Upload app.py with huggingface_hub

app.py

@@ -5,9 +5,11 @@ from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_community.vectorstores import FAISS
 from huggingface_hub import InferenceClient
-import tempfile
 import os
 
+# Set environment variable to fix localhost issue
+os.environ["GRADIO_SERVER_NAME"] = "0.0.0.0"
+
 # Initialize embedding model (runs on CPU, small enough for free tier)
 embedding_model = HuggingFaceEmbeddings(
     model_name="sentence-transformers/all-MiniLM-L6-v2",
@@ -28,27 +30,24 @@ def process_pdf(pdf_file):
         return "Please upload a PDF file."
     
     try:
-        # Load PDF
         loader = PyPDFLoader(pdf_file.name)
         documents = loader.load()
         
-        # Split into chunks
         text_splitter = RecursiveCharacterTextSplitter(
             chunk_size=1000,
             chunk_overlap=200,
         )
         chunks = text_splitter.split_documents(documents)
         
-        # Create vector store
         vectorstore = FAISS.from_documents(
             documents=chunks,
             embedding=embedding_model
         )
         
-        return f"✅ Successfully processed {len(documents)} pages into {len(chunks)} chunks. You can now ask questions!"
+        return f"✅ Processed {len(documents)} pages into {len(chunks)} chunks. Ready for questions!"
     
     except Exception as e:
-        return f"❌ Error processing PDF: {str(e)}"
+        return f"❌ Error: {str(e)}"
 
 def answer_question(question):
     """Answer question using RAG."""
@@ -61,15 +60,11 @@ def answer_question(question):
         return "Please enter a question.", ""
     
     try:
-        # Retrieve relevant chunks
         docs = vectorstore.similarity_search(question, k=3)
-        
-        # Format context
         context = "\n\n".join([doc.page_content for doc in docs])
         
-        # Create prompt
         prompt = f"""<|system|>
-You are a helpful assistant that answers questions based on the provided context. Only use information from the context to answer. If the answer is not in the context, say "I cannot find this information in the document."
+You are a helpful assistant that answers questions based on the provided context. Only use information from the context. If the answer is not in the context, say "I cannot find this information in the document."
 </s>
 <|user|>
 Context:
@@ -79,14 +74,12 @@ Question: {question}
 </s>
 <|assistant|>"""
         
-        # Call Inference API
         response = client.text_generation(
             prompt,
             max_new_tokens=512,
             temperature=0.7,
         )
         
-        # Format sources
         sources = []
         for i, doc in enumerate(docs, 1):
             page = doc.metadata.get('page', 'N/A')
@@ -95,67 +88,30 @@ Question: {question}
             preview = doc.page_content[:150].replace('\n', ' ')
             sources.append(f"{i}. Page {page}: {preview}...")
         
-        sources_text = "\n".join(sources)
-        
-        return response, sources_text
+        return response, "\n".join(sources)
     
     except Exception as e:
         return f"❌ Error: {str(e)}", ""
 
-# Create Gradio interface
-with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("""
-    # 📚 RAG Document Q&A System
-    
-    Upload a PDF document and ask questions about its content.
-    
-    **How it works:**
-    1. Upload a PDF file
-    2. Click "Process PDF" to analyze the document
-    3. Ask questions about the document content
-    """)
+# Create Gradio interface using simpler Interface API
+with gr.Blocks() as demo:
+    gr.Markdown("# 📚 RAG Document Q&A System")
+    gr.Markdown("Upload a PDF and ask questions about its content.")
     
     with gr.Row():
-        with gr.Column(scale=1):
+        with gr.Column():
             pdf_input = gr.File(label="Upload PDF", file_types=[".pdf"])
-            process_btn = gr.Button("📄 Process PDF", variant="primary")
-            status_output = gr.Textbox(label="Status", interactive=False)
+            process_btn = gr.Button("📄 Process PDF")
+            status = gr.Textbox(label="Status")
         
-        with gr.Column(scale=2):
-            question_input = gr.Textbox(
-                label="Your Question",
-                placeholder="What is this document about?",
-                lines=2
-            )
-            ask_btn = gr.Button("🔍 Ask Question", variant="primary")
-            answer_output = gr.Textbox(label="Answer", lines=6, interactive=False)
-            sources_output = gr.Textbox(label="Sources", lines=4, interactive=False)
-    
-    gr.Markdown("""
-    ---
-    ### 🛠️ Technical Details
-    
-    | Component | Technology |
-    |-----------|------------|
-    | Embeddings | sentence-transformers/all-MiniLM-L6-v2 |
-    | Vector Store | FAISS |
-    | LLM | Zephyr-7B via Inference API |
-    | Chunking | 1000 chars, 200 overlap |
-    
-    Built by [Nav772](https://huggingface.co/Nav772) as part of AI Engineering portfolio.
-    """)
-    
-    # Connect buttons to functions
-    process_btn.click(
-        fn=process_pdf,
-        inputs=[pdf_input],
-        outputs=[status_output]
-    )
+        with gr.Column():
+            question = gr.Textbox(label="Question", placeholder="Ask about the document...")
+            ask_btn = gr.Button("🔍 Ask")
+            answer = gr.Textbox(label="Answer", lines=5)
+            sources = gr.Textbox(label="Sources", lines=3)
     
-    ask_btn.click(
-        fn=answer_question,
-        inputs=[question_input],
-        outputs=[answer_output, sources_output]
-    )
+    process_btn.click(process_pdf, inputs=[pdf_input], outputs=[status])
+    ask_btn.click(answer_question, inputs=[question], outputs=[answer, sources])
 
-demo.launch(server_name="0.0.0.0", server_port=7860)
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860, share=False)