Upload app.py with huggingface_hub

app.py

@@ -5,15 +5,12 @@ from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_community.vectorstores import FAISS
 from huggingface_hub import InferenceClient
-import os
 
-# Initialize embedding model
 embedding_model = HuggingFaceEmbeddings(
     model_name="sentence-transformers/all-MiniLM-L6-v2",
     model_kwargs={'device': 'cpu'}
 )
 
-# Initialize Inference Client
 client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta")
 
 vectorstore = None
@@ -39,10 +36,10 @@ def process_pdf(pdf_file):
             embedding=embedding_model
         )
         
-        return f"✅ Processed {len(documents)} pages into {len(chunks)} chunks. Ready for questions!"
+        return f"Processed {len(documents)} pages into {len(chunks)} chunks. Ready!"
     
     except Exception as e:
-        return f"❌ Error: {str(e)}"
+        return f"Error: {str(e)}"
 
 def answer_question(question):
     global vectorstore
@@ -58,7 +55,7 @@ def answer_question(question):
         context = "\n\n".join([doc.page_content for doc in docs])
         
         prompt = f"""<|system|>
-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."
+You are a helpful assistant. Answer based on the context only.
 </s>
 <|user|>
 Context:
@@ -85,25 +82,17 @@ Question: {question}
         return response, "\n".join(sources)
     
     except Exception as e:
-        return f"❌ Error: {str(e)}", ""
+        return f"Error: {str(e)}", ""
 
-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():
-            pdf_input = gr.File(label="Upload PDF", file_types=[".pdf"])
-            process_btn = gr.Button("📄 Process PDF")
-            status = gr.Textbox(label="Status")
-        
-        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)
-    
-    process_btn.click(process_pdf, inputs=[pdf_input], outputs=[status])
-    ask_btn.click(answer_question, inputs=[question], outputs=[answer, sources])
+demo = gr.Interface(
+    fn=answer_question,
+    inputs=gr.Textbox(label="Question"),
+    outputs=[
+        gr.Textbox(label="Answer"),
+        gr.Textbox(label="Sources")
+    ],
+    title="RAG Document Q&A",
+    description="Ask questions about uploaded documents."
+)
 
-demo.launch(share=True)
+demo.launch()