update

Reviewed-on: #27

Manifest.toml

@@ -2,7 +2,7 @@
 
 julia_version = "1.12.6"
 manifest_format = "2.0"
-project_hash = "76bd6c852fad3452022f32202b19c4689be8e912"
+project_hash = "dc7878808bbc4637a12e709dd495979a784824a5"
 
 [[deps.Accessors]]
 deps = ["CompositionsBase", "ConstructionBase", "Dates", "InverseFunctions", "MacroTools"]
@@ -97,9 +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"]
@@ -244,11 +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"]
@@ -290,11 +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 = "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"]
@@ -311,9 +321,9 @@ version = "1.14.0"
 
 [[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"
@@ -496,6 +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"
@@ -678,15 +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"]
@@ -767,9 +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"
@@ -822,6 +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"
@@ -926,6 +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"
@@ -1046,11 +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", "GeneralUtils", "HTTP", "JSON", "LLMMCTS", "LibPQ", "NATS", "PrettyPrinting", "Random", "Revise", "SQLLLM", "Serialization", "URIs", "UUIDs"]
 path = "."
 uuid = "e012c34b-7f78-48e0-971c-7abb83b6f0a2"
-version = "0.5.0"
+version = "0.7.2"
 
 [[deps.Zlib_jll]]
 deps = ["Libdl"]

Project.toml

@@ -1,9 +1,10 @@
 name = "YiemAgent"
 uuid = "e012c34b-7f78-48e0-971c-7abb83b6f0a2"
-version = "0.6.0"
+version = "0.7.2"
 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 = "0.5.0"
+GeneralUtils = "0.5.1"
 HTTP = "2.4.0"
 JSON = "1.6.1"
 LLMMCTS = "0.1.5"
 NATS = "0.1.0"
 SQLLLM = "0.2.8"
+Serde = "3.7.2"

etc.jl

@@ -1,13 +1,111 @@
+using HTTP, JSON, URIs, Random, PrettyPrinting, UUIDs, Dates, DataFrames, DataStructures
+using GeneralUtils, SQLLLM, YiemAgent
+
+config = JSON.parsefile("./appconfig.json")
+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"]
+pg_conn_str = "host=$host_url port=$port dbname=$dbname user=$user password=$password"
+
+  function execute_sql_winedb(sql::T) where {T<:AbstractString}
+    host_url, _port = split(config["externalservice"]["sommpanion_db"]["url"], ':')
+    port = parse(Int, _port)
+    dbname = "winedb"
+    user = config["externalservice"]["sommpanion_db"]["user"]
+    password = config["externalservice"]["sommpanion_db"]["password"]
+    db_connection = LibPQ.Connection("host=$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
+    
+    LibPQ.close(db_connection)
+    return result
+  end
+
+
+
+sql =
+"""
+SELECT T1.winery, T1.wine_name, T1.wine_id, T1.vintage, T1.region, T1.country, T1.wine_type, T1.grape, T1.serving_temperature, T1.sweetness, T1.intensity, T1.tannin, T1.acidity, T1.tasting_notes, T2.price, T2.currency, T1.image_url, T3.retailer_name, T3.retailer_id FROM "wine" AS T1 JOIN "retailer_wine" AS T2 ON T1.wine_id = T2.wine_id JOIN "retailer" AS T3 ON T2.retailer_id = T3.retailer_id WHERE T1.wine_name = 'Montrachet Grand Cru' AND T1.winery = 'Domaine Jacques Prieur' AND T3.retailer_name = 'Yiem Wines Ltd' AND T3.retailer_id = 'f54eab6b-7650-4448-b009-c53f3efbcc3b';
+"""
+
+textresult, sql_result_raw, _, _ = YiemAgent.SQLexecution(execute_sql_winedb, sql)
+result_vec = GeneralUtils.dfToVectorDict(sql_result_raw)
+
+for d in result_vec
+  wine_name = d["wine_name"]
+  image_url_json_str = d["image_url"]
+  image_url_json_obj = JSON.parse(image_url_json)
+  base_url = "http://192.168.88.106:8080/"
+  image_base64 =
+    if haskey(image_url_json_obj, "bottle")
+      url = base_url * image_url_json_obj["bottle"]
+      image_data = HTTP.get(url)  # vector{int} data
+      image_base64_string = base64encode(image_data)
+    else
+      nothing
+    end
+  d["image"] = image_base64
+end
+
+
+
+
+
+
+
+
+
+
+using LibPQ
+using Tables
+
+"""
+    update_car_regions_one_by_one(conn::LibPQ.Connection, target_word::String)
+
+Iterates through all rows in the 'car' table where the region is "German", 
+and updates them one-by-one to the `target_word`.
+"""
+function update_car_regions_one_by_one(pg_conn_str::String, replace_word::String , target_word::String)
+  conn = LibPQ.Connection(pg_conn_str)
+    # 1. Fetch the target rows. Assumes 'id' is the primary key.
+    # We select the ID to target rows individually during the update step.
+    select_query = "SELECT id FROM car WHERE region = '$replace_word';"
+    
+    result = execute(conn, select_query)
+    rows = Tables.rows(result)
+    
+    # 2. Prepare the update statement for execution reuse
+    # Using explicit types for parameter placeholders ($1, $2)
+    update_query = "UPDATE car SET region = \$1 WHERE id = \$2;"
+    
+    println("Starting one-by-one update...")
+    updated_count = 0
+
+    # 3. Iterate through rows one-by-one
+    for row in rows
+        # LibPQ row values are accessed via properties or column names
+        row_id = row.id 
+        
+        # Execute the parameterized statement safely
+        execute(conn, update_query, [target_word, row_id])
+        updated_count += 1
+    end
+
+    println("Successfully updated \$updated_count rows.")
+    return updated_count
+end
+
+
+
+
 
 
 
-d = Dict(
-  "hello"=> 555,
-  "world"=> Dict(
-    "name"=> "ton"
-  )
-)
 
-x = 55
 
-@info "YiemAgent think() 1 " d x @__LINE__

src/interface.jl

@@ -73,9 +73,9 @@ OrderedDict{String, Any} with 4 entries:
   "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 =
@@ -123,9 +123,7 @@ function decisionMaker(a::T; recentevents::Integer=20, maxattempt=10
   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
+
     
     msg = Dict(
       "model" => "gemma-4-E4B-it-UD-Q4_K_XL",
@@ -134,12 +132,13 @@ function decisionMaker(a::T; recentevents::Integer=20, maxattempt=10
     )
 
     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)
-    
+
     # dollar sign in Julia means string interpolation
     while occursin('$', response)
       response = replace(response, '$' => "USD")
@@ -154,26 +153,26 @@ 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
+    else
+      println("\nERROR YiemAgent decisionMaker() $errornote --(not qualify response)-> $responsedict ", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
+      continue
     end
 
     # check whether all answer's key points are in responsedict
+    println("\n---")
+    println(responsedict)
+    println("---\n")
     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")
+      println("\nERROR YiemAgent decisionMaker() $errornote --(not qualify response)-> $responsedict ", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
+      continue
+    end
+
+    if responsedict["action_input"] == "CHAT_BOX" && 
+      occursin("similar", responsedict["action_input"])
+
       continue
     end
 
@@ -185,10 +184,17 @@ function decisionMaker(a::T; recentevents::Integer=20, maxattempt=10
 
     # 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(
+    "plan"=> "N/A",
+    "action_name"=> "CHAT_BOX",
+    "action_input"=> "N/A"
+  )
+  return responsedict
 end
 
 
@@ -317,7 +323,7 @@ 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
 
@@ -360,7 +366,7 @@ 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
@@ -376,7 +382,7 @@ 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)
 
@@ -385,49 +391,119 @@ function conversation(a::sommelier; userinput::Union{Dict{String, Any}, JSON.Obj
     while true
       loopcount += 1
       if loopcount > max_think_loop
-        @info "YiemAgent conversation() 2-1 think count $loopcount " @__LINE__
-        r = generatechat!(a)
-        @info "YiemAgent conversation() 2-2 think count $loopcount " @__LINE__
-        return r
-      end
 
-      @info "YiemAgent conversation() 2-3 think count $loopcount " @__LINE__
-      thoughtdict, result_raw = think(a)
-      if thoughtdict["action_name"] ∈ ["CHAT_BOX"]
-        @info "YiemAgent conversation() 2-4 think count $loopcount " @__LINE__
+        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)
-        @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__
-      #   assistant_response = Dict{String, Any}(
-      #     "role" => "assistant",
-      #     "content" => [
-      #         Dict("type" => "text", "text" => thoughtdict["action_input"]),
-      #         Dict( #WORKING put 1st image here
-      #           "type" => "image_url",
-      #           "image_url" => Dict("url" => image1_data_uri)
-      #         ),
-      #         Dict( #WORKING put 2nd image here
-      #           "type" => "image_url",
-      #           "image_url" => Dict("url" => image2_data_uri)
-      #         ),
-      #       ]
-      #   )
-      #   addNewMessage(a, "assistant", assistant_response; maximumMsg=maximumMsg)
 
