Upload app.py with huggingface_hub

app.py

@@ -7,23 +7,18 @@ from langchain_community.vectorstores import FAISS
 from huggingface_hub import InferenceClient
 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)
+# Initialize embedding model
 embedding_model = HuggingFaceEmbeddings(
     model_name="sentence-transformers/all-MiniLM-L6-v2",
     model_kwargs={'device': 'cpu'}
 )
 
-# Initialize Inference Client (uses free API)
+# Initialize Inference Client
 client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta")
 
-# Global variable to store vectorstore
 vectorstore = None
 
 def process_pdf(pdf_file):
-    """Process uploaded PDF and create vector store."""
     global vectorstore
     
     if pdf_file is None:
@@ -50,7 +45,6 @@ def process_pdf(pdf_file):
         return f"❌ Error: {str(e)}"
 
 def answer_question(question):
-    """Answer question using RAG."""
     global vectorstore
     
     if vectorstore is None:
@@ -93,7 +87,6 @@ Question: {question}
     except Exception as e:
         return f"❌ Error: {str(e)}", ""
 
-# 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.")
@@ -113,5 +106,4 @@ with gr.Blocks() as demo:
     process_btn.click(process_pdf, inputs=[pdf_input], outputs=[status])
     ask_btn.click(answer_question, inputs=[question], outputs=[answer, sources])
 
-if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860, share=False)
+demo.launch(share=True)