-
-  """ 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()),
-    ]
-  """
-  memory = Dict{String, Any}(
-            "events"=> Vector{Dict{String, Any}}(),
-            "state"=> Dict{String, Any}(), # state of the agent
-            "recap"=> OrderedDict{String, Any}(),  # recap summary of the conversation
-          )
-
-  newAgent = companion(
-    name,
-    id,
-    systemmsg,
-    tools,
-    maxHistoryMsg,
-    chathistory,
-    memory,
-    context,
-    llmFormatName
-    )
-  
-  return newAgent
-end
-
-
 mutable struct sommelier <: agent
   name::String  # agent name
   id::String    # agent id
   retailername::String
+  retailerid::String
   tools::Dict   
   maxHistoryMsg::Integer  # e.g. 21th and earlier messages will get summarized
   chathistory::Vector{Dict{String, Any}}
@@ -140,11 +75,12 @@ julia> agent = sommelier(context, name="WineExpert", id="123", retailername="MyW
 ```
 """
 function sommelier(
-  context::agentcontext,  # app context
+  context::agentcontext,  # agent functions, db connect and other context
   ;
   name::String= "Assistant",
   id::String= string(uuid4()),
-  retailername::String= "retailer_name",
+  retailername::String= "not specified",
+  retailerid::String= "not specified",
   maxHistoryMsg::Integer= 20,
   chathistory::Vector{Dict{String, Any}} = Vector{Dict{String, Any}}(),
   llmFormatName::String= "granite3"
@@ -205,17 +141,14 @@ function sommelier(
   memory = Dict{String, Any}(
             "shortmem"=> OrderedDict{String, Any}(),
             "scratchpad"=> "",
-            "events"=> Vector{Dict{String, Any}}(),
-            "state"=> Dict{String, Any}(
-            ),
             "recap"=> OrderedDict{String, Any}(),
-            
           )
 
   newAgent = sommelier(
     name,
     id,
     retailername,
+    retailerid,
     tools,
     maxHistoryMsg,
     chathistory,
@@ -231,7 +164,6 @@ function sommelier(
       - You can only recommend wines that are currently in our inventory
       - Before searching the database for wine, ensure you have at least the following information: 1) budget, 2) wine type, and 3) occasion. Additional details are always helpful. If the user is unsure, provide relevant information and gather insights to make reasonable inferences.
       - Ask the user one question at a time.
-      - 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, if you haven't already, ask the user whether they need any further assistance. Do not offer any additional services.
       - Only end the conversation when the user explicitly intends to do so. When ending, ensure a polite farewell and an invitation to return in the future.
       - Spicy foods should be paired only with light red wines.
@@ -246,6 +178,7 @@ function sommelier(
       - Your store carries only wine.
       - Vintage 0 means non-vintage.
       - Start searching the database as broadly as possible within the given information boundary to maximize the chances of finding. Avoid unnecessary parameters unless specified by the user. Refine the search subsequently.
+      - User usually ask for something similar. This means you should use the search term based on the profile they like.
 
     # situation
       You are having conversation with a customer.
@@ -266,26 +199,20 @@ function sommelier(
       - Processing sales orders or engaging in any other sales-related activities. These are the job of our sales team at the store.
       - Answering questions or offering additional services beyond those related to your store's wine recommendations such as discounts, quantity, rewards programs, promotions, delivery options, shipping, boxes, gift wrapping, packaging, personalized messages or something similar. These are the job of our sales team at the store.
 
-    # you should then respond to the user with interleaving plan, action_name, action_input
-      1) **plan**, Based on the current situation, state a complete action plan to complete the task and rationale. Be specific.
-      2) **action_name**, (Typically corresponds to the execution of the first step in your plan) Can be one of the available_actions name
-      3) **action_input**, The input to the action you are about to perform according to your plan.
+    # you should then respond to the user with interleaving think, action_name, action_input in JSON format
+      1) "think", Your step-by-step reasoning process. Explain why you are choosing this action.
+      2) "action_name", Can be one of the available actions. Typically corresponds to the execution of the first step in your thought
+      3) "action_input", The input to the action you are about to perform.
       After the action is executed you gets "action_result". It is the output from the action you selected.
 
-    # you should only respond in JSON format as described below
-      "plan": "...",
-      "action_name": "...",
-      "action_input": "..."
-
     # available actions
-      **CHAT_BOX**, which you can use to talk with the user. The input is dialogue you want to chat with the user according to your plan.
-      **CHECK_WINE**, allows you to check information about wines you want in your inventory's database. The input is text that specify supported search criteria includeing: retailer_name, wine price, winery, name, vintage, region, country, type, grape varietal, tasting notes, occasion, food pairing, intensity, tannin, sweetness, and acidity.
-        Example query 1: "Dry, full-bodied red wine from 1) region: Burgundy, country: France or 2) region: Tuscany, country: Italy. Grape varietal: Merlot or Syrah. price 100 to 1000 USD."
+      "CHAT_BOX", which you can use to talk with the user. The input is dialogue you want to say with the user.
+      "SEARCH_WINE_DATABASE", allows you to search information about wines you want in your inventory's database. The input is strictly supported search term including: retailer_name, wine price, winery, name, vintage, region, country, type of wine, grape varietal, tasting notes, occasion, food pairing, intensity, tannin, sweetness, and acidity.
+        Example query 1: "Dry, full-bodied red wine from Burgundy, France. Grape varietal could be Merlot or Syrah. price 100 to 1000 USD."
         Example query 2: "Red or white wine, medium tannin, price under 700 USD"
-        Example query 3: "white wine, region: Tuscany or Bordeaux, country: Italy or France
-      **WINE_PRESENTATION_GUIDELINE**, which you can use to check the store guidelines about how to present wines you have found to the user. The input is "nothing" keyword. The output is the guidelines that you can follow.
-      **END_CONVER_GUIDELINE**, which you can use to check the store guidelines about how to end the conversation with the user. The input is "nothing" keyword. The output is the guidelines that you can follow.
-
+        Example query 3: "white wine from Tuscany, Italy or Bordeaux, France
+      "WINE_PRESENTATION_GUIDELINE", store guidelines about how to present wines to the user appropriately. The input is "null" keyword.
+      "END_CONVER_GUIDELINE", store guidelines about how to end the conversation with the user appropriately. The input is "null" keyword.
     """
     
   system_msg = Dict(

src/util.jl

@@ -95,15 +95,15 @@ end
 """
 function addNewMessage(a::T1, name::String, userinput::T2; 
                       maximumMsg::Integer=30) where {T1<:agent, T2<:AbstractDict}
-  if name ∉ ["system", "user", "assistant"]   # guard against typo
-    error("name is not in agent.availableRole $(@__LINE__)")
-  end
+  # if name ∉ ["system", "user", "assistant"]   # guard against typo
+  #   error("name is not in agent.availableRole $(@__LINE__)")
+  # end
 
   #TODO summarize the oldest 10 message
   if length(a.chathistory) > maximumMsg
     summarize(a.chathistory)
   else
-    userinput["timestamp"] = Dates.now()
+    # userinput["timestamp"] = Dates.now()
     push!(a.chathistory, userinput)
   end
 end
@@ -297,7 +297,7 @@ function createTimeline(events::T1; eventindex::Union{UnitRange, Nothing}=nothin
     #   timeline *= "Event_$i $(event["subject"])> action_name: $(event["action_name"]), action_input: $(event["action_input"])\n"
     # elseif event["action_name"] == "CHECKINVENTORY" && event["observation"] === nothing
     #   timeline *= "Event_$i $(event["subject"])> action_name: $(event["action_name"]), action_input: $(event["action_input"]), observation: Not done yet.\n"
-    if event["action_name"] == "CHECK_WINE"
+    if event["action_name"] == "SEARCH_WINE_DATABASE"
       timeline *= "Event_$i $(event["subject"])> action_name: $(event["action_name"]), action_input: $(event["action_input"]), observation: $(event["observation"])\\n"
     else
       timeline *= "Event_$i $(event["subject"])> action_name: $(event["action_name"]), action_input: $(event["action_input"])\\n"

test/runtests.jl

@@ -128,7 +128,7 @@ systemmsg =
 
   # Available Actions
   - **CHAT_BOX** which you can use to talk with the user.
-  - **CHECK_WINE** allows you to check information about wines you want in your inventory's database. The input is text that specify supported search criteria includeing: retailer_name, wine price, winery, name, vintage, region, country, type, grape varietal, tasting notes, occasion, food pairing, intensity, tannin, sweetness, and acidity.
