update

src/llmfunction.jl

@@ -481,20 +481,9 @@ julia> response = SQLLLM.SQLexecution(executeSQL, sql)
 # Signature
 """
 function SQLexecution(executeSQL::Function, sql::T
-) where {T<:AbstractString}
+  )::NamedTuple where {T<:AbstractString}
 
   try
-    #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)
 
@@ -508,39 +497,36 @@ function SQLexecution(executeSQL::Function, sql::T
     else
       sql = sql * ";"
     end
-    println("\n~~~ SQLexecution() SQL: ", @__FILE__, " ", @__LINE__)
-    println(sql)
-
     result = executeSQL(sql)
     df = DataFrame(result)
-
     tablesize = size(df)
     row, column = tablesize
     if row == 0
-      error("\nThe resulting table has 0 row. Please try again.")
-    elseif column > 50
-      error("\nSQL execution success but there are more than 50 rows Please be more specific.")
+      return (result_str="The resulting table has 0 row.", result_raw=df, success=true, errormsg=nothing)
+    elseif column > 30
+      return (result_str="There are more than 30 columns. Please be more specific.", result_raw=df, success=true, errormsg=nothing)
+    else
+      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
+      result = GeneralUtils.dfToString(df1)
+      println("\n~~~ SQLexecution() result: ", @__FILE__, " ", @__LINE__)
+      println(sql)
+      println(df1)
+      println("\n")
+      return (result_str=result, result_raw=df1, success=true, errormsg=nothing)
     end
-
-    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)
   catch e
     io = IOBuffer()
     showerror(io, e)
     errorMsg = String(take!(io))
     st = sprint((io, v) -> show(io, "text/plain", v), stacktrace(catch_backtrace()))
     println(errorMsg)
-    response = (result=nothing, success=false, errormsg=errorMsg)
-    return response
+    return (result_str=nothing, result_raw=nothing, success=false, errormsg=errorMsg)
   end
 end
 
@@ -559,7 +545,7 @@ end
   - `result::String`
 
 # Signature
-"""
+""" #WORKING
 function extractContent_dataframe(df::DataFrame, text2textInstructLLM::Function, action::String,
   llmFormatName::String
   )::String
@@ -633,7 +619,7 @@ function extractContent_dataframe(df::DataFrame, text2textInstructLLM::Function,
   dictkey = ["about_resulting_table", "search_summary"]
 
   for i in 1:5
-    response = text2textInstructLLM(prompt, modelsize="medium")
+    response = text2textInstructLLM("ramdom_id", prompt)
     response = GeneralUtils.deFormatLLMtext(response, llmFormatName)
     think, response = GeneralUtils.extractthink(response)
 
@@ -653,7 +639,6 @@ function extractContent_dataframe(df::DataFrame, text2textInstructLLM::Function,
     responsedict = GeneralUtils.textToDict(response, header; 
                                             dictKey=dictkey, symbolkey=false)
 
-    # result = dfstr
     result = 
     """
     Summary: $(responsedict["search_summary"])