Update kadi_apy_bot.py

kadi_apy_bot.py

@@ -10,7 +10,7 @@ class KadiAPYBot:
 
 
 
-    def process_query(self, query, chat_history):
+ #   def process_query(self, query, chat_history):
         """
         Process a user query, handle history, retrieve contexts, and generate a response.
         """
@@ -48,7 +48,44 @@ class KadiAPYBot:
         
         return response
 
+    def process_query(self, query):
+        """
+        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)
+        
+        # Rewrite query
+        rewritten_query = self.rewrite_query(query)
+        print("RRRRRRRRRREEEEEEEEEEWRITEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEE: ",rewritten_query)
+        # Predict library usage
+        code_library_usage_prediction = self.predict_library_usage(query)
+        
+        # Retrieve contexts
+        doc_contexts = self.retrieve_contexts(query, k=3, filter={"directory": "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={"directory": "doc/"})
+      #  code_contexts = self.retrieve_contexts(rewritten_query, k=5, filter={"directory": "kadi_apy/"})
+        
+        
+        # Format contexts
+        formatted_doc_contexts = self.format_documents(doc_contexts)
+        formatted_code_contexts = self.format_documents(code_contexts)
+        
+        # Generate response
+        response = self.generate_response(query, formatted_doc_contexts, formatted_code_contexts)
+        
+        # Add the response to the existing query in the conversation history
+        #self.add_to_conversation(llm_response=response)
+        
+        return response
+        
     #not supported yet, need session handling in app.py
     def add_to_conversation(self, user_query=None, llm_response=None):
         """
@@ -132,7 +169,7 @@ class KadiAPYBot:
         context = self.vector_store.similarity_search(query = query, k=k, filter=filter)       
         return context
 
-    def generate_response(self, query, history, doc_context, code_context):
+    def generate_response(self, query, doc_context, code_context):
         """
         Generate a response using the retrieved contexts and the LLM.
         """
@@ -165,40 +202,40 @@ class KadiAPYBot:
         return self.llm.invoke(prompt).content
 
 
-    def generate_response(self, query, history, doc_context, code_context):
-        """
-        Generate a response using the retrieved contexts and the LLM.
-        """     
-        formatted_history = format_history(history)
-        
-        # Update the prompt with history included
-        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 answer the user's query based on the guidelines, and if needed, combine understanding provided by 
-            "Document Snippets" with the implementation details provided by "Code Snippets." 
+    # def generate_response(self, query, history, doc_context, code_context):
+    #     """
+    #     Generate a response using the retrieved contexts and the LLM.
+    #     """     
+    #     formatted_history = format_history(history)
+        
+    #     # Update the prompt with history included
+    #     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 answer the user's query based on the guidelines, and if needed, combine understanding provided by 
+    #         "Document Snippets" with the implementation details provided by "Code Snippets." 
     
-            Guidelines if generating code:
-                - Display the complete code first, followed by a concise explanation in no more than 5 sentences.
+    #         Guidelines if generating code:
+    #             - Display the complete code first, followed by a concise explanation in no more than 5 sentences.
                 
-            General Guidelines:
-                - Refer to the "Conversation History" if it provides context that could enhance your understanding of the user's query.
-                - If the user's query cannot be fulfilled based on the provided snippets, reply with "The API does not support the requested functionality."
-                - If the user's query does not implicate any task, reply with a question asking the user to elaborate.
+    #         General Guidelines:
+    #             - Refer to the "Conversation History" if it provides context that could enhance your understanding of the user's query.
+    #             - If the user's query cannot be fulfilled based on the provided snippets, reply with "The API does not support the requested functionality."
+    #             - If the user's query does not implicate any task, reply with a question asking the user to elaborate.
             
-            Conversation History:
-            {formatted_history}
+    #         Conversation History:
+    #         {formatted_history}
     
-            Document Snippets:
-            {doc_context}
+    #         Document Snippets:
+    #         {doc_context}
     
-            Code Snippets:
-            {code_context}
+    #         Code Snippets:
+    #         {code_context}
         
-            Query:
-            {query}
-        """
-        return self.llm.invoke(prompt).content
+    #         Query:
+    #         {query}
+    #     """
+    #     return self.llm.invoke(prompt).content