+  - **SEARCH_WINE_DATABASE** allows you to check information about wines you want in your inventory's database. The input is text that specify supported search criteria includeing: retailer_name, wine price, winery, name, vintage, region, country, type, grape varietal, tasting notes, occasion, food pairing, intensity, tannin, sweetness, and acidity.
       - Example query 1: "Dry, full-bodied red wine from 1) region: Burgundy, country: France or 2) region: Tuscany, country: Italy. Grape varietal: Merlot or Syrah. price 100 to 1000 USD."
       - Example query 2: "Red or white wine, medium tannin, price under 700 USD"
       - Example query 3: "white wine, region: Tuscany or Bordeaux, country: Italy or France
@@ -157,7 +157,7 @@ openai_msg = Dict(
       "content" => [
         Dict("type" => "text", "text" => 
         """
-        " <plan>I will greet the customer warmly as Janie, acknowledge their request to find a similar wine for their wedding party based on the image, identify the wine type and country (Italian Sparkling Wine), and then use the CHECK_WINE action to search the inventory for suitable options.</plan>\n <action_name>CHAT_BOX</action_name>\n <action_input>Hello! I'm Janie, and I'd be delighted to help you find the perfect wine for your wedding party. That beautiful wine in the image appears to be an Italian sparkling wine, which is wonderful for a celebration like a wedding! Since you have an unlimited budget, I can certainly look for some truly exceptional options. To start, I will check our inventory for similar Italian sparkling wines that are perfect for a wedding celebration.</action_input><action_result> User response in the next message </action_result>"
+        " <plan>I will greet the customer warmly as Janie, acknowledge their request to find a similar wine for their wedding party based on the image, identify the wine type and country (Italian Sparkling Wine), and then use the SEARCH_WINE_DATABASE action to search the inventory for suitable options.</plan>\n <action_name>CHAT_BOX</action_name>\n <action_input>Hello! I'm Janie, and I'd be delighted to help you find the perfect wine for your wedding party. That beautiful wine in the image appears to be an Italian sparkling wine, which is wonderful for a celebration like a wedding! Since you have an unlimited budget, I can certainly look for some truly exceptional options. To start, I will check our inventory for similar Italian sparkling wines that are perfect for a wedding celebration.</action_input><action_result> User response in the next message </action_result>"
         """
         ),
       ]

test/test1.jl

@@ -2,200 +2,236 @@ using JSON, Dates, UUIDs, PrettyPrinting, LibPQ, Base64, DataFrames, DataStructu
       NATS, Base.Threads
 using YiemAgent, GeneralUtils, msghandler
 
+  function text2text_instruct_llm(sender_id::String, openai_msg::Dict{String, Any})
+    payloads = [("msg", openai_msg, "dictionary")]  # List of tuples
+    _, msg_envelope_json_str = msghandler.smartpack(
+          config["externalservice"]["servicesloadbalancer"]["nats"], 
+          payloads;
+          sender_id=sender_id,
+          msg_purpose="text2text",  
+          broker_url=config["nats_server_info"]["url"],
+          fileserver_url=config["externalservice"]["fileserver"]["url"])
 
-function text2text_instruct_llm(sender_id::String, openai_msg::Dict{String, Any})
-  payloads = [("msg", openai_msg, "dictionary")]  # List of tuples
-  _, msg_envelope_json_str = msghandler.smartpack(
-        config["externalService"]["servicesloadbalancer"]["nats"], 
-        payloads;
-        sender_id=sender_id,
-        msg_purpose="text2text",  
-        broker_url=config["nats_server_info"]["url"],
-        fileserver_url=config["externalService"]["fileserver"]["url"])
+    reply = NATS.request(agent_conn, 
+                        config["externalservice"]["servicesloadbalancer"]["nats"], 
+                        msg_envelope_json_str, timeout=120)
 
-  reply = NATS.request(agent_conn, 
-                      config["externalService"]["servicesloadbalancer"]["nats"], 
