Ragas
Evaluate RAG and LLM applications with automated metrics and scoring.
Prompts, structured output and evals PyPI Apache-2.0
How Ragas is used
Ragas is a dependency in 3 of the 6,208 public GitHub projects set up for AI coding agents that we scanned, too few to describe it from them alone. Our scan also samples projects by dependency (Solana 2,661, Ethereum and EVM 1,496, 3D and games 2,818, agent frameworks and SDKs 10,983); counting those, it appears in 70 projects, and what it is used with below comes from all of them. The most used alternative in our scan is Azure AI Evaluation (4 projects). Projects that use it most often also use LangChain (91.4%), python-dotenv (75.7%), pandas (60.0%).
Ragas popularity over time
Gid Score 54: downloads 53, use in agent projects 46, GitHub stars 58, downloads trend 64 (each 0-100). How it is calculated.
Often used with Ragas
| LangChain | 91.4% of Ragas projects · 45.0× more than average |
|---|---|
| python-dotenv | 75.7% of Ragas projects · 8.3× more than average |
| pandas | 60.0% of Ragas projects · 14.0× more than average |
| NumPy | 60.0% of Ragas projects · 10.3× more than average |
| Pydantic | 60.0% of Ragas projects · 6.9× more than average |
| Hugging Face Datasets | 57.1% of Ragas projects · 141.9× more than average |
| OpenAI Python Library | 55.7% of Ragas projects · 14.1× more than average |
| Sentence Transformers | 55.7% of Ragas projects · 42.2× more than average |
From all 70 projects in our scan that use Ragas, including the dependency samples.
Install
| Package | pip install ragas |
|---|---|
| Main stacks | Python (70) |
| Example projects | AlibabaCloudDocs/aliyun_acp_learning, Decade-qiu/CookHero, FareedKhan-dev/complex-RAG-guide, aws-samples/sample-getting-started-with-strands-agents-course, brevdev/workshop-build-an-agent |
Alternatives to Ragas
Tools that do the same job, so a project picks one or the other. Add-ons and libraries used alongside Ragas are not listed here; they are in "Often used with".
| Tool | Gid Score | Used in agent projects | Downloads / wk | GitHub stars | License |
|---|---|---|---|---|---|
| Azure AI Evaluation pypi Microsoft evaluation library for assessing LLM and AI application quality. |
39 | 4 (0.2%) | 42.1K | 5,621 | MIT |
More in Prompts, structured output and evals: Ultracite tiktoken (Python) tokenizers LangSmith Langfuse (Python) GPT Tokenizer TokenLens @graphql-codegen/typescript-operations