Manifest.toml

@@ -2,7 +2,7 @@
 
 julia_version = "1.12.6"
 manifest_format = "2.0"
-project_hash = "dc7878808bbc4637a12e709dd495979a784824a5"
+project_hash = "fec141f7ff95c7150e820def295f9929445168b6"
 
 [[deps.Accessors]]
 deps = ["CompositionsBase", "ConstructionBase", "Dates", "InverseFunctions", "MacroTools"]
@@ -300,11 +300,11 @@ version = "1.1.0"
 
 [[deps.GeneralUtils]]
 deps = ["CSV", "DataFrames", "DataStructures", "Dates", "Distributions", "Graphs", "HTTP", "JSON", "LibPQ", "NATS", "PrettyPrinting", "Random", "Revise", "SHA", "StringDistances", "UUIDs"]
-git-tree-sha1 = "a75a088ee8e5faf10f554ca00748e0e6ca58d1ca"
+git-tree-sha1 = "596da266c851d00fbabcf33660419aeffb820fcb"
 repo-rev = "main"
 repo-url = "https://git.yiem.cc/ton/GeneralUtils"
 uuid = "c6c72f09-b708-4ac8-ac7c-2084d70108fe"
-version = "0.5.1"
+version = "0.5.7"
 
 [[deps.Graphs]]
 deps = ["ArnoldiMethod", "DataStructures", "Inflate", "LinearAlgebra", "Random", "SimpleTraits", "SparseArrays", "Statistics"]
@@ -1089,10 +1089,10 @@ uuid = "ddb6d928-2868-570f-bddf-ab3f9cf99eb6"
 version = "0.4.16"
 
 [[deps.YiemAgent]]
-deps = ["Base64", "CSV", "DataFrames", "DataStructures", "Dates", "GeneralUtils", "HTTP", "JSON", "LLMMCTS", "LibPQ", "NATS", "PrettyPrinting", "Random", "Revise", "SQLLLM", "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 = "0.7.2"
+version = "0.7.4"
 
 [[deps.Zlib_jll]]
 deps = ["Libdl"]

Project.toml

@@ -28,7 +28,7 @@ UUIDs = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
 Base64 = "1.11.0"
 CSV = "0.10.15"
 DataFrames = "1.7.0"
-GeneralUtils = "0.5.1"
+GeneralUtils = "0.5.7"
 HTTP = "2.4.0"
 JSON = "1.6.1"
 LLMMCTS = "0.1.5"

src/llmfunction.jl

@@ -302,10 +302,16 @@ function search_wine_database!(a::T, thoughtdict::AbstractDict; useSQLLLM::Bool=
   else
 
     # direct query with possible sql instead of SQLLLM. 
-    sql = predefined_wine_search_sql(a, thoughtdict["action_input"])
+    hard_conditions, vector_search_words = wine_search_term_classification(a, thoughtdict["action_input"])
+
+    # do hard filter
     # sql = generatesql(a, inventoryquery)
-    println("\nSQL: $sql ", @__FILE__, ":", @__LINE__, " $(Dates.now()) \n")
+    sql = predefined_wine_search_sql(hard_conditions)
+    @info "\nsql: $sql, \nvector_search_words: $vector_search_words"
     textresult, sql_result_df, success, _ = SQLexecution(a.context.executeSQL, sql)
+    
+    #WORKING  do vector search
+    GeneralUtils.find_text_vector_similarity(vector_search_words, "wine")
 
     items = nothing
     if sql_result_df !== nothing
@@ -619,9 +625,9 @@ julia> thoughtdict =
 ```
 julia> predefined_wine_search_sql(agent, thoughtdict["action_input"])
 """
-function predefined_wine_search_sql(a::T, searchterm::String,
+function wine_search_term_classification(a::T, searchterm::String,
   ; maxattempt=10
-  )::String where {T<:agent}
+  ) where {T<:agent}
 
   systemmsg = 
     """
@@ -641,7 +647,7 @@ function predefined_wine_search_sql(a::T, searchterm::String,
       The "extracted_info" key must contain an array of objects. Each object must contain:
       1) "table_name": The name of the table.
       2) "column_name": The specific column being filtered.
-      3) "operator": The comparison operator (e.g., "=", ">", "LIKE").
+      3) "operator": The comparison operator (e.g., "=", ">").
       4) "value": The value to compare against.
 
       If the user does not specify any filters, return an empty array for "extracted_info": {"extracted_info": []}.
@@ -668,7 +674,7 @@ function predefined_wine_search_sql(a::T, searchterm::String,
           {
             "table_name": "car_info",
             "column_name": "drive_feeling",
-            "operator": "ILIKE",
+            "operator": "=",
             "value": "fast and furious"
           },
           {
@@ -781,7 +787,7 @@ function predefined_wine_search_sql(a::T, searchterm::String,
     println("\n ", responsedict)
     @info "before BM25 " @__LINE__  
 
-    #WORKING to ensure user input is correct
+    # to ensure user input is correct
     for entry in responsedict["extracted_info"]
       table_name = entry["table_name"]::String
       column_name = entry["column_name"]::String
@@ -802,11 +808,12 @@ function predefined_wine_search_sql(a::T, searchterm::String,
 
     # Build new list of hard condition entries
     hard_conditions = JSON.Object{String, Any}[]
+    vector_search = JSON.Object{String, Any}[]
     for entry in responsedict["extracted_info"]
       if entry["operator"] ∈ hard_operators
         push!(hard_conditions, entry)
       else
-        vector_search_words = vector_search_words * entry["value"] * ", "
+        push!(vector_search, entry)
       end
     end
     responsedict = hard_conditions
@@ -814,14 +821,8 @@ function predefined_wine_search_sql(a::T, searchterm::String,
     println("")
     @show responsedict
     @info "predefined_wine_search_sql() " @__LINE__
-
-    #WORKING do vector search
-    println("")
-    @show vector_search_words
-    # error(9999)
-    sql = predefined_wine_search_sql(responsedict)
     
-    return sql
+    return (hard_conditions=hard_conditions, vector_search=vector_search)
   end
   error("SQLLLM DecisionMaker() failed to generate a thought \n", response)
 end