Upload 2 files

app.py

@@ -54,9 +54,13 @@ async def main(message: cl.Message):
     # Handle chat messages
     if message.content:
         try:
-            # Generate response using RAG system
-            response = rag_processor.generate_response(message.content)
-            await cl.Message(content=response).send()
+            # Create a message placeholder
+            msg = cl.Message(content="")
+            await msg.send()
+
+            # Stream the response
+            async for chunk in rag_processor.generate_response(message.content):
+                await msg.stream_token(chunk)
         except Exception as e:
             await cl.Message(content=f"Error processing your message: {e}").send()
         return

rag_processor.py

@@ -1,5 +1,5 @@
 import os
-from typing import List
+from typing import List, Generator
 import openai
 from sentence_transformers import SentenceTransformer
 import faiss
@@ -35,8 +35,8 @@ class RAGProcessor:
         
         return [self.documents[i] for i in indices[0]]
 
-    def generate_response(self, query: str) -> str:
-        """Generate a response using OpenAI API with retrieved context."""
+    def generate_response(self, query: str) -> Generator[str, None, None]:
+        """Generate a streaming response using OpenAI API with retrieved context."""
         relevant_docs = self.retrieve_relevant_context(query)
         context = "\n".join(relevant_docs)
         
@@ -48,14 +48,17 @@ Given the context information, please answer the following question. If the cont
 Question: {query}
 Answer:"""
 
-        response = self.openai_client.chat.completions.create(
+        stream = self.openai_client.chat.completions.create(
             model="gpt-3.5-turbo",
             messages=[
                 {"role": "system", "content": "You are a helpful Pilates instructor assistant. Use the provided context to answer questions accurately."},
                 {"role": "user", "content": prompt}
             ],
             temperature=0.7,
-            max_tokens=500
+            max_tokens=500,
+            stream=True
         )
         
-        return response.choices[0].message.content 
+        for chunk in stream:
+            if chunk.choices[0].delta.content is not None:
+                yield chunk.choices[0].delta.content