Merge pull request 'WIP v0.2.2-dev' (#1) from v0.2.2-dev into main

Reviewed-on: #1

Project.toml

@@ -1,7 +1,7 @@
 name = "SQLLLM"
 uuid = "2ebc79c7-cc10-4a3a-9665-d2e1d61e63d3"
 authors = ["narawat lamaiin <narawat@outlook.com>"]
-version = "0.2.1"
+version = "0.2.2"
 
 [deps]
 CSV = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
@@ -23,5 +23,5 @@ URIs = "5c2747f8-b7ea-4ff2-ba2e-563bfd36b1d4"
 UUIDs = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
 
 [compat]
-GeneralUtils = "0.1.0"
+GeneralUtils = "0.1, 0.2"
-LLMMCTS = "0.1.2"
+LLMMCTS = "0.1"

src/interface.jl

@@ -149,7 +149,6 @@ function decisionMaker(state::T1, context, text2textInstructLLM::Function,
 
     You should follow the following guidelines:
     - Do not create any table in the database
-    - Column name can be the same in different tables. Refer to column comments to get more details by using TABLEINFO function
     - 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 query, try joining multiple tables to see if you can obtain the answer.
     - If you are unable to find the requested information, kindly inform the user, "The current data in our database does not provide the specific answer to your query".
@@ -162,8 +161,7 @@ function decisionMaker(state::T1, context, text2textInstructLLM::Function,
         - State your step by step reasoning about the current situation.
     3) Plan: Given the current circumstances, outline a detailed, step-by-step plan to accomplish the task. Be specific.
     4) Action_name (Must be aligned with your plan): Can be one of the following functions: 
-        - TABLEINFO[list_of_table_name], which you can use to get the data type of a table column. "list_of_table_name" is a list of table name you want to get info. e.g. TABLEINFO["table name 1", "table name 2"]
+        - GETDATA, which you can use to get the data from the database. Action_input for this function must be a single SQL query to be executed against the database.
-        - GETDATA[SQL], which you can use to get the data from the database. "SQL" is a single SQL command to be executed against the database.
           For more effective text search, it's necessary to use case-insensitivity and the ILIKE operator.
           Do not wrap the SQL as it will be executed against the database directly and SQL must be ended with ';'.
     5) Action_input: Input to the action
@@ -224,18 +222,31 @@ function decisionMaker(state::T1, context, text2textInstructLLM::Function,
       """
       <|start_header_id|>assistant<|end_header_id|>
       """
-
-    try
     response = text2textInstructLLM(prompt)
-      println("\nSQL decisionMaker() rawresponse: ", response)
+    println("\nSQL decisionMaker() rawresponse: \n", response)
+
+    if occursin("NULL", response)
+      errornote = "\nSQL decisionMaker() NULL response is not allowed"
+      println("Attempt $attempt $errornote ", @__FILE__, " ", @__LINE__)
+      continue
+    end
 
     header = ["Understanding", "Reasoning", "Plan", "Action_name", "Action_input", "Observation"]
 
     # detect if there are more than 1 key per categories
     count = GeneralUtils.countGivenWords(response, header)
-      if sum(count) > length(header)
+    duplicateKeywordFlag = false
-        error("\nSQL decisionMaker() duplicated keywords", @__FILE__, " ", @__LINE__)
+    for (i, v) in enumerate(count)
+      keyword = header[i]
+      keywordNumber = v
+      if keywordNumber > 1
+        errornote = "\nSQL query has duplicated keyword, $keyword"
+        println("Attempt $attempt $errornote ", @__FILE__, " ", @__LINE__)
+        duplicateKeywordFlag = true
+        break
       end
+    end
+    duplicateKeywordFlag == true ? continue : nothing
 
     # textToDict() search for action_input
     responsedict = GeneralUtils.textToDict(response, header, 
@@ -257,18 +268,24 @@ function decisionMaker(state::T1, context, text2textInstructLLM::Function,
 
     toollist = ["TABLEINFO", "GETDATA"]
     if responsedict[:action_name] ∉ toollist
-        error("SQL decisionMaker() didn't use the given functions ", @__FILE__, " ", @__LINE__)
+      errornote = "\nYou must only use the given functions"
+      println("Attempt $attempt $errornote ", @__FILE__, " ", @__LINE__)
+      continue
     end
 
     for i in toollist
       if occursin(i, responsedict[:action_input])
-          error("Action_name is in action_input which is not allowed.")
+        errornote = "\n action_name is in action_input which is not allowed."
+        println("Attempt $attempt $errornote ", @__FILE__, " ", @__LINE__)
+        continue
       end
     end
 
     for i ∈ [:understanding, :reasoning, :plan, :action_name, :action_input]
       if length(JSON3.write(responsedict[i])) == 0
-          error("$i is empty ", @__FILE__, " ", @__LINE__)
+        errornote = "\n $i is empty"
+        println("Attempt $attempt $errornote ", @__FILE__, " ", @__LINE__)
+        continue
       end
     end
 
@@ -276,22 +293,15 @@ function decisionMaker(state::T1, context, text2textInstructLLM::Function,
     for i ∈ [:understanding, :reasoning, :plan, :action_name, :action_input]
       matchkeys = GeneralUtils.findMatchingDictKey(responsedict, i)
       if length(matchkeys) > 1
-          error("DecisionMaker has more than one key per categories")
+        errornote = "\n $i has more than one key"
+        println("Attempt $attempt $errornote ", @__FILE__, " ", @__LINE__)
+        continue
       end
     end
 
     state[:decisionMaker] = responsedict
 
     return responsedict
-    catch e
-      io = IOBuffer()
-      showerror(io, e)
-      errorMsg = String(take!(io))
-      st = sprint((io, v) -> show(io, "text/plain", v), stacktrace(catch_backtrace()))
-      println("")
-      println("\n~~~ SQLLLM decisionMaker() Attempt $attempt. Error occurred: $errorMsg\n$st ", @__FILE__, " ", @__LINE__)
-      println("")
-    end
 
   end
   error("DecisionMaker failed to generate a thought ", response)
@@ -462,8 +472,9 @@ function evaluator(state::T1, text2textInstructLLM::Function;
   "reasoning" is agent's step-by-step reasoning about the current situation
   "plan" is agent's plan to complete the task from the current situation
   "action_name" is the name of the action taken, which can be one of the following functions:
-      - TABLEINFO[list_of_table_name], which you can use to get the data type of a table column. "list_of_table_name" is a list of table name you want to get info. e.g. TABLEINFO["table name 1", "table name 2"]
+      - GETDATA, which you can use to get the data from the database. Action_input for this function must be a single SQL query to be executed against the database.
-      - GETDATA[SQL], which you can use to get the data from the database. "SQL" is the single SQL command to be executed against the database.
+          For more effective text search, it's necessary to use case-insensitivity and the ILIKE operator.
+          Do not wrap the SQL as it will be executed against the database directly and SQL must be ended with ';'.
   "action_input" is the input to the action
   "observation" is result of the preceding immediate action
 
@@ -797,7 +808,7 @@ function transition(state::T, args::NamedTuple
       # so that other simulation start from this same node is not contaminated with actioninput
       listAllTable_json(executeSQL)
     elseif thoughtDict[:action_name] == "TABLEINFO"
-      input = copy(JSON3.read(thoughtDict[:action_input]))
+      input = thoughtDict[:action_input]  # BUG thoughtDict[:action_input] = "\"wine\""
       tableinfo(executeSQL, input)
     elseif thoughtDict[:action_name] == "GETDATA"
       response = SQLexecution(executeSQL, thoughtDict[:action_input])
@@ -967,6 +978,10 @@ function query(query::T, executeSQL::Function, text2textInstructLLM::Function;
     insertSQLVectorDB(resultState[:thoughtHistory][:question], sql)
   end
 
+  if extracted === nothing  #BUG
+    println("query() return nothing")
+  end
+
   return (text=extracted, rawresponse=resultState[:rawresponse]) 
 end
 

src/llmfunction.jl

@@ -520,65 +520,6 @@ julia> response = SQLLLM.SQLexecution(executeSQL, sql)
 