-                      msg_envelope_json_str, timeout=120)
-
-  incoming_env_json_str = String(reply.payload)
-  incoming_env = msghandler.smartunpack(incoming_env_json_str)
-  _llm_response = incoming_env["payloads"][1][2]
-  llm_response = _llm_response["choices"][1]["message"]["content"]
-  return llm_response
-end
-
-#TESTING get text embedding from a LLM service
-function get_embedding(text::AbstractArray{String})
-  documents_dict = Dict("documents" => text)
-  payloads = [("documents", documents_dict, "dictionary")]
-  _, msg_envelope_json_str = msghandler.smartpack(
-    config["externalService"]["servicesloadbalancer"]["nats"], 
-    payloads;   
-    msg_purpose="embedding",  
-    broker_url=config["nats_server_info"]["url"],
-    fileserver_url=config["externalService"]["fileserver"]["url"])
-
-  reply = NATS.request(agent_conn, 
-                      config["externalService"]["servicesloadbalancer"]["nats"], 
-                      msg_envelope_json_str, timeout=120)
-  incoming_env_json_str = String(reply.payload)
-  incoming_env = msghandler.smartunpack(incoming_env_json_str)
-  embedding_response = incoming_env["payloads"][1][2]
-
-  return embedding_response
-end
-
-#TESTING
-function execute_sql_winedb(config::JSON.Object, sql::T) where {T<:AbstractString}
-  host_url, _port = split(config["externalservice"]["sommpanion_db"]["url"], ':')
-  port = parse(Int, _port)
-  dbname = "winedb"
-  user = config["externalservice"]["sommpanion_db"]["user"]
-  password = config["externalservice"]["sommpanion_db"]["password"]
-  db_connection = LibPQ.Connection("host=$host_url port=$port dbname=$dbname user=$user password=$password")
-  result = LibPQ.execute(db_connection, sql)
-  LibPQ.close(db_connection)
-  return result
-end
-
-#TESTING
-function similar_sql_vectordb(query; maxdistance::Integer=100)
-  tablename = "sqlllm_decision_repository"
-  # get embedding of the query
-  df = find_similar_text_from_vectordb(query, tablename, 
-                                  "function_input_embedding", execute_sql_vectordb)
-  # println(df[1, [:id, :function_output]])
-  row, col = size(df)
-  distance = row == 0 ? Inf : df[1, :distance]  
-  # distance = 100  # CHANGE this is for testing only
-  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__, " $(Dates.now())")
-    return (dict=output_str, distance=distance)
-  else
-    println("\n~~~ similar sql not found, max distance $maxdistance ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
-    return (dict=nothing, distance=nothing)
+    incoming_env_json_str = String(reply.payload)
+    incoming_env = msghandler.smartunpack(incoming_env_json_str)
+    _llm_response = incoming_env["payloads"][1][2]
+    llm_response = _llm_response["choices"][1]["message"]["content"]
+    return llm_response
   end
-end
 
-#TESTING
-function insert_sql_vectordb(query::T1, SQL::T2; maxdistance::Integer=3) where {T1<:AbstractString, T2<:AbstractString}
-  tablename = "sqlllm_decision_repository"
-  # get embedding of the query
-  # query = state[:thoughtHistory][:question]
-  df = find_similar_text_from_vectordb(query, tablename, 
-                                  "function_input_embedding", execute_sql_vectordb)
-  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 = get_embedding([query])[1]
-    query_embedding = _query_embedding["data"][1]["embedding"]
-    query = replace(query, "'" => "")
-    sql_base64 = base64encode(SQL)
-    sql_ = replace(SQL, "'" => "")
+  """ get a single text embedding from a LLM service
+  Example
+  text = ["hello"]
+  embedding = get_embedding(text)
+  """
+  function get_embedding(text::AbstractArray{String})
+    documents_dict = Dict("documents" => text)
+    payloads = [("documents", documents_dict, "dictionary")]
+    _, msg_envelope_json_str = msghandler.smartpack(
+      config["externalservice"]["servicesloadbalancer"]["nats"], 
+      payloads;   
+      msg_purpose="embedding",  
+      broker_url=config["nats_server_info"]["url"],
+      fileserver_url=config["externalservice"]["fileserver"]["url"])
 
-    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__, " $(Dates.now())")
