Closed oliviermills closed 5 months ago
Consider adding haiku or replacing with haiku for image in utils/gptVision.ts The same prompt will work well.
Also you should probably shift to the now gpt-4-turbo which recommended instead of the vision model
gpt-4-turbo
Great Points! We already use gpt-4-turbo, but haiku will be a great alternative. @rafaelsideguide
Hey @oliviermills I just implemented it using claude-3-opus-20240229 #5
claude-3-opus-20240229
Consider adding haiku or replacing with haiku for image in utils/gptVision.ts The same prompt will work well.
Also you should probably shift to the now
gpt-4-turbo
which recommended instead of the vision model