Update app.py

app.py

@@ -1,4 +1,3 @@
-# app.py
 import os
 import gradio as gr
 from langchain_community.vectorstores import FAISS
@@ -9,64 +8,74 @@ from langchain.chains import RetrievalQA
 from langchain_community.llms import HuggingFaceEndpoint
 from huggingface_hub import login
 
-# 1. Authentication with validation
+# Authentication
 if not os.environ.get('HF_TOKEN'):
-    raise RuntimeError("Add HF_TOKEN in Space secrets!")
+    raise ValueError("❌ Add HF_TOKEN in Space secrets!")
 login(token=os.environ.get('HF_TOKEN'))
 
-# 2. PDF processing with error handling
 def create_qa_system():
     try:
-        # File check
+        # Validate PDF
         if not os.path.exists("file.pdf"):
-            raise FileNotFoundError("PDF missing")
+            raise FileNotFoundError("Upload PDF via Files tab")
         
-        # Load and validate PDF
+        # Process PDF
         loader = PyMuPDFLoader("file.pdf")
         documents = loader.load()
         if len(documents) == 0:
-            raise ValueError("PDF content empty")
-            
-        # Processing
-        text_splitter = CharacterTextSplitter(chunk_size=300, chunk_overlap=50)
+            raise ValueError("PDF is empty or corrupted")
+        
+        # Split text
+        text_splitter = CharacterTextSplitter(
+            chunk_size=300,
+            chunk_overlap=50
+        )
         texts = text_splitter.split_documents(documents)
         
+        # Create embeddings
         embeddings = HuggingFaceEmbeddings(
             model_name="sentence-transformers/all-MiniLM-L6-v2"
         )
         
+        # Build vector store
         db = FAISS.from_documents(texts, embeddings)
         
-        # Smaller model for free tier
+        # Initialize LLM
         llm = HuggingFaceEndpoint(
             repo_id="google/flan-t5-small",
-            max_length=128,
-            temperature=0.2,
+            task="text2text-generation",
+            model_kwargs={
+                "temperature": 0.2,
+                "max_length": 128
+            },
             huggingfacehub_api_token=os.environ.get('HF_TOKEN')
         )
         
         return RetrievalQA.from_chain_type(
             llm=llm,
             chain_type="stuff",
-            retriever=db.as_retriever(search_kwargs={"k": 1})
-        )  # Closing parenthesis added here
+            retriever=db.as_retriever(search_kwargs={"k": 2})
     except Exception as e:
-        raise gr.Error(f"Setup failed: {str(e)}")
+        raise gr.Error(f"Initialization failed: {str(e)}")
 
-# 3. Initialize system
+# Initialize system
 try:
     qa = create_qa_system()
 except Exception as e:
-    print(f"❌ Critical error: {str(e)}")
+    print(f"Fatal error: {str(e)}")
     raise
 
-# 4. Chat interface with error messages
 def chat_response(message, history):
     try:
         response = qa({"query": message})
         return response["result"]
     except Exception as e:
-        print(f"🚨 User-facing error: {str(e)}")  # Detailed log
-        return f"Error: {str(e)}"  # User message
+        print(f"Error during query: {str(e)}")
+        return f"⚠️ Error: {str(e)[:100]}"
 
-gr.ChatInterface(chat_response).launch()
+# Create interface
+gr.ChatInterface(
+    chat_response,
+    title="PDF Chat Assistant",
+    description="Ask questions about your PDF document"
+).launch()