-      #   return thoughtdict["action_input"]  #XXX change output from string to dict
-      else
+        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
+
+
+      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"]
@@ -435,7 +511,9 @@ function conversation(a::sommelier; userinput::Union{Dict{String, Any}, JSON.Obj
             "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
@@ -455,34 +533,51 @@ 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)
+  @show thoughtdict
+  println("---\n")
 
   result_raw = nothing
   if thoughtdict["action_name"] ∈ ["CHAT_BOX"]
-    @info "YiemAgent think() 2 " @__LINE__
-    thoughtdict, result_raw = generatechat!(a)
-    
+
+    # 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" 
-    @info "YiemAgent think() 5 " @__LINE__
-    thoughtdict, result_raw = search_wine_database!(a, thoughtdict; useSQLLLM=true)
-    #WORKING result_raw will be a df. i need to get images so i can send to frontend
+
+    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
-  println("\n")
+
+  @info "YiemAgent think() end " @__LINE__
   @show thoughtdict
-  @info "YiemAgent think() 7 " @__LINE__
+  println("---\n")
   return (thoughtdict=thoughtdict, result_raw=result_raw)
 end
 
@@ -559,7 +654,7 @@ end
 #PENDING
 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 =
@@ -642,7 +737,7 @@ function generatechat!(a::T; maxattempt::Integer=10
       "action_name": "...",
       "action_input": "..."
     """
-  
+
   system_msg = Dict(
       "role" => "system",
       "content" => [
@@ -673,8 +768,7 @@ function generatechat!(a::T; maxattempt::Integer=10
     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
@@ -686,26 +780,17 @@ 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
+    else
+      println("\nERROR YiemAgent generatechat() $errornote --(not qualify response)> $responsedict ", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
+      continue
     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")
+      println("\nERROR YiemAgent generatechat() $errornote --(not qualify response)> $responsedict ", @__FILE__, ":", @__LINE__, " $(Dates.now())\n")
       continue
     end
 
@@ -717,9 +802,11 @@ function generatechat!(a::T; maxattempt::Integer=10
 
     # println("\nYiem decisionMaker() ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
     # pprintln(responsedict)
-
+    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/llmfunction.jl

@@ -2,9 +2,10 @@ module llmfunction
 
 export  virtualWineUserChatbox, jsoncorrection, search_wine_database!, # recommendbox,
         virtualWineUserRecommendbox, userChatbox, userRecommendbox, extractWineAttributes_1,
-        extractWineAttributes_2, paraphrase
+        extractWineAttributes_2, paraphrase, SQLexecution
 
-using HTTP, JSON, URIs, Random, PrettyPrinting, UUIDs, Dates, DataFrames, DataStructures
+using HTTP, JSON, URIs, Random, PrettyPrinting, UUIDs, Dates, DataFrames, DataStructures,
+      Base64, Serde
 using GeneralUtils, SQLLLM
 using ..type, ..util
 
@@ -211,7 +212,7 @@ pushfirst!(virtualCustomerChatHistory, Dict("name"=> "system", "text"=> systemms
     receiverName= "text2textinstruct",
     mqttBroker= config["mqttServerInfo"]["broker"],
     mqttBrokerPort= config["mqttServerInfo"]["port"],
-    msgId = string(uuid4()) #CHANGE remove after testing finished
+    msgId = string(uuid4()) # remove after testing finished
   )
 
   outgoingMsg = Dict(
@@ -276,21 +277,26 @@ end
 # Example
 ```jldoctest
 julia> using ChatAgent
-julia> agent = ChatAgent.agentReflex("Jene")
-julia> input = "{\"food\": \"pizza\", \"occasion\": \"anniversary\"}"
-julia> result = checkinventory(agent, input)
-"{"wine 1": {\"Winery\": \"Pichon Baron\", \"wine name\": \"Pauillac (Grand Cru Classé)\", \"grape variety\": \"Cabernet Sauvignon\", \"year\": 2010, \"price\": \"125 USD\", \"stock ID\": \"ar-17\"}, }"
+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")
 ```
 """
 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"])
 
   retrieve_attributes = ["winery", "wine_name", "wine_id", "vintage", "region", "country", "wine_type", "grape", "serving_temperature", "sweetness", "intensity", "tannin", "acidity", "tasting_notes", "price", "currency", "image_url", "retailer_name", "retailer_id"]
-  _inventoryquery = "$wineattributes_1, $wineattributes_2, retailer_name: $(a.retailername), retailerid: $(a.retailerid)"
+  _inventoryquery = "$(thoughtdict["action_input"]), $wineattributes_1, $wineattributes_2, retailer_name: $(a.retailername), retailerid: $(a.retailerid)"
   inventoryquery = "Retrieves $retrieve_attributes of wines that match the following criteria - {$_inventoryquery}"
   println("\ncheckinventory input: $inventoryquery ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
 
