Update kadi_apy_bot.py

kadi_apy_bot.py

@@ -15,25 +15,25 @@ class KadiAPYBot:
         Process a user query, handle history, retrieve contexts, and generate a response.
         """
         # Add the user query to the conversation history
-        #self.add_to_conversation(user_query=query)
+        self.add_to_conversation(user_query=query)
         
         # Rewrite query
-    #    rewritten_query = self.rewrite_query(query)
+        rewritten_query = self.rewrite_query(query)
 
         # Predict library usage
-    #    code_library_usage_prediction = self.predict_library_usage(query)
+        code_library_usage_prediction = self.predict_library_usage(query)
         
         # Retrieve contexts
-    #    doc_contexts = self.retrieve_contexts(query, k=3, filter={"usage": "doc"})
-    #    code_contexts = self.retrieve_contexts(rewritten_query, k=5, filter={"usage": code_library_usage_prediction})
+        doc_contexts = self.retrieve_contexts(query, k=3, filter={"usage": "doc"})
+        code_contexts = self.retrieve_contexts(rewritten_query, k=5, filter={"usage": code_library_usage_prediction})
 
 
         # Vanilla
         doc_contexts = self.retrieve_contexts(query, k=3, filter={"directory": "doc/"})
         code_contexts = self.retrieve_contexts(query, k=5, filter={"directory": "kadi_apy/"})
 
-    #    doc_contexts = self.retrieve_contexts(query, k=3, filter={"folder": "doc/"})
-    #    code_contexts = self.retrieve_contexts(rewritten_query, k=5, filter={"folder": "kadi_apy/"})
+        doc_contexts = self.retrieve_contexts(query, k=3, filter={"folder": "doc/"})
+        code_contexts = self.retrieve_contexts(rewritten_query, k=5, filter={"folder": "kadi_apy/"})
         
         
         # Format contexts
@@ -159,21 +159,28 @@ class KadiAPYBot:
         """
         Generate a response using the retrieved contexts and the LLM.
         """
-        prompt = f"""You are an expert python developer assisting in generating code for users.
-                        
-                    Your task is to generate Python scripts that fullfills the user's query based on the provided "Document snippets", "Code Snippets" and guidelines  
-                        
-                    Guidelines when generating code:
-                    - Display the complete code first, followed by a concise explanation in no more than 5 sentences.
-                    
-                    - If the user's query can not be fullfilled based on the provided snippets, reply with "The API does not support the requested functionality"
+
+
+        prompt = f"""You are a Python programming assistant specialized in the "Kadi-APY" library. 
+                     The "Kadi-APY" library is a Python package designed to facilitate interaction with the REST-like API of a software platform called Kadi4Mat. 
+                     Your task is to generate Python scripts that address the user's query based on the guidelines and the combine understanding provided by 
+                     "Document snippets" with the implementation details provided by "Code Snippets."
+
+                     Guidelines when generating code:
+                        - Display the complete code first, followed by a concise explanation in no more than 5 sentences.
                     
-                Document snippets:
-                {doc_context}
-                Code Snippets:
-                {code_context}
-                
-                Query: 
-                {query}
-        """
+                        - If the user's query can not be fullfilled based on the provided snippets, reply with "The API does not support the requested functionality"
+                     
+                    "Document Snippets": These contain documentation excerpts and code examples that explain how to use the "Kadi-APY" library
+                    Document Snippets:
+                    {doc_context}
+
+
+                    "Code Snippets": These are raw source code fragments from the implementation of the "Kadi-APY" library.
+                    Code Snippets:
+                    {code_context}
+        
+                    Query:
+                    {query}
+                """
         return self.llm.invoke(prompt).content