openfuse

Create an annotation queue, a worklist that collects trace or observation items for human review and scoring.

Assign a project user to an annotation queue so they can work through its review items.

Add an annotation queue item, one trace or observation to review, to a queue.

Remove a project user's assignment from an annotation queue.

Remove an annotation queue item, the queued trace or observation, from a queue.

Get an annotation queue, a worklist of trace or observation items for human review and scoring, by ID.

Get an annotation queue item, one queued trace or observation with review status, by queue ID and item ID.

List annotation queue items, each linking one trace or observation to a queue with a review status, with optional status filtering.

List annotation queues, worklists that collect trace or observation items for human review and scoring, with pagination.

Update an annotation queue item's review status, such as pending or completed.

Create a comment on a trace, observation, session, or prompt.

Get a comment by ID from the current Langfuse project.

List comments in the current Langfuse project, optionally filtered by object or author.

Create a dataset run item, a result that links one dataset item to a trace or observation in a dataset run.

Delete a dataset item, one example in a dataset, and all its run items.

Delete a dataset run by dataset ID and run ID, and enqueue deletion of its run items.

Get a dataset, a named collection of input and optional expected-output examples for experiments and evaluations, by ID.

Get a dataset item, one example in a dataset with input and optional expected output, by ID.

Get a dataset run, one experiment or evaluation execution over a dataset, and its run items by dataset ID and run ID.

List dataset items, individual examples with input and optional expected output, optionally filtered by dataset ID, source trace, source observation, or version.

List dataset run items, each linking one dataset item to a trace or observation within a dataset run, by dataset ID and run ID.

List dataset runs, each experiment or evaluation execution over a dataset, by dataset ID.

List datasets, named collections of input and optional expected-output examples for experiments and evaluations. Optionally filter by dataset name to find a dataset ID.

Upsert a dataset, a named collection of input and optional expected-output examples for experiments and evaluations.

Upsert a dataset item (one example in a dataset) by dataset ID

Delete an evaluation rule by id. This stops the rule from evaluating new items and cannot be undone.

Fetch a single evaluation rule by id, including its evaluator reference, target, filter, variable mapping, sampling, and status.

Fetch a single evaluator by id, including its prompt or source code, output definition, and how many evaluation rules reference it.

List evaluation rules in the current Langfuse project. Each rule attaches an evaluator to incoming observations or experiment items. Results are paginated.

List evaluators (llm_as_judge and code) defined in the current Langfuse project. Results are paginated.

Check Langfuse API health. Optionally verify database availability and recent trace/observation ingestion.

Fetch metadata and a signed download URL for one media asset.

Discover which Langfuse metrics can be analyzed and how to group, filter, aggregate, and time-bucket them before calling queryMetrics.

Answer analytics questions about the current Langfuse project, such as usage over time, model costs, latency, errors, scores, or grouped breakdowns by environment, trace, observation, model, user, session, tag, or score name.

Create a custom model definition for cost tracking/tokenization in the current project.

Delete a custom model definition from the current project. Built-in models cannot be deleted.

Get a model definition by ID from the current project scope.

List custom and Langfuse-managed model definitions visible to the current project.

Create a score configuration. Supports numeric, categorical, boolean, and text configs. Boolean configs automatically receive True and False categories.

Delete a score configuration from the current Langfuse project by archiving it.

Fetch one score configuration by ID from the current Langfuse project. Returns the public score config object directly.

List score configurations. Returns exactly data and meta at the top level.

Update a score configuration. Use this to rename, describe, or adjust allowed numeric/category fields.

Get the current weather in a location

Search the web

Get a joke from normalized input

Get a joke from metadata