@@ -309,47 +315,33 @@ function search_wine_database!(a::T, thoughtdict::AbstractDict; useSQLLLM::Bool=
     # direct query with possible sql instead of SQLLLM. 
     sql = generatesql(a, inventoryquery)
     println("\nSQL: $sql ", @__FILE__, ":", @__LINE__, " $(Dates.now()) \n")
-    textresult, result_raw, _, _ = SQLexecution(a.context.executeSQL, sql)
-    #WORKING if result_raw != nothing, get image from image_url column of a df. 
-    # then store in a.memory["shortmem]["image"] = OrderedDict(
-    #   Dict(
-    #       "wine_id"=> "wine_id,
-    #       "name"=> "wine name",
-    #       "image_url" => Dict("url" => data1_uri)
-    #     )
- 
-    # )
-    
-
-    # # 1. Read local file and encode to base64 string
-    # image2_path = "test/small_image.png"
-    # image2_bytes = read(image2_path)
-    # image2_base64_string = base64encode(image2_bytes)
-    # mime_type = "image/png" 
-    # data2_uri = "data:$(mime_type);base64,$(image2_base64_string)"
-
-    # # 3. Construct payload with the Data URI
-    # message = Dict(
-    #     "role" => "user",
-    #     "content" => [
-    #       Dict("type" => "text", "text" => "Do you know type of wine in the image?"),
-    #       Dict(
-    #         "type" => "image_url",
-    #         "image_url" => Dict("url" => data1_uri)
-    #       )
-    #     ]
-    #   )
-
-
-
-
+    textresult, sql_result_df, success, _ = SQLexecution(a.context.executeSQL, sql)
 
+    items = nothing
+    if sql_result_df !== nothing
+      result_vec = GeneralUtils.dfToVectorDict(sql_result_df)
 
+      # get image
+      for d in result_vec
+        image_url_json_str = d["image_url"]
+        image_url_json_obj = JSON.parse(image_url_json_str)
+        base_url = "http://192.168.88.106:8080/"
+        if haskey(image_url_json_obj, "bottle")
+          url = base_url * image_url_json_obj["bottle"]
+          image_data = HTTP.get(url)  # vector{int} data
+          image_base64_string = base64encode(image_data.body)
+          d["image"] = image_base64_string
+        else
+          d["image"] = nothing
+        end
+      end
+      items = result_vec  # image is added to each item
+    end
 
     thoughtdict["action_result"] = textresult
   end
 
-  return (thoughtdict=thoughtdict, result_raw=result_raw)
+  return (thoughtdict=thoughtdict, result_raw=items)
 end
 
 
@@ -366,7 +358,7 @@ function generatesql(a::T, searchterm::String,
       - A junction table can be used to link tables together. Another use case is for filtering data.
       - If you can't find a single table that can be used to answer the user's search term, try joining multiple tables to see if you can obtain the answer.
       - Text information in the database usually stored in lower case. If your search returns empty, try using lower case to search.
-      - If there is no search result from the database, remove the restrictive criteria until a search result is available, and proceed from there.
+      - Overly strict condition usually yields empth result
 
     # situation
       At each round of conversation, you will be given the following:
@@ -379,9 +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.
-      2) "action_name, Must be "RUNSQL"
-      3) "action_input, The input to the action you are about to perform according to your plan.
+      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"
+      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
@@ -517,21 +509,21 @@ 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 +533,6 @@ 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
@@ -629,6 +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}
 
