update

Manifest.toml

@@ -2,7 +2,7 @@
 
 julia_version = "1.12.6"
 manifest_format = "2.0"
-project_hash = "db8baf2dd943e4138b5952183a64465f457da356"
+project_hash = "a5128932115e2d3aa9658af105ac712db061d523"
 
 [[deps.Accessors]]
 deps = ["CompositionsBase", "ConstructionBase", "Dates", "InverseFunctions", "MacroTools"]
@@ -290,9 +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"]
-path = "../GeneralUtils"
+git-tree-sha1 = "a75a088ee8e5faf10f554ca00748e0e6ca58d1ca"
+repo-rev = "main"
+repo-url = "https://git.yiem.cc/ton/GeneralUtils"
 uuid = "c6c72f09-b708-4ac8-ac7c-2084d70108fe"
-version = "0.4.10"
+version = "0.5.1"
 
 [[deps.Graphs]]
 deps = ["ArnoldiMethod", "DataStructures", "Inflate", "LinearAlgebra", "Random", "SimpleTraits", "SparseArrays", "Statistics"]
@@ -791,9 +793,11 @@ version = "0.7.0"
 
 [[deps.SQLLLM]]
 deps = ["CSV", "DataFrames", "DataStructures", "Dates", "FileIO", "GeneralUtils", "HTTP", "JSON", "LLMMCTS", "LibPQ", "PrettyPrinting", "Random", "Revise", "StatsBase", "Tables", "URIs", "UUIDs"]
-path = "../SQLLLM"
+git-tree-sha1 = "bae2fd2e2b087753fbb3415896be41df1ae0eb90"
+repo-rev = "main"
+repo-url = "https://git.yiem.cc/ton/SQLLLM"
 uuid = "2ebc79c7-cc10-4a3a-9665-d2e1d61e63d3"
-version = "0.2.7"
+version = "0.2.8"
 
 [[deps.SQLStrings]]
 git-tree-sha1 = "55de0530689832b1d3d43491ee6b67bd54d3323c"
@@ -1043,10 +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", "SQLLLM", "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 = "0.5.0"
+version = "0.6.4"
 authors = ["narawat lamaiin <narawat@outlook.com>"]
 
 [deps]
@@ -25,7 +25,9 @@ UUIDs = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
 [compat]
 CSV = "0.10.15"
 DataFrames = "1.7.0"
+GeneralUtils = "0.5.1"
 HTTP = "2.4.0"
 JSON = "1.6.1"
 LLMMCTS = "0.1.5"
 NATS = "0.1.0"
+SQLLLM = "0.2.8"

etc.jl

@@ -1,13 +1,28 @@
-
+"""
-
+CREATE TABLE "public"."wine" (
-
+    "wine_id" uuid DEFAULT gen_random_uuid() NOT NULL,
-d = Dict(
+    "seo_name" character varying(128) NOT NULL,
-  "hello"=> 555,
+    "wine_name" character varying(128) NOT NULL,
-  "world"=> Dict(
+    "winery" character varying(128) NOT NULL,
-    "name"=> "ton"
+    "vintage" integer NOT NULL,
-  )
+    "region" character varying(128) NOT NULL,
-)
+    "country" character varying(128) NOT NULL,
-
+    "wine_type" character varying(128) NOT NULL,
-x = 55
+    "grape" character varying(128) NOT NULL,
-
+    "serving_temperature" character varying(128) NOT NULL,
-@info "YiemAgent think() 1 " d x @__LINE__
+    "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
@@ -400,6 +387,7 @@ function conversation(a::sommelier; userinput::Union{Dict{String, Any}, JSON.Obj
           "content" => [Dict("type" => "text", "text" => thoughtdict["action_input"]),]
         )
         addNewMessage(a, "assistant", assistant_response; maximumMsg=maximumMsg)
+        @info "YiemAgent conversation() 2-5 think count $loopcount " @__LINE__
         return thoughtdict["action_input"]
       # elseif thoughtdict["action_name"] ∈ ["CHAT_BOX"]
       #   @info "YiemAgent conversation() 2-4 think count $loopcount " @__LINE__
@@ -419,7 +407,7 @@ function conversation(a::sommelier; userinput::Union{Dict{String, Any}, JSON.Obj
       #   )
       #   addNewMessage(a, "assistant", assistant_response; maximumMsg=maximumMsg)
 
-        return thoughtdict["action_input"]  #XXX change output from string to dict
+      #   return thoughtdict["action_input"]  #XXX change output from string to dict
       else
         action_name = thoughtdict["action_name"]
         action_input = thoughtdict["action_input"]
@@ -473,7 +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__
@@ -685,19 +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

@@ -396,133 +396,143 @@ function generatesql(a::T, searchterm::String,
         Do not wrap the SQL as it will be executed against the database directly and SQL must be ended with ';'.
     """
 
