Chen Qian

Results 193 comments of Chen Qian

DSPy image uses the same format as OpenAI image input: https://platform.openai.com/docs/guides/images-vision?api-mode=chat&format=base64-encoded#giving-a-model-images-as-input, so technically it should just work out of the box for different providers. Ollama seems to require the local...

The variables and edits are only valid within the session, on restart you recreate everything.

@dbczumar Any clues?