Jason Weill comments

Results 566 comments of


                                            Jason Weill

Add test handlers, option to choose mock language model for testing

A testing language model, aka a mock testing model, would need to return predictable output for any prompt.

Make the default chat window memory size configurable

Related to #218, a major config refactor.

Add meaningful errors in the chat interface

#398 rewrites "index that path" to "process that message"

Unable to use ChatVertexAI as provider due to default chat's ChatPromptTemplate

See also #226 for customizing prompts for models/providers.

IndexError: list index out of range???

Hi @Hcrypt! Thanks so much for filing this issue. Do you see this with all models under Hugging Face Hub? I tried to use the same model, and while I...

IndexError: list index out of range???

I typically build and run Jupyter AI from source, using the `./scripts/install.sh` script from my local `jupyter-ai` repository. If you still see this bug with the newest published version of...

Update prompts for locally installed models

Fixed by #309.

Update prompts for locally installed models

OK, reopened.

Folders can be learned with /learn multiple times

Is this still an issue? Do any other models demonstrate it?

Folders can be learned with /learn multiple times

@3coins Please verify