-  table_schema =
+  # table_schema =
-    """
+  #   """
-    create table customer (
+  #   create table customer (
-      customer_id uuid primary key default gen_random_uuid (),
+  #     customer_id uuid primary key default gen_random_uuid (),
-      customer_firstname varchar(128),
+  #     customer_firstname varchar(128),
-      customer_lastname varchar(128),
+  #     customer_lastname varchar(128),
-      customer_displayname varchar(128) not null,
+  #     customer_displayname varchar(128) not null,
-      customer_username varchar(128),
+  #     customer_username varchar(128),
-      customer_password varchar(128),
+  #     customer_password varchar(128),
-      customer_gender varchar(128),
+  #     customer_gender varchar(128),
-      country	varchar(128),
+  #     country	varchar(128),
-      telephone varchar(128),
+  #     telephone varchar(128),
-      email varchar(128) not null,
+  #     email varchar(128) not null,
-      customer_birthdate varchar(128),
+  #     customer_birthdate varchar(128),
-      note text,
+  #     note text,
       
-      other_attributes jsonb,
+  #     other_attributes jsonb,
-      created_time timestamptz default current_timestamp,
+  #     created_time timestamptz default current_timestamp,
-      updated_time timestamptz default current_timestamp,
+  #     updated_time timestamptz default current_timestamp,
-      description	text
+  #     description	text
-    );
+  #   );
 
-    create table retailer (
+  #   create table retailer (
-      retailer_id uuid primary key default gen_random_uuid (),
+  #     retailer_id uuid primary key default gen_random_uuid (),
-      retailer_name varchar(128) not null,
+  #     retailer_name varchar(128) not null,
-      retailer_username varchar(128) not null,
+  #     retailer_username varchar(128) not null,
-      retailer_password varchar(128) not null,
+  #     retailer_password varchar(128) not null,
-      retailer_address	text not null,
+  #     retailer_address	text not null,
-      country	varchar(128) not null,
+  #     country	varchar(128) not null,
-      contact_person varchar(128) not null,
+  #     contact_person varchar(128) not null,
-      telephone	varchar(128) not null,
+  #     telephone	varchar(128) not null,
-      email	varchar(128) not null,
+  #     email	varchar(128) not null,
-      note text,
+  #     note text,
       
-      other_attributes jsonb,
+  #     other_attributes jsonb,
-      created_time timestamptz default current_timestamp,
+  #     created_time timestamptz default current_timestamp,
-      updated_time timestamptz default current_timestamp,
+  #     updated_time timestamptz default current_timestamp,
-      description	text
+  #     description	text
-    ); 
+  #   ); 
 
-    create table food (
+  #   create table food (
-      food_id uuid primary key default gen_random_uuid (),
+  #     food_id uuid primary key default gen_random_uuid (),
-      food_name varchar(128) not null,
+  #     food_name varchar(128) not null,
-      country	varchar(128),
+  #     country	varchar(128),
-      spiciness	integer,
+  #     spiciness	integer,
-      sweetness	integer,
+  #     sweetness	integer,
-      sourness	integer,
+  #     sourness	integer,
-      savoriness	integer, 
+  #     savoriness	integer, 
-      bitterness	integer,
+  #     bitterness	integer,
-      serving_temperature	integer,
+  #     serving_temperature	integer,
-      image_url jsonb,
+  #     image_url jsonb,
-      note text,
+  #     note text,
-      other_attributes jsonb,
+  #     other_attributes jsonb,
 
-      created_time timestamptz default current_timestamp,
+  #     created_time timestamptz default current_timestamp,
-      updated_time timestamptz default current_timestamp,
+  #     updated_time timestamptz default current_timestamp,
-      description	text
+  #     description	text
-    );
+  #   );
 
-    create table wine (
+  #   create table wine (
-      wine_id uuid primary key default gen_random_uuid (),
+  #     wine_id uuid primary key default gen_random_uuid (),
-      seo_name varchar(128) not null,
+  #     seo_name varchar(128) not null,
-      wine_name varchar(128) not null,
+  #     wine_name varchar(128) not null,
-      winery varchar(128) not null,
+  #     winery varchar(128) not null,
-      vintage integer not null,
+  #     vintage integer not null,
-      region varchar(128) not null,
+  #     region varchar(128) not null,
-      country	varchar(128) not null,
+  #     country	varchar(128) not null,
-      wine_type	varchar(128) not null,
+  #     wine_type	varchar(128) not null,
-      grape	varchar(128) not null,
+  #     grape	varchar(128) not null,
-      serving_temperature	varchar(128) not null,
+  #     serving_temperature	varchar(128) not null,
-      intensity	integer,
+  #     intensity	integer,
-      sweetness	integer,
+  #     sweetness	integer,
-      tannin integer,
+  #     tannin integer,
-      acidity integer,
+  #     acidity integer,
-      fizziness	integer,
+  #     fizziness	integer,
-      tasting_notes text,
+  #     tasting_notes text,
-      image_url jsonb,
+  #     image_url jsonb,
-      manufacturer_sku text,
+  #     manufacturer_sku text,
-      note text,
+  #     note text,
-      other_attributes jsonb,
+  #     other_attributes jsonb,
       
