user@ragas ~ % pip install ragas

ragas

~ pip install ragas

features

Metrics

automatic metrics that helps you understand the performance and robustness of your LLM application

Synthetic evaluation data

synthetically generate high quality and diverse evaluation data customised for your requirements.

Online Monitoring

evaluate and ensure the quality of your LLM application in production. Use insights to improve your application.

ragas in your stack

About Us

We are a group of passionate individuals who are leveraging cutting-edge research and pragmatic engineering practices to empower the visionaries who are redefining the possibilities of LLMs, with the right tools.

Founders

Shahul

Applied AI research
Kaggle GM

Jithin James

chief maintainer
previously @ BentoML

For support or questions regarding ragas please join discord as questions in #questions chatroom.

For enterprise features and collaborations email us or

engineers rely on ragas

still not convinced?

Congrats to @shahules786 for creating the only RAG framework directly recommended by openai at devday Thought leadership is the art of nailing the highest order bit

Image
Harrison Chase
Harrison Chase
@hwchase17

Great overview of RAGAS! We also did a webinar with them 2 weeks ago - check it out for more insights of how to evaluate RAG systems! youtube.com/watch?v=fWC4Vx…

143
Reply

RAGAS 🤝 Weaviate! New podcast tomorrow, some awesome background info below! 👇

Erika Cardenas
Erika Cardenas
@ecardenas300

RAG evaluation is the next step once your pipeline is set ☝️ There are four new metrics based on LLM evaluation that are setting the standard: 1. Faithfulness, 2. Answer relevancy, 3. Context precision, and 4. Context recall (Ragas score) The visual below illustrates prompting…

Image
46
Reply

I am blown away by RAGAS With 10 lines of code, I created a question + answer dataset of Airbnb's latest annual report (10-K). The dataset has 3 parts: • questions • contexts • ground truth answers Next step: Evaluate how well various LLMs perform RAG on financial…

Image
425
Reply

Congrats to @shahules786 for creating the only RAG framework directly recommended by openai at devday Thought leadership is the art of nailing the highest order bit

Image
Harrison Chase
Harrison Chase
@hwchase17

Great overview of RAGAS! We also did a webinar with them 2 weeks ago - check it out for more insights of how to evaluate RAG systems! youtube.com/watch?v=fWC4Vx…

143
Reply

RAGAS 🤝 Weaviate! New podcast tomorrow, some awesome background info below! 👇

Erika Cardenas
Erika Cardenas
@ecardenas300

RAG evaluation is the next step once your pipeline is set ☝️ There are four new metrics based on LLM evaluation that are setting the standard: 1. Faithfulness, 2. Answer relevancy, 3. Context precision, and 4. Context recall (Ragas score) The visual below illustrates prompting…

Image
46
Reply

I am blown away by RAGAS With 10 lines of code, I created a question + answer dataset of Airbnb's latest annual report (10-K). The dataset has 3 parts: • questions • contexts • ground truth answers Next step: Evaluate how well various LLMs perform RAG on financial…

Image
425
Reply

Careers

We are a small team focused on innovating on state of the art research in AI to provide value to our users. We are always in lookout for passionate individuals who shares similar vision.

Write to us on founders@explodinggradients.com. We are looking to hearing from you.

ragas is backed by