Merge pull request 'update' (#28) from v0.7.3-fix_item_info into v0.7.3

Reviewed-on: #28

Manifest.toml

@@ -2,7 +2,7 @@
 
 julia_version = "1.12.6"
 manifest_format = "2.0"
-project_hash = "1e317787f914f6d857feb7c23bb910d1185caed9"
+project_hash = "dc7878808bbc4637a12e709dd495979a784824a5"
 
 [[deps.Accessors]]
 deps = ["CompositionsBase", "ConstructionBase", "Dates", "InverseFunctions", "MacroTools"]
@@ -244,6 +244,12 @@ 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 = "6621fef488e496356c9c9625d0562c12a6070819"
@@ -500,6 +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"
@@ -828,6 +840,12 @@ 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"
@@ -932,6 +950,12 @@ 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"
@@ -1052,11 +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", "SQLLLM", "Serialization", "URIs", "UUIDs"]
+deps = ["Base64", "CSV", "DataFrames", "DataStructures", "Dates", "GeneralUtils", "HTTP", "JSON", "LLMMCTS", "LibPQ", "NATS", "PrettyPrinting", "Random", "Revise", "SQLLLM", "Serialization", "URIs", "UUIDs"]
 path = "."
 uuid = "e012c34b-7f78-48e0-971c-7abb83b6f0a2"
-version = "0.6.5"
+version = "0.7.2"
 
 [[deps.Zlib_jll]]
 deps = ["Libdl"]

Project.toml

@@ -19,6 +19,7 @@ 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"
@@ -33,3 +34,4 @@ JSON = "1.6.1"
 LLMMCTS = "0.1.5"
 NATS = "0.1.0"
 SQLLLM = "0.2.8"
+Serde = "3.7.2"

src/interface.jl

@@ -393,8 +393,6 @@ function conversation(a::sommelier; userinput::Union{Dict{String, Any}, JSON.Obj
       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"]),]
@@ -404,17 +402,17 @@ function conversation(a::sommelier; userinput::Union{Dict{String, Any}, JSON.Obj
         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}(
@@ -435,8 +433,6 @@ function conversation(a::sommelier; userinput::Union{Dict{String, Any}, JSON.Obj
       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"]),]
@@ -446,17 +442,17 @@ function conversation(a::sommelier; userinput::Union{Dict{String, Any}, JSON.Obj
         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}(

src/llmfunction.jl

@@ -5,7 +5,7 @@ export  virtualWineUserChatbox, jsoncorrection, search_wine_database!, # recomme
         extractWineAttributes_2, paraphrase, SQLexecution
 
 using HTTP, JSON, URIs, Random, PrettyPrinting, UUIDs, Dates, DataFrames, DataStructures,
-      Base64
+      Base64, Serde
 using GeneralUtils, SQLLLM
 using ..type, ..util
 
@@ -277,15 +277,20 @@ end
 # Example
 ```jldoctest
 julia> using ChatAgent
-julia> agent = ChatAgent.agentReflex("Jene")
+julia> agent = YiemAgent.sommelier(...)
-julia> input = "{\"food\": \"pizza\", \"occasion\": \"anniversary\"}"
+julia> thoughtdict = 
-julia> result = checkinventory(agent, input)
+  OrderedDict{String, Any}(
-"{"wine 1": {\"Winery\": \"Pichon Baron\", \"wine name\": \"Pauillac (Grand Cru Classé)\", \"grape variety\": \"Cabernet Sauvignon\", \"year\": 2010, \"price\": \"125 USD\", \"stock ID\": \"ar-17\"}, }"
+    "plan" => "The user is asking a very specific question about a wine (Brunello di Montalcino from Tenuta CastelGiocondo). Although the policy suggests gathering budget, wine type, and occasion, the user has provided enough specific information (name, region, producer) to attempt a direct search in the database. I will use the SEARCH_WINE_DATABASE action to check if this specific wine is in our inventory.", 
+    "action_name" => "SEARCH_WINE_DATABASE", 
+    "action_input" => "Brunello di Montalcino from Tenuta CastelGiocondo")
 ```
 """
 function search_wine_database!(a::T, thoughtdict::AbstractDict; useSQLLLM::Bool=false
   )::NamedTuple{(:thoughtdict, :result_raw), Tuple{OrderedDict, Any}} where {T<:agent}
   
+  # WORKING
+  # look_for_wine_in_wine_database(a, thoughtdict["action_input"])
+
   println("\ncheckinventory order: $(thoughtdict["action_input"]) ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
   wineattributes_1 = extractWineAttributes_1(a, thoughtdict["action_input"])
   wineattributes_2 = extractWineAttributes_2(a, thoughtdict["action_input"])
@@ -366,9 +371,9 @@ function generatesql(a::T, searchterm::String,
       Fulfill the objective.
     
     # 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.
+      1) "plan", Based on the current situation, state a complete action plan to complete the task and rationale. Be specific.
-      2) "action_name, Must be "RUNSQL"
+      2) "action_name", Must be "RUNSQL"
-      3) "action_input, The input to the action you are about to perform according to your plan.
+      3) "action_input", The input to the action you are about to perform 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
@@ -610,6 +615,230 @@ function generatesql(a::T, searchterm::String,
   error("SQLLLM DecisionMaker() failed to generate a thought \n", response)
 end
 
+
+"""
+# Example
+```jldoctest
+julia> using ChatAgent
+julia> agent = YiemAgent.sommelier(...)
+julia> thoughtdict = 
+  OrderedDict{String, Any}(
+    "plan" => "The user is asking a very specific question about a wine (Brunello di Montalcino from Tenuta CastelGiocondo). Although the policy suggests gathering budget, wine type, and occasion, the user has provided enough specific information (name, region, producer) to attempt a direct search in the database. I will use the SEARCH_WINE_DATABASE action to check if this specific wine is in our inventory.", 
+    "action_name" => "SEARCH_WINE_DATABASE", 
+    "action_input" => "Brunello di Montalcino from Tenuta CastelGiocondo")
+```
+julia> look_for_wine_in_wine_database(agent, thoughtdict["action_input"])
+"""
+function look_for_wine_in_wine_database(a::T, searchterm::String,
+  ; maxattempt=10
+  )::String where {T<:agent}
+
+  systemmsg = 
+    """
+
+    # situation
+      At each round of conversation, you will be given the following:
+      - user search term
+      - database tables schema
+
+    # objective
+      Consult the provided database schema (tables and columns), please map a user's natural-language search term to the appropriate database columns and tables—identify the relevant fields, operators, and values (e.g., for SQL filtering).
+
+    # your responsibility includes
+      Fulfill the objective.
+
+    # you should only respond in YAML format as described below
+      table_name_1:
+        column_name_1:
+          operator: "="
+          value: "..."
+        column_name_2:
+          operator: "="
+          value: "..."
+        ...   
+      table_name_2:
+        column_name_1:
+          operator: "="
+          value: "..."
+        column_name_2:
+          operator: "="
+          value: "..." 
+        ...
+
+    # here are some example
+      <user>
+        4-wheel drive car with red color that will give me fast and furious emotion. No more than 7000 USD
+      </user>
+      <assistant>
+        car_info:          # table_name
+          drive_type:      # column_name
+            operator: "="  # operator is not "N/A" because drive_type column store quantitative value
+            value: "4-wheel"  # column_value
+          color:
+            operator: "="  # operator is not "N/A" because color column store quantitative value
+            value: "red"
+          drive_feeling:
+            operator: "N/A"  # operator is "N/A" because drive_feeling column store qualitative value
+            value: "fast and furious"
+        price_list:
+          price:
+            operator: "<"  # operator is not "N/A" because drive_type column store quantitative value
+            value: "7000"
+      </assistant>
+    """
+
+
+  # use find_related_tables_for_user_question and inject only related table schema for a given search term
+  # to LLM instead of giving LLM all tables schema.
+  related_tables = a.context.find_related_tables_for_user_question(searchterm)
+  table_schema = ""
+  for table in related_tables
+    _table_schema_str = GeneralUtils.get_db_table_schema_simple(a.context.pg_conn_str, table)
+    table_schema_str = sprint(show, _table_schema_str) * "\n"
+    table_schema = table_schema * table_schema_str
+  end
+
+  context = 
+    """
+    <internal_context_for_assistant>
+      <database_table_schema>
+        $table_schema
+      </database_table_schema>
+    </internal_context_for_assistant>
+    """
+  input = context * searchterm
+
+  msg = Dict(
+    "model" => "gemma-4-E4B-it-UD-Q4_K_XL",
+    "messages" => [
+      Dict(
+        "role" => "system",
+        "content" => [
+          Dict("type" => "text", "text" => systemmsg),
+        ]
+      ),
+      Dict(
+        "role" => "user",
+        "content" => [
+          Dict("type" => "text", "text" => input),
+        ]
+      ),
+    ],
+    "temperature" => 0.7
+  )
+
+  for attempt in 1:maxattempt
+    response = a.context.text2textInstructLLM("random_id", msg)
+    responsedict = Serde.parse_yaml(response)
+
+    """
+    responsedict = Dict(
+      "wine" => Dict(
+                    "tasting_notes" => Dict(
+                                              "operator" => "N/A", 
+                                              "value" => "casual dinner"
+                                            ),
+                    "wine_type" => Dict(
+                                          "operator" => "=", 
+                                          "value" => "red"
+                                        )
+                    ),
+     "retailer_wine" => Dict(
+                            "currency" => Dict(
+                                              "operator" => "=", "value" => "USD"
+                                              ), 
+                            "price" => Dict(
+                                          "operator" => "<", "value" => "1000"
+                                          )
+                            )
+                        )
+    """   
+
+    for (table_name, table_info_dict) in responsedict
+      for (column_name, v) in table_info_dict
+
+        # 
+        do_not_resolve_BM25_list = ["tasting_notes", "seo_name", "vintage", "grape"]
+        if column_name ∉ do_not_resolve_list
+          words_catalog = GeneralUtils.harvest_entity_catalog(a.context.pg_conn_str, table_name, column_name)
+          resolved_word = GeneralUtils.resolve_entity(v["value"], words_catalog; threshold=0.9)
+          table_info_dict[column_name] = resolved_word
+        end
+      end
+    end
+
+
+    # check each attributes against each column in a database table with BM25 and get the closest
+    # word match because there is a typo sometimes. 
+    for (k, v) in responsedict
+      if k ∉ ["tasting_notes"]
+        words_catalog = GeneralUtils.harvest_entity_catalog(a.context.pg_conn_str, "wine", k)
+        resolved_word = GeneralUtils.resolve_entity(v, words_catalog; threshold=0.9)
+        responsedict[k] = resolved_word
+      end
+    end
+
+
+
+
+
+
+    #WORKING
+    println("\n", responsedict)
+    @info "test done " @__LINE__
+    error(9999)
+
+
+
+
+
+    think, response = GeneralUtils.extractthink(response)
+    responsedict = nothing
+     try
+      _responsedict = JSON.parse(response)
+      responsedict = GeneralUtils.dictify(_responsedict, keytype=String)
+    catch
+      println("\nERROR decisionMaker() failed to parse response: $response ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+      continue
+    end
+
+    # check each attributes against each column in a database table with BM25 and get the closest
+    # word match because there is a typo sometimes. 
+    for (k, v) in responsedict
+      if k ∉ ["tasting_notes"]
+        words_catalog = GeneralUtils.harvest_entity_catalog(a.context.pg_conn_str, "wine", k)
+        resolved_word = GeneralUtils.resolve_entity(v, words_catalog; threshold=0.9)
+        responsedict[k] = resolved_word
+      end
+    end
+
+    #  LLM already extract user search term against tables schema
+    # Ex. responsedict = Dict(
+    #                       "wine_type"=> "red",                  # hard constraint
+    #                       "region"=> "bordeaux",                # hard constraint
+    #                       "price_max"=> "100",                  # hard constraint
+    #                       "tasting_notes"=> "fruity, oak"       # semantic search)
+    
+
+    
+
+    
+
+
+
+
+
+
+
+
+
+
+
+    return items
+  end
+  error("SQLLLM DecisionMaker() failed to generate a thought \n", response)
+end
+
 function SQLexecution(executeSQL::Function, sql::T
   )::NamedTuple where {T<:AbstractString}