-    # println(sql)
-    _ = execute_sql_vectordb(sql)
+    reply = NATS.request(agent_conn, 
+                        config["externalservice"]["servicesloadbalancer"]["nats"], 
+                        msg_envelope_json_str, timeout=120)
+    incoming_env_json_str = String(reply.payload)
+    incoming_env = msghandler.smartunpack(incoming_env_json_str)
+    embedding_response = incoming_env["payloads"][1][2]
+
+    return embedding_response
   end
-end
 
-#TESTING
-function execute_sql_vectordb(sql::T) where {T<:AbstractString}
-  host_url, _port = split(config["SQLVectorDB"]["url"], ':')
-  port = parse(Int, _port)
-  dbname = config[:externalservice][:SQLVectorDB][:dbname]
-  user = config[:externalservice][:SQLVectorDB][:user]
-  password = config[:externalservice][:SQLVectorDB][:password]
-  DBconnection = LibPQ.Connection("host=$host_url port=$port dbname=$dbname user=$user password=$password")
-  result = LibPQ.execute(DBconnection, sql)
-  close(DBconnection)
-  return result
-end
+  """ sql = "SELECT * FROM wine;"
+  result = execute_sql_winedb(sql)
+  """
+  function execute_sql_winedb(sql::T) where {T<:AbstractString}
+    host_url, _port = split(config["externalservice"]["sommpanion_db"]["url"], ':')
+    port = parse(Int, _port)
+    dbname = "winedb"
+    user = config["externalservice"]["sommpanion_db"]["user"]
+    password = config["externalservice"]["sommpanion_db"]["password"]
+    db_connection = LibPQ.Connection("host=$host_url port=$port dbname=$dbname user=$user password=$password")
+    result = nothing
+    try
+      result = LibPQ.execute(db_connection, sql)  
+    catch e
+      LibPQ.close(db_connection)
+    end
     
-
-function similar_sommelier_decision(recentevents::T1; maxdistance::Integer=3
-  )::Union{AbstractDict, Nothing} where {T1<:AbstractString}
-  tablename = "sommelier_decision_repository"
-  # find similar
-  println("\n~~~ search vectorDB for this: $recentevents ", @__FILE__, " ", @__LINE__)
-  df = find_similar_text_from_vectordb(recentevents, tablename, 
-                                  "function_input_embedding", execute_sql_vectordb)
-  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(JSON.read(_output_str))
-    return output
-  else
-    println("\n~~~ similar decision not found, max distance $maxdistance ", @__FILE__, " ", @__LINE__)
-    return nothing
+    LibPQ.close(db_connection)
+    return result
   end
-end
 
-#TESTING
-function find_similar_text_from_vectordb(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 = get_embedding([text])[1]
-  embedding = _embedding["data"][1]["embedding"]
-  # check whether there is close enough vector already store in vectorDB. if no, add, else skip 
-  sql = """
-        SELECT *, $embeddingColumnName <-> '$embedding' as distance
-        FROM $tablename
-        ORDER BY distance LIMIT $limit;
+  """ find similar sql from vector database
+  sql = "SELECT * FROM wine;"
+  result, distance = similar_sql_vectordb(sql)
+  """
+  function similar_sql_vectordb(sql::T; maxdistance::Number=0.2) where {T<:AbstractString}
+    tablename = "sqlllm_decision_repository"
+    # get embedding of the query
+    df = find_similar_text_from_vectordb(sql, tablename, 
+          "function_input_embedding", execute_sql_vectordb)
+    # println(df[1, [:id, :function_output]])
+    row, col = size(df)
+    distance = row == 0 ? Inf : df[1, :distance]  
+    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--| similar sql found. row id $rowid, distance $distance ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+      pprintln(output_str)
+      return (result=output_str, distance=distance)
+    else
+      println("\n--| similar sql not found, max distance $maxdistance ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+      return (result=nothing, distance=nothing)
+    end
+  end
+
+  """ insert query and sql into vector database
+  query = "get all wines from wine table"
+  sql = "SELECT * FROM wine;"
+  insert_sql_vectordb(query, sql)
+  """
+  function insert_sql_vectordb(query::T1, SQL::T2; maxdistance::Number=3
+    ) where {T1<:AbstractString, T2<:AbstractString}
