Akrem Abayed retweetledi
Akrem Abayed
14 posts

Akrem Abayed retweetledi

Happy New Year!
As we step into 2024, we wanted to reflect on our journey since our launch.
Our mission in agenta is to build an end-to-end, open-source LMOps platform for developers and product teams. We are building the tools to allow team to quickly and confidently ship robust LLM-powered applications to production.
In the past year, we shipped:
Prompt Engineering: We developed a playground compatible with any model or workflow, enabling quick experimentation and versioning of prompts.
Evaluation Tools: We created a set of tools for evaluating LLM applications, this enables team to rapidly iterate to improve their applicatoins.
Human Evaluation: We created a web interface for human annotation and A/B testing, allowing for comparison and selection of the best LLM app variant.
Cloud and Enterprise Editions: Launched in November, these editions provide collaboration features, self-hosting, and enhanced security.
In the upcoming weeks, look forward to exciting updates such as new playground models, token and cost optimization tools, and a revamped evaluation workflow.
Finally, we'd like to extend our sincere gratitude to our 52 contributors and over 1,000 registered users!
Wishing you a year full of success,
The Agenta Team

English
Akrem Abayed retweetledi

We've just launched chat capabilities in @agenta_ai. If you are building #chat applications and struggling with errors, #hallucinations, and wrong answers. Read ahead:
With our open-source platform agenta, you can now:
⭐ Develop and test chat applications in the playground
⭐ Compare various prompts and configurations
⭐ Easily add conversations from the playground to the test set
⭐ Evaluate #chatbots using human feedback, featuring an interface for A/B testing, scoring, and annotation
⭐ Implement automatic evaluations to check output quality before production
We support all #LLM providers, and can handle both simple chat applications and more complex ones based on #RAG.
Check it out: cloud.agenta.ai
Repo: github.com/agenta-ai/agen…
#llmops #evaluation #llm #openai
English
Akrem Abayed retweetledi

🎉 Exciting update from #Agenta! We've introduced a new feature to build production-ready #LLM apps in minutes, directly from our UI.🖥
Try the live demo here: demo.agenta.ai
#llmops #opensource
English
Akrem Abayed retweetledi
Akrem Abayed retweetledi

🚀 @agenta_ai 's Exciting Update: The #Evaluation Feature is here! 🧪 Building a robust #LLM application requires ample experimentation with #prompts and configurations. Our new feature is here to ease the process.
English
Akrem Abayed retweetledi
Akrem Abayed retweetledi

⚡ Boost your efficiency with our latest feature in @agenta_ai
We've revamped the process of serving multiple LLM app variants based on user feedback. 🔄💪 Create and test multiple versions seamlessly from a single folder.
Learn more: docs.agenta.ai/docs/howto/cre…
English
Akrem Abayed retweetledi
Akrem Abayed retweetledi

🚀 Exciting news! Today, we're launching the alpha of @agenta_ai , an #open-source #LLMOps platform enabling developers to rapidly iterate, evaluate, and deploy #LLM powered applications.
⭐ Give us a star here: github.com/agenta-ai/agen… and visit us in agenta.ai
GIF
English
Akrem Abayed retweetledi






