Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[ML-OB] ragas evaluation integration #27217

Open
wants to merge 17 commits into
base: master
Choose a base branch
from
Open

Conversation

lievan
Copy link
Contributor

@lievan lievan commented Jan 21, 2025

What does this PR do? What is the motivation?

Introduce LLM Observability's integration with the RAGAS evaluation framework

Existing LLM integrations are all tracing related - by turning one of them on, a user gets automatic tracing if they use a LLM library we integration with

Our ragas integration is the first "evaluations" integration - we're aiming to provide a similar experience by allowing users to get evaluations, out of the box, from the ragas open source framework simply by flipping on an environment variable

Merge instructions

Merge readiness:

  • Ready for merge

Merge queue is enabled in this repo. To have it automatically merged after it receives the required reviews, create the PR (from a branch that follows the <yourname>/description naming convention) and then add the following PR comment:

/merge

Additional notes

@lievan lievan changed the title [MLOB] ragas evaluation integration [ML-OB] ragas evaluation integration Jan 21, 2025
@github-actions github-actions bot added the Architecture Everything related to the Doc backend label Jan 22, 2025
@cswatt cswatt added the editorial review Waiting on a more in-depth review label Jan 27, 2025
@cswatt
Copy link
Contributor

cswatt commented Jan 27, 2025

Added DOCS-9960 to track review

@github-actions github-actions bot added Images Images are added/removed with this PR Guide Content impacting a guide labels Feb 11, 2025
@cswatt cswatt marked this pull request as ready for review February 11, 2025 01:05
@cswatt cswatt requested a review from a team as a code owner February 11, 2025 01:05
@cswatt
Copy link
Contributor

cswatt commented Feb 11, 2025

Hold for merge until ddtrace 3.0.0 is released

Copy link
Contributor

@jhgilbert jhgilbert left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Approved with some suggestions, thanks!


3. Run the script with the Ragas Faithfulness evaluation enabled:
```bash
DD_LLMOBS_EVALUATORS=ragas_faithfulness DD_ENV=dev DD_API_KEY=<YOUR-DD-API-KEY> DD_SITE=datadoghq.com python quickstart.py
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It seems like you're intentionally hyphenating your placeholders to distinguish them from Bash vars etc., so I won't make suggestions on those.

content/en/llm_observability/ragas_evaluations.md Outdated Show resolved Hide resolved
content/en/llm_observability/ragas_evaluations.md Outdated Show resolved Hide resolved
content/en/llm_observability/ragas_evaluations.md Outdated Show resolved Hide resolved
content/en/llm_observability/ragas_evaluations.md Outdated Show resolved Hide resolved
content/en/llm_observability/ragas_evaluations.md Outdated Show resolved Hide resolved
content/en/llm_observability/ragas_evaluations.md Outdated Show resolved Hide resolved
content/en/llm_observability/ragas_evaluations.md Outdated Show resolved Hide resolved
content/en/llm_observability/ragas_evaluations.md Outdated Show resolved Hide resolved
content/en/llm_observability/ragas_evaluations.md Outdated Show resolved Hide resolved
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Architecture Everything related to the Doc backend editorial review Waiting on a more in-depth review Guide Content impacting a guide Images Images are added/removed with this PR
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants