-
Notifications
You must be signed in to change notification settings - Fork 170
Lotte/gtm 1752 evaluation core concepts page #2425
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
base: main
Are you sure you want to change the base?
Lotte/gtm 1752 evaluation core concepts page #2425
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
|
||
| Live evaluations are used to monitor what's happening live in production. This is done by evaluating live traces. | ||
|
|
||
| Real users will always find edge cases you didn't anticipate. When you find edge cases through live evaluation, you can add them to your experiment datasets so that you can catch unexpected behavior during |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Sentence ending missing
|
|
||
| ## Evaluation Core Concepts | ||
|
|
||
| ### What is evaluation? |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
High level, I think I would map the headlines we have on this page, closely to the two sub-sections "Evaluations" in Langfuse has: Experiments and Evaluation Methods. I would therefore structure the page as follows:
- Experiments in Langfuse
Show what an experiment is, what is needed for it and link to the quickstart
I like the diagram you created! It it possible to make it either more Langfuse style or use a mermide diagram? - Evaluation methods
Show that you can 1) evaluate Experiments and 2) evaluate Live data - Evaluation Loop Overview
| sidebarTitle: Data Model | ||
| --- | ||
|
|
||
| This page describes the data model for evaluation-related objects in Langfuse. For an overview of how these objects work together, see the [Core Concepts](/docs/evaluation/core-concepts) page. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
In the tracing and prompt management section, we combined the datamodel into the concepts page. Do you think this would not work for Evaluations?
No description provided.