Get customers
Answer customers
Work for you
Reach people
Give agents tools
Run and ship
Manage prompts, evaluation datasets, observations, scores and comments
Read the project associated with this project API key.
List prompt metadata, versions and labels.
5 fields
Get a prompt, optionally selecting its version or label.
3 fields
Create a text prompt or a new version of an existing prompt.
Replace a prompt version's deployment labels; labels move between versions.
List evaluation datasets.
2 fields
Get dataset metadata by name.
1 field
Create an evaluation dataset.
List dataset items, optionally filtering by dataset and source trace.
4 fields
Get one dataset item.
Create an item or update the supplied project-unique item ID.
Irreversibly delete a dataset item and all its run items.
Read observation rows using the current v2 cursor API.
6 fields
Read evaluation scores using the current v3 cursor API.
Submit one numeric trace score for asynchronous processing.
Delete a score by its Langfuse ID.
List comments in the project.
Get a comment by ID.
Attach a comment to a trace, observation, session or prompt.
