Update app.py

app.py

@@ -5,7 +5,7 @@ from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain_community.document_loaders import PyMuPDFLoader
 from langchain_text_splitters import CharacterTextSplitter
 from langchain.chains import RetrievalQA
-from langchain_community.llms import HuggingFaceEndpoint
+from langchain_huggingface import HuggingFaceEndpoint  # Updated import
 from huggingface_hub import login
 
 # Authentication
@@ -40,14 +40,12 @@ def create_qa_system():
         # Build vector store
         db = FAISS.from_documents(texts, embeddings)
         
-        # Initialize LLM
+        # Initialize LLM with corrected parameters
         llm = HuggingFaceEndpoint(
-            repo_id="google/flan-t5-small",
+            endpoint_url="https://api-inference.huggingface.co/models/google/flan-t5-small",
             task="text2text-generation",
-            model_kwargs={
-                "temperature": 0.2,
-                "max_length": 128
-            },
+            temperature=0.2,  # Direct parameter
+            max_new_tokens=128,  # Correct parameter name
             huggingfacehub_api_token=os.environ.get('HF_TOKEN')
         )
         
@@ -73,9 +71,4 @@ def chat_response(message, history):
         print(f"Error during query: {str(e)}")
         return f"⚠️ Error: {str(e)[:100]}"
 
-# Create interface
-gr.ChatInterface(
-    chat_response,
-    title="PDF Chat Assistant",
-    description="Ask questions about your PDF document"
-).launch()
+gr.ChatInterface(chat_response).launch()