 # Signature
 """
-# function SQLexecution(executeSQL::Function, sql::T
-#   )::NamedTuple{(:result, :success, :errormsg, :reward, :isterminal), Tuple{Union{DataFrame, Nothing}, Bool, Union{String, Nothing}, Integer, Bool}} where {T<:AbstractString}
-#   println("\n~~~ 1-01 ", @__FILE__, " ", @__LINE__) 
-#   #XXX dummy SQL. use for testing
-#   # sql = "SELECT w.wine_name FROM wine w JOIN wine_food wf ON w.wine_id = wf.wine_id JOIN food f ON wf.food_id = f.food_id WHERE f.\"food_name\" = 'lamb';"
-#   # sql = " SELECT      w.wine_name FROM      wine w JOIN      food f ON f.food_name = 'lamb' JOIN      wine_food wf ON w.wine_id = wf.wine_id AND f.food_id = wf.food_id GROUP BY      w.wine_name ORDER BY      COUNT(DISTINCT w.wine_id) DESC;"
-#   # sql = " SELECT COUNT(DISTINCT wf.wine_id) FROM wine w JOIN wine_food wf ON w.wine_id = wf.wine_id JOIN food f ON wf.food_id = f.food_id WHERE f.food_name ILIKE '%lamb%'"
-
-#   #XXX use for package testing, remove when done
-#   # ans = "1.schilfwein zweigelt 2.cabernet sauvignon reserve limited edition"
-#   # ans = "There are 1500 wines that can be paired with lamb."
-#   # ans = "1500"
-#   # return (response=ans, errormsg=nothing, reward=1, isterminal=true)
-
-#   # add LIMIT to the SQL to prevent loading large data
-#   sql = strip(sql)
-#   println("\n~~~ SQL 1", @__FILE__, " ", @__LINE__)
-#   println(sql)
-#   println("\n~~~ 1-02 ", @__FILE__, " ", @__LINE__) 
-
-#   if sql[end] != ';'
-#     errorMsg = "Error, SQL execution failed because it does not ended with ';'"
-#     return (result=nothing, success=false, errormsg=errorMsg, reward=0, isterminal=false)
-#   end
-#   println("\n~~~ 1-03 ", @__FILE__, " ", @__LINE__) 
-#   if !occursin("LIMIT", sql)
-#     # sql = sql[1:end-1] * " LIMIT 100;"
-#     sql = sql[1:end-1] * " ORDER BY RANDOM() LIMIT 2;"
-#   end
-
-#   println("\n~~~ SQL 2", @__FILE__, " ", @__LINE__)
-#   println(sql)
-#   println("\n~~~ 1-1 ", @__FILE__, " ", @__LINE__) 
-#   result = executeSQL(sql)
-#   println("\n~~~ 1-2 ", @__FILE__, " ", @__LINE__) 
-#   df = DataFrame(result)
-#   println("\n~~~ raw df ", df)
-#   tablesize = size(df)
-#   println("\n~~~ df size ", tablesize)
-#   println("\n~~~ 6 ", @__FILE__, " ", @__LINE__) 
-#   row = tablesize[1]
-#   println("\n~~~ 7 ", @__FILE__, " ", @__LINE__) 
-#   if row == 0  # if 0 row
-#     errorMsg = "The resulting table has 0 row. Possible causes: 1) SQL is incorrect 2) There is no data that match your search criteria."
-#     return (result=nothing, success=false, errormsg=errorMsg, reward=0, isterminal=false)
-#   end
-#   println("\n~~~ 8 ", @__FILE__, " ", @__LINE__) 
-#   df1 =   
-#     if row > 2
-#       # ramdom row to pick
-#       df[sample(1:nrow(df), 2, replace=false), :] # random select 2 rows from df
-#     else
-#       df
-#     end
-
-#   println("\n~~~ SQLexecution result ", @__FILE__, " ", @__LINE__)   
-#   println(df1)
-#   return (result=df1, success=true, errormsg=nothing, reward=1, isterminal=true)
-# end
 function SQLexecution(executeSQL::Function, sql::T
 ) where {T<:AbstractString}
 
@@ -596,9 +537,12 @@ function SQLexecution(executeSQL::Function, sql::T
 
     # add LIMIT to the SQL to prevent loading large data
     sql = strip(sql)
+
+    # remove DISTINCT keyword because it is incompatible with RANDOM()
+    sql = replace(sql, "DISTINCT" => "")  
+
     if sql[end] == ';'
       if !occursin("LIMIT", sql)
-        # sql = sql[1:end-1] * " LIMIT 100;"
         sql = sql[1:end-1] * " ORDER BY RANDOM() LIMIT 2;"
       end
     else