@@ -717,7 +927,6 @@ function extractWineAttributes_1(a::T1, input::T2; maxattempt=10
     wine_name: name of the wine
     winery: name of the winery
     vintage: the year of the wine
-    region: a region, such as Burgundy, Bordeaux, Champagne, Napa Valley, Tuscany, California, Oregon, etc. Use "or" if there are multiple regions.
     country: a country where wine is produced. Can be "Austria", "Australia", "France", "Germany", "Italy", "Portugal", "Spain", "United States". Use "or" if there are multiple countries.
     wine_type: can be one of: "red", "white", "sparkling", "rose", "dessert" or "fortified"
     grape_varietal: the name of the primary grape used to make the wine
@@ -726,13 +935,12 @@ function extractWineAttributes_1(a::T1, input::T2; maxattempt=10
     wine_price_max: maximum price range of wine. Example: For wine price 20, wine_price_max will be 20. For wine price 10 to 100, wine_price_max will be 100.
     occasion: the occasion the user is having the wine for
     food_to_be_paired_with_wine: food that the user will be served with the wine such as poultry, fish, steak, etc
-    _keyword suffice is the related keyword that appears in user's query. each keyword can not be used twice.
+    _keyword suffice is the related keyword that appears in user's query.
   </you should then respond to the user with>
   <you should only respond in JSON format as described below>
     "wine_name": "...",
     "winery": "...",
     "vintage": "...",
-    "region": "...",
     "country": "...",
     "wine_type": "...",
     "grape_varietal": "...",
@@ -747,7 +955,6 @@ function extractWineAttributes_1(a::T1, input::T2; maxattempt=10
       "wine_name": "N/A",
       "winery": "N/A",
       "vintage": "N/A",
-      "region": "Tuscany or Napa Valley",
       "country": "Italy or United States",
       "wine_type": "red or white",
       "grape_varietal": "Chenin Blanc or Riesling",
@@ -761,18 +968,17 @@ function extractWineAttributes_1(a::T1, input::T2; maxattempt=10
       "wine_name": "Saumur Blanc",
       "winery": "Domaine du Collier",
       "vintage": "2019",
-      "region": "Saumur",
       "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",
       "food_to_be_paired_with_wine": "N/A"
   </here are some examples>
   """
-  requiredKeys = ["wine_name", "winery", "vintage", "region", "country", "wine_type", "grape_varietal", "tasting_notes", "wine_price_min", "wine_price_max", "occasion", "food_to_be_paired_with_wine"]
+  requiredKeys = ["wine_name", "winery", "vintage", "country", "wine_type", "grape_varietal", "tasting_notes", "wine_price_min", "wine_price_max", "occasion", "food_to_be_paired_with_wine"]
   errornote = ""
   context = 
   """
@@ -833,15 +1039,17 @@ function extractWineAttributes_1(a::T1, input::T2; maxattempt=10
       responsedict[k] = _v
     end
 
-    # println("\n--- extractWineAttributes_1-1()")
-    # @show responsedict
-    # @info "---\n" @__LINE__
+    @info "YiemAgent extractWineAttributes_1() " @__LINE__
+    @show responsedict
+    @info "---\n" @__LINE__
 
     # 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)
-      resolved_word = GeneralUtils.resolve_entity(v, words_catalog;threshold=0.9)
-      responsedict[k] = resolved_word
+      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 = ""
@@ -853,10 +1061,11 @@ function extractWineAttributes_1(a::T1, input::T2; maxattempt=10
     end
 
     result = result[1:end-2]  # remove the ending ", "
-    # println("\n--- extractWineAttributes_1-2()")
-    # @show responsedict
-    # @show result
-    # @info "---\n" @__LINE__
+
+    @info "YiemAgent extractWineAttributes_1() " @__LINE__
+    @show result
+    @info "---\n" @__LINE__
+
     return result
   end
   error("extractWineAttributes_1() failed to get a response")
@@ -1009,9 +1218,6 @@ function extractWineAttributes_2(a::T1, input::T2)::String where {T1<:agent, T2<
   for attempt in 1:10
     response = a.context.text2textInstructLLM(a.id, msg)
     response = GeneralUtils.clean_json_response(response)
-    println("\n--- extractWineAttributes_2-1()")
-    println(response)
-    println("--- \n")
 
     response = GeneralUtils.remove_french_accents(response)
     think, response = GeneralUtils.extractthink(response)
@@ -1049,9 +1255,11 @@ function extractWineAttributes_2(a::T1, input::T2)::String where {T1<:agent, T2<
       end
     end
     result = result[1:end-2]  # remove the ending ", "
-    println("\n--- extractWineAttributes_2-2()")
-    println(result)
-    println("--- \n")
+
+    @info "YiemAgent extractWineAttributes_2() " @__LINE__
+    @show result
+    @info "---\n" @__LINE__
+
     return result
   end
   error("extractWineAttributes_2() failed to get a response")

src/type.jl

@@ -252,6 +252,7 @@ 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.
@@ -285,10 +286,10 @@ function sommelier(
 
     # 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.
-      "SEARCH_WINE_DATABASE", allows you to search information about wines you want in your inventory's database. The input is supported search criteria including: 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."
+      "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
+        Example query 3: "white wine from Tuscany, Italy or Bordeaux, 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.
     """