Search image data from /api/conversation/custom

[adamdougal]

Required by #323

Description

When calling the /api/conversation/custom endpoint, generate embeddings of the question using computer vision and query the image embeddings using the question embeddings. We should continue to create question embeddings using text-embeddings-ada-002 in addition to be used to search the image description.

Tasks

• Stop using langchain in the quesiton answer tool and post prompt tool
• Generate question embeddings using computer vision
• Query the search index using the generated embeddings
• Pass any returned images to gpt-4-vision along with the chat
• Add a limit on the number of images passed to vision
• Update post answering prompt to include images