update

src/interface.jl

@@ -217,7 +217,7 @@ function decisionMaker(state::T1, context, text2textInstructLLM::Function,
 
     # put in model format
     prompt = GeneralUtils.formatLLMtext(_prompt; formatname="qwen")
-    response = text2textInstructLLM(prompt)
+    response = text2textInstructLLM(prompt) #BUG response === nothing
 
     # LLM tends to generate observation given that it is in the input
     response = 
@@ -812,7 +812,7 @@ function evaluator(state::T1, text2textInstructLLM::Function;
       question: Find cars with a stereo.
       observation: There are 1 cars in the table. 1) brand: Toyota, model: yaris, color: black.
   4) Score: Correctness score s where s is a single integer between 0 to 9. 
-      Score guideline:
+      For example:
       - 0 indicates that both the trajectory is incorrect, failed or errors and the observation is incorrect or failed
       - 4 indicates that the trajectory are correct but the observation is incorrect or failed
       - 8 indicates that both the trajectory are correct, and the observation's content directly answers the question.
@@ -1034,7 +1034,7 @@ function reflector(config::T1, state::T2)::String where {T1<:AbstractDict, T2<:A
       )
     )
 
-  for attempt in 1:5
+  for attempt in 1:10
     try
       response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg)
       _responseJsonStr = response[:response][:text]
@@ -1280,7 +1280,8 @@ function query(query::T, executeSQL::Function, text2textInstructLLM::Function;
   _, _, resultState = LLMMCTS.runMCTS(initialstate, transition, transitionargs;
                       horizontalSampleExpansionPhase=3, 
                       horizontalSampleSimulationPhase=2,
-                      maxSimulationDepth=5, maxiterations=2, 
+                      maxSimulationDepth=10, 
+                      maxiterations=1, 
                       explorationweight=1.0,
                       earlystop=earlystop,
                       saveSimulatedNode=true)

src/llmfunction.jl

@@ -403,10 +403,8 @@ function getdata_decisionMaker(state::Dict, context::Dict, text2textInstructLLM:
               - Text information in the database is sometimes stored in lower case. If your search returns empty, try using lower case to search.
 
               You should then respond to the user with:
-              1) Understanding: 
+              1) Comprehension: 
-                    - State your understanding about the current situation.
+                  - State your comprehension about the current situation.
-              2) Reasoning: 
-                  - State your step by step reasoning about the current situation.
               3) Plan: Step-by-step instructions of how to complete the task.
                   - Focus on improving the code from the last round.
                   - Do not create any table in the database.
@@ -415,8 +413,7 @@ function getdata_decisionMaker(state::Dict, context::Dict, text2textInstructLLM:
                   - Do not wrap the code and no comment as it will be executed directly without any modification against the database.
 
               You should only respond in format as described below and nothing more:
-              Understanding: ...
+              Comprehension: ...
-              Reasoning: ...
               Plan: 
                 1) ...
                 2) ... 
@@ -446,15 +443,15 @@ function getdata_decisionMaker(state::Dict, context::Dict, text2textInstructLLM:
       ]
 
     # put in model format
-    prompt = GeneralUtils.formatLLMtext(_prompt; formatname="llama3instruct")
+    prompt = GeneralUtils.formatLLMtext(_prompt; formatname="qwen")
-    prompt *= """
-              <|start_header_id|>assistant<|end_header_id|>
-              """
     try
       response = text2textInstructLLM(prompt)
-      responsedict = GeneralUtils.textToDict(response,
+
-        ["Understanding", "Reasoning", "Plan", "Code"];
+      header = ["Comprehension:", "Plan:", "Code:"]
-        rightmarker=":", symbolkey=true, lowercasekey=true)
+      dictkey = ["comprehension", "plan", "code"]
+
+      responsedict = GeneralUtils.textToDict(response, header; 
+                                            dictKey=dictkey, symbolkey=true)
       _code = responsedict[:code]
       code = strip(_code)
 
@@ -480,7 +477,7 @@ function getdata_decisionMaker(state::Dict, context::Dict, text2textInstructLLM:
 
       println("\n~~~ getdata_decisionMaker() ", @__FILE__, " ", @__LINE__)
       pprintln(Dict(responsedict))
-      return (thought=responsedict[:reasoning], code=code, success=true, errormsg=nothing)
+      return (thought=responsedict[:comprehension], code=code, success=true, errormsg=nothing)
     catch e
       io = IOBuffer()
       showerror(io, e)
@@ -631,29 +628,30 @@ function extractContent_dataframe(df::DataFrame, text2textInstructLLM::Function
 
   dfstr = GeneralUtils.dfToString(df1)
 
-  systemmsg = """
+  systemmsg = 
-              You are an assistant that readouts the resulting table after the user executing SQL command.
+  """
+  You are an assistant that readouts the resulting table after the user executing SQL command.
 
-              At each round of conversation, the user will give you:
+  At each round of conversation, the user will give you:
-              - User intention: ...
+  - User intention: ...
-              - Resulting table dimension: ...
+  - Resulting table dimension: ...
-              - Resulting table: The resulting table after executing the user's intention.
+  - Resulting table: The resulting table after executing the user's intention.
 
-              You should then respond to the user with:
+  You should then respond to the user with:
-              - About_resulting_table:
+  - About_resulting_table:
-                  1) What is the resulting table represent?
+      1) What is the resulting table represent?
-              - Search_summary:
+  - Search_summary:
-                  1) Summarize the table's content based on the user intension in verbal English.
+      1) Summarize the table's content based on the user intension in verbal English.
-                    Here are some example:
+        Here are some example:
-                    Bad example (you are not Summarize the table content): there are 2 columns in the table i.e. "cash" and "number".
+        Bad example (you are not Summarize the table content): there are 2 columns in the table i.e. "cash" and "number".
-                  2) Do not generate additional text.
+      2) Do not generate additional text.
 
-              You should only respond in format as described below:
+  You should only respond in format as described below:
-              About_resulting_table: ...
+  About_resulting_table: ...
-              Search_summary: ...
+  Search_summary: ...
 
-              Let's begin!
+  Let's begin!
-              """
+  """
   usermsg = """
             Resulting table: $dfstr
             """
@@ -664,20 +662,33 @@ function extractContent_dataframe(df::DataFrame, text2textInstructLLM::Function
     ]
 
   # put in model format
-  prompt = GeneralUtils.formatLLMtext(_prompt; formatname="llama3instruct")
+  prompt = GeneralUtils.formatLLMtext(_prompt; formatname="qwen")
-  prompt *= """
+  header = ["About_resulting_table:", "Search_summary:"]
-            <|start_header_id|>assistant<|end_header_id|>
+  dictkey = ["about_resulting_table", "search_summary"]
-            """
+
   for i in 1:5
     response = text2textInstructLLM(prompt)
-    responsedict = GeneralUtils.textToDict(response, ["About_resulting_table", "Search_summary"],
+
-      rightmarker=":", symbolkey=true)
+    kw = []
+    # use for loop and detect_keyword function to get the exact variation of each keyword in the text then push to kw list
+    for keyword in header
+      detected = GeneralUtils.detect_keyword(keyword, response)
+      push!(kw, detected)
+    end
+    if nothing ∈ kw
+      println("Some keywords are missing, Required keywords=$header, Response keywords=$kw ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+      continue  # try again next loop
+    end
+
+    responsedict = GeneralUtils.textToDict(response, header; 
+                                            dictKey=dictkey, symbolkey=true)
 
     # result = dfstr
-    result = """
+    result = 
-             Summary: $(responsedict[:Search_summary]) 
+    """
-             More details: $dfstr
+    Summary: $(responsedict[:search_summary]) 
-             """
+    More details: $dfstr
+    """
 
     if row > 2
       result *= "There are many more rows, but they are truncated because there are too many of them."
@@ -766,11 +777,11 @@ function getTableNameFromSQL(sql::T, text2textInstructLLM::Function)::Vector{Str
               Query: ...
 
               You should then respond to the user with:
-              - table_name: a list of table name that the user mentioned in the query. 
+              - Table_name: a list of table name that the user mentioned in the query. 
                   For example, ["color", "type"]
 
               You must only respond in format as described below:
-              table_name: ["...", "...", ...]
+              Table_name: ["...", "...", ...]
 
               Let's begin!
               """
@@ -786,17 +797,15 @@ function getTableNameFromSQL(sql::T, text2textInstructLLM::Function)::Vector{Str
     ]
 
   # put in model format
-  prompt = GeneralUtils.formatLLMtext(_prompt; formatname="llama3instruct")
+  prompt = GeneralUtils.formatLLMtext(_prompt; formatname="qwen")
-  prompt *= """
+  header = ["Table_name:"]
-            <|start_header_id|>assistant<|end_header_id|>
+  dictkey = ["table_name"]
-            """
 
   for attempt in 1:5
     try
       response = text2textInstructLLM(prompt)
-      responsedict = GeneralUtils.textToDict(response,
+      responsedict = GeneralUtils.textToDict(response, header; 
-        ["table_name"],
+                                            dictKey=dictkey, symbolkey=true)
-        rightmarker=":", symbolkey=true)
       response = copy(JSON3.read(responsedict[:table_name]))
 
       return response

test/runtest.jl

@@ -51,7 +51,7 @@ function text2textInstructLLM(prompt::String)
     )
   )
 
-  _response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg; timeout=120, maxattempt=3)
+  _response = GeneralUtils.sendReceiveMqttMsg(outgoingMsg; timeout=120, maxattempt=2)
   response = _response[:response][:text]
 
   return response
@@ -147,10 +147,10 @@ sessionId = "555"
 
 # query = Dict(:text=> "How many wines from France do you have that can be paired with lamb?")
 # query = "How many wines are from United States?"
-# query = "retailer: Yiem, wine_type: red, sweetness: 1-2, intensity: 4-5, wine price: 20-40"
+query = "retailer: Yiem, wine_type: red, sweetness: 1-2, intensity: 4-5, wine price: 20-40"
 # query = "wine_type: white, country: United States, sweetness: 1-2, tannin: 3, food to be served with wine: pizza"
 # query = "wine_type: white, country: Austria, food to be served with wine: pork"
-query = "wine price: less than 25, wine_type: rose, country: France, sweetness: 2, tannin: 3, food to be served with wine: pizza"
+# query = "wine price: less than 25, wine_type: rose, country: France, sweetness: 2, tannin: 3, food to be served with wine: pizza"
 # query = Dict(:text=> "wine_type: white, country: France, sweetness: 1")
 result = SQLLLM.query(query, executeSQL, text2textInstructLLM;
                       insertSQLVectorDB=insertSQLVectorDB,