-      created_time timestamptz default current_timestamp,
+  #     created_time timestamptz default current_timestamp,
-      updated_time timestamptz default current_timestamp,
+  #     updated_time timestamptz default current_timestamp,
-      description	text
+  #     description	text
-    );
+  #   );
 
-    create table wine_food (
+  #   create table wine_food (
-      wine_id uuid references wine(wine_id),
+  #     wine_id uuid references wine(wine_id),
-      food_id uuid references food(food_id),
+  #     food_id uuid references food(food_id),
-      constraint wine_food_id primary key (wine_id, food_id),
+  #     constraint wine_food_id primary key (wine_id, food_id),
 
-      created_time timestamptz default current_timestamp,
+  #     created_time timestamptz default current_timestamp,
-      updated_time timestamptz default current_timestamp
+  #     updated_time timestamptz default current_timestamp
-    );
+  #   );
 
-    CREATE TABLE retailer_wine (
+  #   CREATE TABLE retailer_wine (
-      retailer_id uuid references retailer(retailer_id),
+  #     retailer_id uuid references retailer(retailer_id),
-      wine_id uuid references wine(wine_id),
+  #     wine_id uuid references wine(wine_id),
-      constraint retailer_wine_id primary key (retailer_id, wine_id),
+  #     constraint retailer_wine_id primary key (retailer_id, wine_id),
-      price NUMERIC(10, 2),
+  #     price NUMERIC(10, 2),
-      currency varchar(3) not null,
+  #     currency varchar(3) not null,
       
-      created_time timestamptz default current_timestamp,
+  #     created_time timestamptz default current_timestamp,
-      updated_time timestamptz default current_timestamp
+  #     updated_time timestamptz default current_timestamp
-    );
+  #   );
 
-    CREATE TABLE retailer_food (
+  #   CREATE TABLE retailer_food (
-      retailer_id uuid references retailer(retailer_id),
+  #     retailer_id uuid references retailer(retailer_id),
-      food_id uuid references food(food_id),
+  #     food_id uuid references food(food_id),
-      constraint retailer_food_id primary key (retailer_id, food_id),
+  #     constraint retailer_food_id primary key (retailer_id, food_id),
-      price NUMERIC(10, 2),
+  #     price NUMERIC(10, 2),
-      currency varchar(3) not null,
+  #     currency varchar(3) not null,
       
-      created_time timestamptz default current_timestamp,
+  #     created_time timestamptz default current_timestamp,
-      updated_time timestamptz default current_timestamp
+  #     updated_time timestamptz default current_timestamp
-    );
+  #   );
-    """
+  #   """
 
   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"
+  # similarSQL_ = sql !== nothing ? sql : "None"
-  # if sql is really close, just use it
+  # # if sql is really close, just use it
-  if similarSQL_ != "None" && distance <= 0.1
+  # if similarSQL_ != "None" && distance <= 0.1
-    return similarSQL_
+  #   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_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 = 
@@ -531,12 +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
@@ -751,11 +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",
@@ -823,15 +827,17 @@ function extractWineAttributes_1(a::T1, input::T2; maxattempt=10
       responsedict[k] = _v
     end
 
-    println("\n--- extractWineAttributes_1-1()")
+    # println("\n--- extractWineAttributes_1-1()")
-    @show responsedict
+    # @show responsedict
-    @info "---\n" @__LINE__
+    # @info "---\n" @__LINE__
 
-    #WORKING check each attributes against database with BM25
+    # check each attributes against each column in a database table with BM25
     for (k, v) in responsedict
-      words_catalog = GeneralUtils.harvest_entity_catalog(a.context.pg_conn_str, "wine", k)
+      if k ∉ ["wine_price_min", "wine_price_max"]
-      resolved_word = GeneralUtils.resolve_entity(v, words_catalog;threshold=0.9)
+        words_catalog = GeneralUtils.harvest_entity_catalog(a.context.pg_conn_str, "wine", k)
-      responsedict[k] = resolved_word
+        resolved_word = GeneralUtils.resolve_entity(v, words_catalog;threshold=0.9)
+        responsedict[k] = resolved_word
+      end
     end
 
     result = ""
@@ -843,15 +849,10 @@ function extractWineAttributes_1(a::T1, input::T2; maxattempt=10
     end
 
     result = result[1:end-2]  # remove the ending ", "
-    println("\n--- extractWineAttributes_1-2()")
+    # println("\n--- extractWineAttributes_1-2()")
-    @show responsedict
+    # @show responsedict
-    @show result
+    # @show result
-    @info "---\n" @__LINE__
+    # @info "---\n" @__LINE__
-
-
-    
-
-
     return result
   end
   error("extractWineAttributes_1() failed to get a response")

src/type.jl

@@ -16,7 +16,9 @@ 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