Ulises M
Ulises M
### Prerequisites If you are **not** suggesting a feature, you must be able to check all of the following (place an x inside the brackets to check the box). If...
**Is your feature request related to a problem? Please describe.** Ollama is a good solution for local evaluation for projects that already use it. If a project uses pure llama.cpp...
**Describe the bug** Sometimes, the evaluator returns null for score/explanation and sometimes it crashes with the following error: ```2024-03-10 22:36:45.719 | INFO | uptrain.framework.evalllm:evaluate:100 - Sending evaluation request for rows...
**Is your feature request related to a problem? Please describe.** As of now, Haystack's evaluators which extend LLMEvaluator only support OpenAI. I would like for support through llama.cpp to be...
### Related Issues - fixes #7839 ### Proposed Changes: This PR makes it possible to pass in a ChatMessage to AnswerBuilder ### How did you test it? Replicated str tests...
**Is your feature request related to a problem? Please describe.** There is no current way for a `ChatGenerator` to directly connect to `AnswerBuilder()` despite similar functionality to a regular Generator....
### Description If groups are not created correctly in Shoko (due to the order of import) and Jellyfin receives the incorrect grouping metadata, Jellyfin will produce an error due to...
**Is your feature request related to a problem? Please describe.** This was asked for by a [user on the discord](https://discord.com/channels/993534733298450452/993539071815200889/1265985848315478056) a couple weeks ago. Useful for those who don't use...
### Related Issues - fixes #8243 ### Proposed Changes: I explicitly chose to expose default_headers and add an optional azure_kwargs for the other more niche parameters that some users might...
RTX VSR is resource intensive, but the output looks better than NIS for me. I got it working by adding this to the settings group: ``` hw-d3d11va-rtxvsr": { "settings": [...