update

Manifest.toml

@@ -2,7 +2,7 @@
 
 julia_version = "1.12.6"
 manifest_format = "2.0"
-project_hash = "76bd6c852fad3452022f32202b19c4689be8e912"
+project_hash = "a5128932115e2d3aa9658af105ac712db061d523"
 
 [[deps.Accessors]]
 deps = ["CompositionsBase", "ConstructionBase", "Dates", "InverseFunctions", "MacroTools"]
@@ -290,11 +290,11 @@ 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 = "aa695d21f155567524e7329fb7b96d8a9d0eba86"
+git-tree-sha1 = "a75a088ee8e5faf10f554ca00748e0e6ca58d1ca"
 repo-rev = "main"
 repo-url = "https://git.yiem.cc/ton/GeneralUtils"
 uuid = "c6c72f09-b708-4ac8-ac7c-2084d70108fe"
-version = "0.5.0"
+version = "0.5.1"
 
 [[deps.Graphs]]
 deps = ["ArnoldiMethod", "DataStructures", "Inflate", "LinearAlgebra", "Random", "SimpleTraits", "SparseArrays", "Statistics"]
@@ -1047,10 +1047,10 @@ uuid = "76eceee3-57b5-4d4a-8e66-0e911cebbf60"
 version = "1.6.1"
 
 [[deps.YiemAgent]]
-deps = ["CSV", "DataFrames", "DataStructures", "Dates", "GeneralUtils", "HTTP", "JSON", "LLMMCTS", "LibPQ", "NATS", "PrettyPrinting", "Random", "Revise", "Serialization", "URIs", "UUIDs"]
+deps = ["CSV", "DataFrames", "DataStructures", "Dates", "HTTP", "JSON", "LLMMCTS", "LibPQ", "NATS", "PrettyPrinting", "Random", "Revise", "SQLLLM", "Serialization", "URIs", "UUIDs"]
 path = "."
 uuid = "e012c34b-7f78-48e0-971c-7abb83b6f0a2"
-version = "0.5.0"
+version = "0.6.4"
 
 [[deps.Zlib_jll]]
 deps = ["Libdl"]

Project.toml

@@ -1,6 +1,6 @@
 name = "YiemAgent"
 uuid = "e012c34b-7f78-48e0-971c-7abb83b6f0a2"
-version = "0.6.0"
+version = "0.6.4"
 authors = ["narawat lamaiin <narawat@outlook.com>"]
 
 [deps]
@@ -25,7 +25,7 @@ UUIDs = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
 [compat]
 CSV = "0.10.15"
 DataFrames = "1.7.0"
-GeneralUtils = "0.5.0"
+GeneralUtils = "0.5.1"
 HTTP = "2.4.0"
 JSON = "1.6.1"
 LLMMCTS = "0.1.5"

etc.jl

@@ -1,13 +1,28 @@
-
-
-
-d = Dict(
-  "hello"=> 555,
-  "world"=> Dict(
-    "name"=> "ton"
-  )
-)
-
-x = 55
-
-@info "YiemAgent think() 1 " d x @__LINE__
+"""
+CREATE TABLE "public"."wine" (
+    "wine_id" uuid DEFAULT gen_random_uuid() NOT NULL,
+    "seo_name" character varying(128) NOT NULL,
+    "wine_name" character varying(128) NOT NULL,
+    "winery" character varying(128) NOT NULL,
+    "vintage" integer NOT NULL,
+    "region" character varying(128) NOT NULL,
+    "country" character varying(128) NOT NULL,
+    "wine_type" character varying(128) NOT NULL,
+    "grape" character varying(128) NOT NULL,
+    "serving_temperature" character varying(128) NOT NULL,
+    "intensity" integer NULL,
+    "sweetness" integer NULL,
+    "tannin" integer NULL,
+    "acidity" integer NULL,
+    "fizziness" integer NULL,
+    "tasting_notes" text NULL,
+    "image_url" jsonb NULL,
+    "manufacturer_sku" text NULL,
+    "note" text NULL,
+    "other_attributes" jsonb NULL,
+    "created_time" timestamp with time zone DEFAULT CURRENT_TIMESTAMP NULL,
+    "updated_time" timestamp with time zone DEFAULT CURRENT_TIMESTAMP NULL,
+    "description" text NULL,
+    PRIMARY KEY (wine_id)
+);
+"""

src/interface.jl

@@ -154,19 +154,6 @@ function decisionMaker(a::T; recentevents::Integer=20, maxattempt=10
         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
     end
 
