Update app.py

app.py

@@ -413,7 +413,7 @@ def create_vector_db_and_annoy_index(pdf_path, vector_db_path, annoy_index_path)
 # Cell 9: Run the store embeddings function (example)
 # Replace 'example.pdf' with your PDF file path.
 # It will create 'vector_db.pkl' and 'vector_index.ann'
-#create_vector_db_and_annoy_index(pdf_path, 'vector_db.pkl', 'vector_index.ann')
+create_vector_db_and_annoy_index('med.pdf', 'vector_db.pkl', 'vector_index.ann')
 
 # # Cell 10: Query the chatbot with user input
 # async def query_chatbot():
@@ -502,32 +502,16 @@ def create_vector_db_and_annoy_index(pdf_path, vector_db_path, annoy_index_path)
 
 import gradio as gr
 
-def chatbot_interface(user_query, response_style, selected_retrieval_methods, selected_reranking_methods, pdf_file, chunk_size, overlap):
+def chatbot_interface(user_query, response_style, selected_retrieval_methods, selected_reranking_methods, chunk_size, overlap):
     vector_db_path = "vector_db.pkl"
     annoy_index_path = "vector_index.ann"
 
     
     
     
-    if pdf_file is not None:
-        pdf_path = pdf_file.name  # Get the file path
-        # Now you can process the file path as needed
-        return f"File path: {pdf_path}\nUser Query: {user_query}\nResponse Style: {response_style}\nRetrieval Methods: {retrieval_methods}\nReranking Methods: {reranking_methods}\nChunk Size: {chunk_size}\nOverlap: {overlap}"
-    else:
-        return "No file uploaded."
-        # Create vector DB and Annoy index
-        create_vector_db_and_annoy_index(pdf_path, vector_db_path, annoy_index_path)
-        store_embeddings_in_vector_db(pdf_path, 'vector_db.pkl', 'vector_index.ann', chunk_size, overlap)
-    # if pdf_file is not None:
-    #     pdf_path = pdf_file.name  # Get the path of the uploaded file
-    #     create_vector_db_and_annoy_index(pdf_path, 'vector_db.pkl', 'vector_index.ann')
-    #     store_embeddings_in_vector_db(pdf_path, 'vector_db.pkl', 'vector_index.ann', chunk_size, overlap)
-        
-    # else:
-    #     return "Please upload a PDF file." 
-
-    # Load the documents and create embeddings with the provided chunk_size and overlap
-    #store_embeddings_in_vector_db('med.pdf', 'vector_db.pkl', 'vector_index.ann', chunk_size, overlap)
+
+    #Load the documents and create embeddings with the provided chunk_size and overlap
+    store_embeddings_in_vector_db('med.pdf', 'vector_db.pkl', 'vector_index.ann', chunk_size, overlap)
 
     chatbot = MistralRAGChatbot(vector_db_path, annoy_index_path)