Update app.py

app.py

@@ -5,6 +5,7 @@ from langchain_huggingface import HuggingFaceEmbeddings, HuggingFaceEndpoint
 from langchain_community.vectorstores import FAISS
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain_core.prompts import ChatPromptTemplate
+from langchain_huggingface import ChatHuggingFace # Add this to your imports
 
 # 2026 Imports: These now live in the classic/retrieval modules
 from langchain_classic.chains import create_retrieval_chain
@@ -28,13 +29,13 @@ retriever = vectorstore.as_retriever()
 # 4. Initialize LLM (The Fix: Task="conversational")
 llm = HuggingFaceEndpoint(
     repo_id="Qwen/Qwen2.5-7B-Instruct",
-    task="conversational",  # Required for Instruct/Chat models in 2026
+    task="conversational",  # Matches the provider's requirement
     huggingfacehub_api_token=sec_token,
     temperature=0.1,
-    max_new_tokens=512,
-    timeout=300
 )
 
+chat_model = ChatHuggingFace(llm=llm)
+
 # 5. Define the RAG Prompt
 system_prompt = (
     "You are a helpful assistant for Examfriendly tuition. "
@@ -52,18 +53,17 @@ prompt = ChatPromptTemplate.from_messages(
 )
 
 # 6. Build the Chain
-question_answer_chain = create_stuff_documents_chain(llm, prompt)
+question_answer_chain = create_stuff_documents_chain(chat_model, prompt)
 rag_chain = create_retrieval_chain(retriever, question_answer_chain)
 
 # 7. Define the Chat Function for Gradio
 def chat(message, history):
     try:
-        # The chain expects a dictionary with "input"
+        # ChatHuggingFace expects "input" inside the dictionary
         result = rag_chain.invoke({"input": message})
         return result["answer"]
     except Exception as e:
-        # This will show you exactly why it failed in the chat box
-        return f"Error: {str(e)}"
+        return f"System Error: {str(e)}"
 
 # 8. Launch the Interface
 demo = gr.ChatInterface(