Update app.py

app.py

@@ -5,40 +5,35 @@ 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 HuggingFaceHub
+from langchain_community.llms import HuggingFaceEndpoint  # Updated import
 from huggingface_hub import login
 
-# 1. Authentication (MUST HAVE)
-from huggingface_hub import login
-import os
+# 1. Authentication
+login(token=os.environ.get('HF_TOKEN'))
 
+# 2. PDF Processing
 def create_qa_system():
-    login(token=os.environ.get('HF_TOKEN'))  # Safe method
-
-# 2. PDF Processing Function
-def create_qa_system():
-    # File check
-    if not os.path.exists("file.pdf"):
-        raise gr.Error("❌ file.pdf not found! Upload it in Space's Files tab")
+    if not os.path.exists("data.pdf"):
+        raise gr.Error("❗ Upload data.pdf in Files tab")
     
-    # Load PDF
-    loader = PyMuPDFLoader("file.pdf")
+    loader = PyMuPDFLoader("data.pdf")
     documents = loader.load()
     
-    # Split text
     text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=50)
     texts = text_splitter.split_documents(documents)
     
-    # Create embeddings
-    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+    embeddings = HuggingFaceEmbeddings(
+        model_name="sentence-transformers/all-MiniLM-L6-v2"
+    )
     
-    # Build vector store
     db = FAISS.from_documents(texts, embeddings)
     
-    # Initialize LLM (Free-tier compatible)
-    llm = HuggingFaceHub(
-        repo_id="google/flan-t5-base",  # Changed to smaller model
-        model_kwargs={"temperature": 0.2, "max_length": 256}
+    # 3. Updated LLM initialization
+    llm = HuggingFaceEndpoint(
+        repo_id="google/flan-t5-base",
+        max_length=256,
+        temperature=0.2,
+        huggingfacehub_api_token=os.environ.get('HF_TOKEN')  # Explicit token passing
     )
     
     return RetrievalQA.from_chain_type(
@@ -47,17 +42,12 @@ def create_qa_system():
         retriever=db.as_retriever(search_kwargs={"k": 2})
     )
 
-# 3. Initialize system
+# 4. Initialize system
 qa = create_qa_system()
 
-# 4. Chat interface
-def chat(message, history):
+# 5. Chat interface
+def chat_response(message, history):
     response = qa({"query": message})
     return response["result"]
 
-# 5. Launch Gradio
-gr.ChatInterface(
-    chat,
-    title="PDF Chatbot",
-    description="Upload your PDF in Files tab ➡️ Ask questions!",
-).launch()
+gr.ChatInterface(chat_response).launch()