agenta
agenta copied to clipboard
Agenta-AI
The all-in-one LLM developer platform: prompt management, evaluation, human feedback, and deployment all in one place.
# Context: We would like to enable users to update their LLM API keys in agenta and continue using their apps with the new API keys. Right now, after an...
**Context**: Some users would like to use observability without using the application hosted in agenta to minimise latency and increase reliability **Problem**: Right now instrumenting the observability requires a multitude...
The beta version of observability does not support nested spans. From [SyncLinear.com](https://synclinear.com) | [AGE-150](https://linear.app/agenta/issue/AGE-150/support-nested-spans-in-the-trace-detail-view-on-the-frontend)
Currently only the outputs for spans are shown. From [SyncLinear.com](https://synclinear.com) | [AGE-154](https://linear.app/agenta/issue/AGE-154/[fea]-show-the-inputs-for-spans)
Creating an app from code. If using the line *model_1*=ag.GroupedMultipleChoiceParam( *default*="gpt-3.5-turbo", *choices*=get_all_supported_llm_models()), We get the warning when running the app from shell (or in the lambda/docker logs) From [SyncLinear.com](https://synclinear.com) |...
To reproduce: - Create a test set with a correct_answer - Run an evaluation The evaluation will fail and the result will not be seen Expected behavior: The evaluation will...
Next build is taking a lot of time. After some researches [one](https://forums.docker.com/t/build-a-nextjs-project-is-too-heavy-and-some-doubts/138748/11) of the solutions is to upgrade to next 14. We are using next 13 and it would be...
I think we should disable this for cloud and keep it only for oss. @aakrem Tracking issue for: - [x] https://github.com/Agenta-AI/agenta/security/code-scanning/26
In the playground, each time we add a datapoint to a test set, the default selected option in the multi-select down below is the "+Add new". For users who are...