NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI · #3960 most downloaded on PyPI
Evaluation framework for RAG and LLM applications
Last release 8 months ago
13 Jan 2026
Ships on a steady schedule
a new release about every 2 weeks
Nearly every release is documented
notes for 58 of the last 60 stable releases
1 version withdrawn
withdrawn after publishing
3 years old
88 releases · first in 2023
One column per quarter.
add initial embeddings.encode_kwargs by @lucasiscovici in https://github.com/explodinggradients/ragas/pull/371
ground_truths arg type-hint info in the eval function by @MANISH007700 in https://github.com/explodinggradients/ragas/pull/404json_load by @jjmachan in https://github.com/explodinggradients/ragas/pull/430raise_exception and max_workers by @jjmachan in https://github.com/explodinggradients/ragas/pull/486TestsetGenerator by @jjmachan in https://github.com/explodinggradients/ragas/pull/487ExceptionInRunner if executor faces any issues by @jjmachan in https://github.com/explodinggradients/ragas/pull/569Full Changelog: https://github.com/explodinggradients/ragas/compare/v0.0.22...v0.1.0
add initial embeddings.encode_kwargs by @lucasiscovici in https://github.com/explodinggradients/ragas/pull/371
ground_truths arg type-hint info in the eval function by @MANISH007700 in https://github.com/explodinggradients/ragas/pull/404json_load by @jjmachan in https://github.com/explodinggradients/ragas/pull/430raise_exception and max_workers by @jjmachan in https://github.com/explodinggradients/ragas/pull/486TestsetGenerator by @jjmachan in https://github.com/explodinggradients/ragas/pull/487Full Changelog: https://github.com/explodinggradients/ragas/compare/v0.0.22...v0.1.0rc1
docs: comparing llms using ragas evaluations by @tinomaxthayil in https://github.com/explodinggradients/ragas/pull/314
validate_api_key by @arm-diaz in https://github.com/explodinggradients/ragas/pull/350Full Changelog: https://github.com/explodinggradients/ragas/compare/v0.0.21...v0.0.22
docs: Import AnswerSimilarity by @nelsonauner in https://github.com/explodinggradients/ragas/pull/296
Full Changelog: https://github.com/explodinggradients/ragas/compare/v0.0.20...v0.0.21
docs: update how LLMs are customized in Ragas metrics by @jjmachan in https://github.com/explodinggradients/ragas/pull/219
Full Changelog: https://github.com/explodinggradients/ragas/compare/v0.0.19...v0.0.20
docs: fix typo by @shahules786 in https://github.com/explodinggradients/ragas/pull/214
Full Changelog: https://github.com/explodinggradients/ragas/compare/v0.0.18...v0.0.19
fix: use llm from baseclass for metrics by @jjmachan in https://github.com/explodinggradients/ragas/pull/189
Full Changelog: https://github.com/explodinggradients/ragas/compare/v0.0.17...v0.0.18
Testset generation: add gaurdrails to chunk filtering by @shahules786 in https://github.com/explodinggradients/ragas/pull/166
context_precision is correctly called by @monstertruck in https://github.com/explodinggradients/ragas/pull/168Full Changelog: https://github.com/explodinggradients/ragas/compare/v0.0.16...v0.0.17
docs: azure openai quickstart by @jjmachan in https://github.com/explodinggradients/ragas/pull/155
context_relevancy to context_precision by @jjmachan in https://github.com/explodinggradients/ragas/pull/157Full Changelog: https://github.com/explodinggradients/ragas/compare/v0.0.15...v0.0.16
added contact info by @shahules786 in https://github.com/explodinggradients/ragas/pull/142
Full Changelog: https://github.com/explodinggradients/ragas/compare/v0.0.14...v0.0.15
Update README.md by @emilesilvis in https://github.com/explodinggradients/ragas/pull/139
Full Changelog: https://github.com/explodinggradients/ragas/compare/v0.0.13...v0.0.14
General bug fixes and reliability improvements
General bug fixes and reliability improvements
Full Changelog: https://github.com/explodinggradients/ragas/compare/v0.0.12...v0.0.13
chore: added note about consultation by @jjmachan in https://github.com/explodinggradients/ragas/pull/98
Full Changelog: https://github.com/explodinggradients/ragas/compare/v0.0.11...v0.0.12
docs: correct docs for answer relevancy by @jjmachan in https://github.com/explodinggradients/ragas/pull/86
Full Changelog: https://github.com/explodinggradients/ragas/compare/v0.0.10...v0.0.11
feat: llama_index integration by @jjmachan in https://github.com/explodinggradients/ragas/pull/78
Full Changelog: https://github.com/explodinggradients/ragas/compare/v0.0.9...v0.0.10
fix: validation was incorrect by @jjmachan in https://github.com/explodinggradients/ragas/pull/75
patch release for v0.0.8
Full Changelog: https://github.com/explodinggradients/ragas/compare/v0.0.8...v0.0.9
Critique metrics by @shahules786 in https://github.com/explodinggradients/ragas/pull/70
Full Changelog: https://github.com/explodinggradients/ragas/compare/0.0.7...v0.0.8
feat: added langchains LLM by @jjmachan in https://github.com/explodinggradients/ragas/pull/66
Full Changelog: https://github.com/explodinggradients/ragas/compare/0.0.6...0.0.7
Context Relevancy v2 - measures how relevant is the retrieved context to the prompt. This is done using a combination of OpenAI models and cross-encod
context_relavency by @jjmachan in https://github.com/explodinggradients/ragas/pull/62Full Changelog: https://github.com/explodinggradients/ragas/compare/0.0.5...0.0.6
chore: removed lfs files by @jjmachan in https://github.com/explodinggradients/ragas/pull/56
Full Changelog: https://github.com/explodinggradients/ragas/compare/0.0.4...0.0.5
Rename metrics by @shahules786 in https://github.com/explodinggradients/ragas/pull/48
Full Changelog: https://github.com/explodinggradients/ragas/compare/v0.0.3...0.0.4
v0.0.3 is a major design change
v0.0.3 is a major design change
We have added 3 new metrics that help you answer how factually correct is your generated answers, how relevant are the answers to the question and how relevant are the contexts returned form the retriever to the questions. This gives you a sense of the performance of both you generation and retrieval steps. We also have a "ragas_score" which is unified score to give a single metric about your pipelines.
checkout the quickstart to see how it works: https://github.com/explodinggradients/ragas/blob/main/examples/quickstart.ipynb
Nothing published for this version
Update README by @shahules786 in https://github.com/explodinggradients/ragas/pull/27
Full Changelog: https://github.com/explodinggradients/ragas/compare/0.0.1...0.0.2
fix: added a spacy check before installation by @jjmachan in https://github.com/explodinggradients/ragas/pull/22
MVP release!!!
Full Changelog: https://github.com/explodinggradients/ragas/compare/0.0.1a6...0.0.1
Nothing published for this version
chore: fix issues with released package by @jjmachan in https://github.com/explodinggradients/ragas/pull/20
Full Changelog: https://github.com/explodinggradients/ragas/compare/0.0.1a5...0.0.1a6
chore: mention release environment by @jjmachan in https://github.com/explodinggradients/ragas/pull/19
testing release workflow
Full Changelog: https://github.com/explodinggradients/ragas/compare/0.0.1a4...0.0.1a5
Your coding agent can read these notes before it upgrades. Set up the MCP server →