agenta
agenta copied to clipboard
Agenta-AI
The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.
**Is your feature request related to a problem? Please describe.** Currently, the LLM provider keys are being saved directly to local storage without any encryption, storing keys without encryption poses...
**Is your feature request related to a problem? Please describe.** Exceptions are currently not handled as per OpenTelemetry specifications. **Describe the solution you'd like** This feature would require changes in...
AI critique provides different results from run to run. The goal of this issue is to determine and implement the best practices / parameters for running AI critic and improving...
**Describe the bug** Any kind of evaluation can't stop running on self-host agenta. **To Reproduce** Steps to reproduce the behavior: 1. In CLI, run "docker compose -f docker-compose.gh.yml up -d...
I think custom code evaluators are one of the nicest feature we have in agenta. It allows much more flexibility and allows to check for specific business rules, computing bleeding...
### Description This PR aims to improve the image optimization of the documentation site.
### Description This PR aims to resolve the UX bug in the testset by moving it from the application scope to the project scope. ### Related Issue Closes [AGE-964](https://linear.app/agenta/issue/AGE-964/move-test-sets-outside-of-applications-in-webui) ###...
### Description This PR significantly improves the App Management UI, enhancing user experience and workflow efficiency. ### Related Issue Closes [AGE-914](https://linear.app/agenta/issue/AGE-914/implement-new-app-management-view). ### Key Changes - Redesigned the app selection interface...