search

Azure-Samples / rag-postgres-openai-python

A RAG app to ask questions about rows in a database table. Deployable on Azure Container Apps with PostgreSQL Flexible Server.
MIT License
263 stars 132 forks source link

Add question caching #82

Open pamelafox opened 2 months ago

pamelafox commented 2 months ago

Description

Add a question caching feature. Pseudocode based on other repo-

def chat_completion(user_input):
   # Generate embeddings from the user input
   user_embeddings = generate_embeddings(openai_client, user_input)
   # Query the chat history cache first to see if this question has been asked before
   cache_results = cache_search(vectors=user_embeddings , num_results=1)

   if len(cache_results) > 0:
       return cache_results[0]['completion'], True
   else:
       # Perform vector search 
       search_results = get_similar_docs(openai_client, dbsource, user_input, 3)
       print("Getting Chat History\n")
       # Chat history
       chat_history = get_chat_history(1)

       # Generate the completion
       print("Generating completions \n")
       completions_results = generatecompletionede(user_input, search_results, chat_history)

       # Cache the response
       cacheresponse(user_input, user_embeddings, completions_results)

       print("\n")
       # Return the generated LLM completion
       return completions_results['choices'][0]['message']['content'], False