     # check whether all answer's key points are in responsedict
@@ -474,7 +461,7 @@ function think(a::T)::NamedTuple{(:thoughtdict, :result_raw), Tuple{OrderedDict,
 
   elseif thoughtdict["action_name"] == "SEARCH_WINE_DATABASE" 
     @info "YiemAgent think() 5 " @__LINE__
-    thoughtdict, result_raw = search_wine_database!(a, thoughtdict; useSQLLLM=true)
+    thoughtdict, result_raw = search_wine_database!(a, thoughtdict; useSQLLLM=false)
     #WORKING result_raw will be a df. i need to get images so i can send to frontend
   else
     @info "YiemAgent think() 6 " @__LINE__
@@ -686,19 +673,6 @@ function generatechat!(a::T; maxattempt::Integer=10
         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
     end
 
     # check whether all answer's key points are in responsedict

src/llmfunction.jl

@@ -517,21 +517,21 @@ function generatesql(a::T, searchterm::String,
   requiredKeys = ["plan", "action_name", "action_input"]
   errornote = ""
   # provide similar sql only for the first attempt
-  sql, distance = a.context.similarSQLVectorDB(searchterm)
+  # sql, distance = a.context.similarSQLVectorDB(searchterm)
 
-  similarSQL_ = sql !== nothing ? sql : "None"
-  # if sql is really close, just use it
-  if similarSQL_ != "None" && distance <= 0.1
-    return similarSQL_
-  end
+  # similarSQL_ = sql !== nothing ? sql : "None"
+  # # if sql is really close, just use it
+  # if similarSQL_ != "None" && distance <= 0.1
+  #   return similarSQL_
+  # end
 
   #CHANGE use find_related_tables_for_user_question and inject only related table schema instead
   # of hard code table schema. CPU embedding is too slow. use embedding service on GPU. 
   related_tables = a.context.find_related_tables_for_user_question(searchterm)
   table_schema = ""
   for table in related_tables
-    table_schema_df = GeneralUtils.get_db_table_schema(a.context.pg_conn_str, table)
-    table_schema_str = sprint(show, table_schema_df) * "\n"
+    _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
 
@@ -541,12 +541,6 @@ function generatesql(a::T, searchterm::String,
       <database_table_schema>
         $table_schema
       </database_table_schema>
-      <possible SQL for user's search term>
-        $similarSQL_
-      </possible SQL for user's search term>
-      <error_note>
-        $errornote
-      <error_note>
     </internal_context_for_assistant>
     """
   input = context * searchterm
@@ -761,11 +755,11 @@ function extractWineAttributes_1(a::T1, input::T2; maxattempt=10
       "wine_name": "Saumur Blanc",
       "winery": "Domaine du Collier",
       "vintage": "2019",
-      "region": "Saumur",
+      "region": "N/A",
       "country": "France",
       "wine_type": "white",
       "grape_varietal": "Merlot",
-      "tasting_notes": "plum",
+      "tasting_notes": "N/A",
       "wine_price_min": "N/A",
       "wine_price_max": "N/A",
       "occasion": "N/A",
@@ -839,10 +833,12 @@ function extractWineAttributes_1(a::T1, input::T2; maxattempt=10
 
     # check each attributes against each column in a database table with BM25
     for (k, v) in responsedict
+      if k ∉ ["wine_price_min", "wine_price_max"]
         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
 
     result = ""
     for (k, v) in responsedict