Update app.py

app.py

@@ -1,3 +1,4 @@
+# app.py
 import os
 import gradio as gr
 from langchain_community.vectorstores import FAISS
@@ -5,49 +6,66 @@ 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  # Updated import
+from langchain_community.llms import HuggingFaceEndpoint
 from huggingface_hub import login
 
-# 1. Authentication
+# 1. Authentication with validation
+if not os.environ.get('HF_TOKEN'):
+    raise RuntimeError("Add HF_TOKEN in Space secrets!")
 login(token=os.environ.get('HF_TOKEN'))
 
-# 2. PDF Processing
+# 2. PDF processing with error handling
 def create_qa_system():
-    if not os.path.exists("file.pdf"):
-        raise gr.Error("❗ Upload file.pdf in Files tab")
-    
-    loader = PyMuPDFLoader("file.pdf")
-    documents = loader.load()
-    
-    text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=50)
-    texts = text_splitter.split_documents(documents)
-    
-    embeddings = HuggingFaceEmbeddings(
-        model_name="sentence-transformers/all-MiniLM-L6-v2"
-    )
-    
-    db = FAISS.from_documents(texts, embeddings)
-    
-    # 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(
-        llm=llm,
-        chain_type="stuff",
-        retriever=db.as_retriever(search_kwargs={"k": 2})
-    )
+    try:
+        # File check
+        if not os.path.exists("data.pdf"):
+            raise FileNotFoundError("PDF missing")
+        
+        # Load and validate PDF
+        loader = PyMuPDFLoader("data.pdf")
+        documents = loader.load()
+        if len(documents) == 0:
+            raise ValueError("PDF content empty")
+            
+        # Processing
+        text_splitter = CharacterTextSplitter(chunk_size=300, chunk_overlap=50)
+        texts = text_splitter.split_documents(documents)
+        
+        embeddings = HuggingFaceEmbeddings(
+            model_name="sentence-transformers/all-MiniLM-L6-v2"
+        )
+        
+        db = FAISS.from_documents(texts, embeddings)
+        
+        # Smaller model for free tier
+        llm = HuggingFaceEndpoint(
+            repo_id="google/flan-t5-small",
+            max_length=128,
+            temperature=0.2,
+            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})
+    except Exception as e:
+        raise gr.Error(f"Setup failed: {str(e)}")
 
-# 4. Initialize system
-qa = create_qa_system()
+# 3. Initialize system
+try:
+    qa = create_qa_system()
+except Exception as e:
+    print(f"❌ Critical error: {str(e)}")
+    raise
 
-# 5. Chat interface
+# 4. Chat interface with error messages
 def chat_response(message, history):
-    response = qa({"query": message})
-    return response["result"]
+    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
 
 gr.ChatInterface(chat_response).launch()