fix: update PDF processing in web interfaces - Update gradio_app to handle docuent_id correctly - Update FastAPI endpoint to use returned document_id - Fix document_id handling in vector store integration

Author: jasperan

agentic_rag/gradio_app.py

@@ -40,9 +40,9 @@ def load_config():
 def process_pdf(file: tempfile._TemporaryFileWrapper) -> str:
     """Process uploaded PDF file"""
     try:
-        chunks = pdf_processor.process_pdf(file.name)
-        vector_store.add_pdf_chunks(chunks)
-        return f"✓ Successfully processed PDF and added {len(chunks)} chunks to knowledge base"
+        chunks, document_id = pdf_processor.process_pdf(file.name)
+        vector_store.add_pdf_chunks(chunks, document_id=document_id)
+        return f"✓ Successfully processed PDF and added {len(chunks)} chunks to knowledge base (ID: {document_id})"
     except Exception as e:
         return f"✗ Error processing PDF: {str(e)}"
 

agentic_rag/main.py

@@ -66,11 +66,10 @@ async def upload_pdf(file: UploadFile = File(...)):
             buffer.write(content)
 
         # Process the PDF
-        chunks = pdf_processor.process_pdf(temp_path)
+        chunks, document_id = pdf_processor.process_pdf(temp_path)
 
         # Add chunks to vector store
-        document_id = str(uuid.uuid4())
-        vector_store.add_pdf_chunks(chunks, document_id)
+        vector_store.add_pdf_chunks(chunks, document_id=document_id)
 
         # Clean up
         os.remove(temp_path)