Update app.py

app.py

@@ -15,13 +15,13 @@ retriever = vectorstore.as_retriever(search_kwargs={"k": 5})
 hf_token = os.environ.get("HF_TOKEN")
 llm = HuggingFaceEndpoint(
     repo_id="HuggingFaceH4/zephyr-7b-beta",
-    task="text-generation",
+    # REMOVED the "task" parameter to prevent backend routing clashes
     max_new_tokens=512,
     temperature=0.1,
     huggingfacehub_api_token=hf_token
 )
 
-# 3. Create the RAG Chain using modern LCEL (No langchain.chains needed!)
+# 3. Create the RAG Chain using modern LCEL
 system_prompt = (
     "You are an expert C++ programming assistant. You answer questions strictly based "
     "on the provided context from learncpp.com. If the answer is not in the context, "
@@ -68,7 +68,8 @@ demo = gr.ChatInterface(
     fn=chat_function,
     title="LearnCpp.com AI Assistant",
     description="Ask me any C++ question! I retrieve my answers directly from the complete LearnCpp tutorials.",
-    examples=["What is a pointer?", "Explain dynamic memory allocation.", "Give me an example of the previous concept."]
+    examples=["What is a pointer?", "Explain dynamic memory allocation.", "Give me an example of the previous concept."],
+    type="tuples" # ADDED THIS: Forces Gradio to use the format our memory loop expects!
 )
 
 if __name__ == "__main__":