+    
+    tablename = "sqlllm_decision_repository"
+    # get embedding of the query
+    # query = state[:thoughtHistory][:question]
+    df = find_similar_text_from_vectordb(query, tablename, 
+                                    "function_input_embedding", execute_sql_vectordb)
+    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 = get_embedding([query])
+      _query_embedding = GeneralUtils.dictify(_query_embedding)
+      # println("\n--- _query_embedding() ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+      # println(_query_embedding)
+      # println("---\n")
+      query_embedding = _query_embedding["data"][1]["embedding"]
+      query = replace(query, "'" => "")
+      sql_base64 = base64encode(SQL)
+      sql_ = replace(SQL, "'" => "")
+
+      sql = 
         """
-  response = vectorDB(sql)
-  df = DataFrame(response)
-  return df
-end
-
-
-function insert_sommelier_decision(recentevents::T1, decision::T2; maxdistance::Integer=5
-  ) where {T1<:AbstractString, T2<:AbstractDict}
-  tablename = "sommelier_decision_repository"
-  # find similar
-  df = find_similar_text_from_vectordb(recentevents, tablename, 
-                                  "function_input_embedding", execute_sql_vectordb)
-  row, col = size(df)
-  distance = row == 0 ? Inf : df[1, :distance]
-  if row == 0 || distance > maxdistance # no close enough SQL stored in the database
-    _embedding = get_embedding([recentevents])[1]
-    recentevents_embedding = _embedding["data"][1]["embedding"]
-    recentevents = replace(recentevents, "'" => "")
-    decision_json = JSON.json(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)
-    _ = execute_sql_vectordb(sql)
-  else
-    println("~~~ similar decision previously cached, distance $distance ", @__FILE__, " ", @__LINE__)
+        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__, " $(Dates.now())")
+      # println(sql)
+      _ = execute_sql_vectordb(sql)
+    end
   end
-end
 
+  """ execute sql against vectordb
+  sql = "SELECT * FROM wine;"
+  result = execute_sql_vectordb(sql)
+  """
+  function execute_sql_vectordb(sql::T) where {T<:AbstractString}
+    host_url, _port = split(config["externalservice"]["sommpanion_vectordb"]["url"], ':')
+    port = parse(Int, _port)
+    dbname = config["externalservice"]["sommpanion_vectordb"]["dbname"]
+    user = config["externalservice"]["sommpanion_vectordb"]["user"]
+    password = config["externalservice"]["sommpanion_vectordb"]["password"]
+    DBconnection = LibPQ.Connection("host=$host_url port=$port dbname=$dbname user=$user password=$password")
+    result = LibPQ.execute(DBconnection, sql)
+    close(DBconnection)
+    return result
+  end
+
+  """ search similar decision llm made from vectordb
+  """
+  function similar_sommelier_decision(recentevents::T1; maxdistance::Integer=3
+    )::Union{AbstractDict, Nothing} where {T1<:AbstractString}
+
+    tablename = "sommelier_decision_repository"
+    # find similar
+    df = find_similar_text_from_vectordb(recentevents, tablename, 
+                                    "function_input_embedding", execute_sql_vectordb)
+    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(JSON.read(_output_str))
+      return output
+    else
+      println("\n--| similar decision not found, max distance $maxdistance ", @__FILE__, " ", @__LINE__)
+      return nothing
+    end
+  end
+
+  """ search similar text from vectordb
+  """
+  function find_similar_text_from_vectordb(text::T1, tablename::T2, embeddingColumnName::T3,
+    vectorDB::Function; limit::Integer=1
+    )::DataFrame where {T1<:AbstractString, T2<:AbstractString, T3<:AbstractString}
+    # get embedding from LLM service
+    _embedding = get_embedding([text])
+    _embedding = _embedding["data"][1]["embedding"]
+    _embedding = "$_embedding"
+
+    embedding = _embedding[4:end]
+
+    # check whether there is close enough vector already store in vectorDB. if no, add, else skip 
+    sql = """
+          SELECT *, $embeddingColumnName <-> '$embedding' as distance
+          FROM $tablename
+          ORDER BY distance LIMIT $limit;
+          """
+    response = vectorDB(sql)
+    df = DataFrame(response)
+
+    return df
+  end
+
+  """ insert decision llm made to vectordb
+  """
+  function insert_sommelier_decision(recentevents::T1, decision::T2; maxdistance::Integer=5
+    ) where {T1<:AbstractString, T2<:AbstractDict}
+    tablename = "sommelier_decision_repository"
+    # find similar
+    df = find_similar_text_from_vectordb(recentevents, tablename, 
+                                    "function_input_embedding", execute_sql_vectordb)
+    row, col = size(df)
+    distance = row == 0 ? Inf : df[1, :distance]
+    if row == 0 || distance > maxdistance # no close enough SQL stored in the database
+      _embedding = get_embedding([recentevents])[1]
+      recentevents_embedding = _embedding["data"][1]["embedding"]
+      recentevents = replace(recentevents, "'" => "")
+      decision_json = JSON.json(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)
+      _ = execute_sql_vectordb(sql)
+    else
+      println("--| similar decision previously cached, distance $distance ", @__FILE__, " ", @__LINE__)
+    end
+  end
+
+config = JSON.parsefile("./appconfig.json")
 sessionId = "0"
-backend_session_topic = "sommpanion.backend.agentbackend.v1.inbox.$sessionId"
-
-config = JSON.parsefile("./dummy_config.json")
+backend_session_topic = "sommpanion.testsubject"
 agent_ch = Channel(8)
 agent_conn  = NATS.connect(config["nats_server_info"]["url"])
+
 sub2 = NATS.subscribe(agent_conn, backend_session_topic) do msg
   put!(agent_ch, msg)
 end
@@ -210,32 +246,34 @@ agent_context = YiemAgent.agentcontext(
     insert_sommelier_decision
   )
 
-# can't instantiate
-agent = YiemAgent.sommelier(
-  agent_context;
-  name="Janie",
-  id=sessionId,  # agent instance id
-  retailername="Yiem",
-  llmFormatName=""
-)
+  # can't instantiate
+  agent = YiemAgent.sommelier(
+    agent_context;
+    name="Janie",
+    id=sessionId,  # agent instance id
+    retailername="Yiem Wine Ltd.",
+    llmFormatName=""
+  )
 
 
-
-
-# 1. Read local file and encode to base64 string
 image1_path = "test/large_image.png"
 image1_bytes = read(image1_path)
 image1_base64_string = base64encode(image1_bytes)
-
-# 2. Match the MIME type according to your file extension (e.g., png, jpeg)
 mime_type = "image/png" 
 data1_uri = "data:$(mime_type);base64,$(image1_base64_string)"
 
+# 1. Read local file and encode to base64 string
+image2_path = "test/small_image.png"
+image2_bytes = read(image2_path)
+image2_base64_string = base64encode(image2_bytes)
+mime_type = "image/png" 
+data2_uri = "data:$(mime_type);base64,$(image2_base64_string)"
+
 # 3. Construct payload with the Data URI
-usermsg = Dict{String, Any}(
+message = Dict(
     "role" => "user",
     "content" => [
-      Dict("type" => "text", "text" => "รู้จักไวน์ที่อยู่ในรูปมั้ย"),
+      Dict("type" => "text", "text" => "Do you know type of wine in the image?"),
       Dict(
         "type" => "image_url",
         "image_url" => Dict("url" => data1_uri)
@@ -243,8 +281,80 @@ usermsg = Dict{String, Any}(
     ]
   )
 
-result = YiemAgent.conversation(agent; userinput=usermsg)
-println(result)
+result = YiemAgent.conversation(agent; userinput=message)
+println("\n$result")
+
+
+
+
+
+
+
+
+
+# message = Dict(
+#     "role" => "user",
+#     "content" => [
+#       Dict("type" => "text", "text" => 
+#       "
+#       เป็นงานเลี้ยงทั่วไป
+#       "),
+#     ]
+#   )
+
+# result = YiemAgent.conversation(agent; userinput=message)
+# println("\n$result")
+
+
+
+
+
+
+
+
+
+# message = Dict(
+#     "role" => "user",
+#     "content" => [
+#       Dict("type" => "text", "text" => "no thanks. that's all"),
+#     ]
+#   )
+
+# result = YiemAgent.conversation(agent; userinput=message)
+# println("\n$result")
+
+
+
+
+
+
+# message = Dict(
+#     "role" => "user",
+#     "content" => [
+#       Dict("type" => "text", "text" => "What about this wine?"),
+#       Dict(
+#         "type" => "image_url",
+#         "image_url" => Dict("url" => data2_uri)
+#       )
+#     ]
+#   )
+
+# result = YiemAgent.conversation(agent; userinput=message)
+# println("\n$result")
+
+
+
+
+
+
+
+
+
+
+
+
+
+