You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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
The text was updated successfully, but these errors were encountered:
adamdougal
changed the title
Allow image based questions from /api/conversation/custom using openai_functions
Search image data from /api/conversation/custom when using openai_functionsApr 24, 2024
cecheta
changed the title
Search image data from /api/conversation/custom when using openai_functions
Search image data from /api/conversation/customMay 22, 2024
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 usingtext-embeddings-ada-002
in addition to be used to search the image description.Tasks
gpt-4-vision
along with the chatThe text was updated successfully, but these errors were encountered: