Langfuse

• New traceRuns when a new trace arrives in Langfuse, of every name or the one you choose, with a tag or for a user, with its input and output. Traces from before the workflow was turned on don't start it.
• New scoreRuns when a trace, observation or session is scored, such as a low evaluation score or a user's thumbs down: by score name, and at most or at least a value, or equal to one.
• New prompt versionRuns when a prompt gets a new version, or a new prompt is made, with its text, labels and config: of every prompt or the one you choose.
• Prompt label movedRuns when a label such as production moves to another version of a prompt, such as when a new version is promoted or rolled back, with the version that has it now.

• List tracesList recent traces, the latest first, by name, user, session, tags and environment, with each one's input, output, time taken, cost and tokens.
• Get traceGet a trace with every observation in it (each step, model call, tokens and cost) and its scores.
• List observationsList recent observations, the latest first: generations of a model, the steps of one trace, or the ones that went wrong, with their tokens and cost.
• Get sessionGet a session (a conversation) with its traces in order, their inputs and outputs, and what it cost.
• Log traceLog a trace to Langfuse, such as a model call a workflow made: one span or generation with its input, output, user, session, tags and, for a generation, model, tokens and cost.
• Add observation to traceAdd a step to a trace logged earlier: a span, a generation (with model, tokens and cost), an event or a tool call, inside the trace or one of its observations.
• Delete traceDelete a trace with its observations and scores, such as when a user asks for their data to be removed. Langfuse deletes it in the background.
• Add scoreScore a trace, an observation in it, or a session: a number, true or false, a category or text, such as a user's thumbs down or a reviewer's rating.
• List scoresList recent scores, the latest first, by name, trace, session, source and value range, such as every low helpfulness score this week, with their average.
• Delete scoreDelete a score, such as one given by mistake.
• List score configsList the project's score configs: each score's name, type, allowed range or categories.
• Get promptGet a prompt by label (production unless you pick another) or version, with its variables filled in, ready to send to a model, as text or chat messages, and its config.
• List promptsList prompts with their versions, labels and tags.
• Create prompt versionSave a new version of a prompt, or a new prompt: text, or chat messages, with labels such as staging, tags and a config.
• Label prompt versionMove labels such as production to a version of a prompt; they leave the version that had them. This is how a new version is promoted, or an old one brought back.
• Delete promptDelete one version of a prompt, or the whole prompt with every version.
• Create datasetCreate a dataset to collect test cases in, such as questions with their right answers. One with that name already is updated.
• Add dataset itemAdd a test case to a dataset: an input with the expected output, such as a question a user asked and the answer it should have got, optionally from a trace.
• List dataset itemsList a dataset's active items, the newest first, with their inputs and expected outputs. Langfuse leaves archived items out.
• Delete dataset itemDelete an item from its dataset, with its results in past runs.
• List dataset runsList a dataset's runs (experiments), the latest first, with how many items each ran and their scores.
• Get daily usageGet cost, tokens, traces and observations per day, for the whole project or one trace name, user, tag or environment, optionally split by model: for a daily cost report or a budget alert.
• Add commentAdd a comment to a trace, observation, session or prompt, such as what a reviewer found or what was done about it.
• List commentsList comments, the newest first, on one trace, observation, session or prompt, or on every one of a kind.

No actions match that.