Christian Weyer comments

Results 179 comments of


                                            Christian Weyer

Using the lib with server-side pre-rendering fails

Thanks! Yeah, it seems like some effort just to get the initial pre-rendering done.

Using the lib with server-side pre-rendering fails

How did you find that @sabitertan ? :-)

Upgrade to support 3.2.0 GA

These are all excellent points you bring up. The out-of-the-box support e.g. still lacks some interesting functionality, renewing etc. 3rd party cookies may be avoided by hosting on the same...

.Net: 0613 models tools not recognized

> I can confirm the preview of gpt-4 in Azure Open AI (1106-Preview) works well (but 0603 did not, 32k or not) How did you get the GPT-4 preview model...

[Question] The results of the local model are inconsistent with the web ui in the demo

I am seeing the exact same thing. Currently, I am running Llava:34b-V1.6 in Ollama, and it just does not recognize things in a form and hallucinates values - whereas the...

NotImplementedError: parse_raw is not supported for pydantic 2 - how to do it with Pydantic 2?

For now, I could move back to Pydantic 1...

TypeChat design question: Aren't we mixing schema and data?

I am not sure how either approach would help with my initial doubts... 🤔

TypeChat design question: Aren't we mixing schema and data?

Would you have a simple example that illustrates your approach @philkunz ?

Feature Request: Support for `phi-3-vision-128k-instruct`

> @JosefAlbers > > Paligemma is done, thanks! > > Do you want to take on Phi-3-vision? Is there a list of officially supported models?

Feature Request: Support for `phi-3-vision-128k-instruct`

> @ChristianWeyer not yet. > > But at the moment we support the following archictetures: > > * Llava (Clip + Llama) > * Paligemma (Siglip + Gemma) > *...