From a4227ec165b562dc3bc29ab74338aada6d04fe68 Mon Sep 17 00:00:00 2001
From: narawat <narawat@gmail.com>
Date: Wed, 23 Jul 2025 18:31:38 +0700
Subject: [PATCH] update

---
 src/interface.jl   | 15 ++++++++-------
 src/llmfunction.jl | 42 ++++++++++++++++++++++--------------------
 2 files changed, 30 insertions(+), 27 deletions(-)

diff --git a/src/interface.jl b/src/interface.jl
index 501e6f5..debdae0 100644
--- a/src/interface.jl
+++ b/src/interface.jl
@@ -694,14 +694,15 @@ function evaluator(state::T1, thoughtDict, text2textInstructLLM::Function, llmFo
     response = replace(response, "***"=>"")
 
     # check whether response has all header
-    detected_kw = GeneralUtils.detect_keyword(header, response)
-    if 0 ∈ values(detected_kw)
-      errornote = "Your previous attempt does not have all answer points"
-      println("\nERROR SQLLLM evaluator() Attempt $attempt/$maxattempt. $errornote ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+    detected_kw = GeneralUtils.detectKeywordVariation(header, response)
+    missingkeys = [k for (k, v) in detected_kw if v === nothing]
+    if !isempty(missingkeys)
+      errornote = "$missingkeys are missing from your previous response"
+      println("\nERROR SQLLLM extractContent_dataframe() $errornote ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
       continue
-    elseif sum(values(detected_kw)) > length(header)
-      errornote = "Your previous attempt has duplicated answer point"
-      println("\nERROR SQLLLM evaluator() Attempt $attempt/$maxattempt. $errornote ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+    elseif sum([length(i) for i in values(detected_kw)]) > length(header)
+      errornote = "\nYour previous attempt has duplicated points according to the required response format"
+      println("\nERROR SQLLLM extractContent_dataframe() $errornote ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
       continue
     end
 
diff --git a/src/llmfunction.jl b/src/llmfunction.jl
index 0ac9018..641c317 100644
--- a/src/llmfunction.jl
+++ b/src/llmfunction.jl
@@ -637,15 +637,17 @@ function extractContent_dataframe(df::DataFrame, text2textInstructLLM::Function,
     response = GeneralUtils.deFormatLLMtext(response, llmFormatName)
     think, response = GeneralUtils.extractthink(response)
 
-    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__, " $(Dates.now())")
-      continue  # try again next loop
+    # check whether response has all header
+    detected_kw = GeneralUtils.detectKeywordVariation(header, response)
+    missingkeys = [k for (k, v) in detected_kw if v === nothing]
+    if !isempty(missingkeys)
+      errornote = "$missingkeys are missing from your previous response"
+      println("\nERROR SQLLLM extractContent_dataframe() $errornote ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+      continue
+    elseif sum([length(i) for i in values(detected_kw)]) > length(header)
+      errornote = "\nYour previous attempt has duplicated points according to the required response format"
+      println("\nERROR SQLLLM extractContent_dataframe() $errornote ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+      continue
     end
 
     responsedict = GeneralUtils.textToDict(response, header; 
@@ -929,17 +931,17 @@ function compareState(question::String, highValueStateList::Vector{T},
     response = GeneralUtils.deFormatLLMtext(response, llmFormatName)
     think, response = GeneralUtils.extractthink(response)
 
-    # make sure every header is in the response
-    for i in header
-      detected = GeneralUtils.detect_keyword(i, response)
-      if detected === nothing
-        errornote = "Your previous attempt didn't provide $i"
-        errorFlag = true
-      end
-    end
-    if errorFlag  
-      println("\nERROR SQLLLM compareState() Attempt $attempt $errornote ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
-      continue  # skip to the next iteration
+    # check whether response has all header
+    detected_kw = GeneralUtils.detectKeywordVariation(header, response)
+    missingkeys = [k for (k, v) in detected_kw if v === nothing]
+    if !isempty(missingkeys)
+      errornote = "$missingkeys are missing from your previous response"
+      println("\nERROR SQLLLM extractContent_dataframe() $errornote ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+      continue
+    elseif sum([length(i) for i in values(detected_kw)]) > length(header)
+      errornote = "\nYour previous attempt has duplicated points according to the required response format"
+      println("\nERROR SQLLLM extractContent_dataframe() $errornote ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+      continue
     end
 
     responsedict = GeneralUtils.textToDict(response, header; dictKey=dictkey, symbolkey=true)