Skip to main content
Langfuse logo
  • Category: developer tools
  • Auth: API_KEY
  • Composio-managed OAuth available? N/A
  • Tools: 13
  • Triggers: 0
  • Slug: LANGFUSE
  • Version: 20261101_00

Tools

Slug: LANGFUSE_ADD_ANNOTATION_QUEUE_ITEMAdd a trace, observation, or session to a Langfuse annotation queue by queue ID and object ID. Optionally set the item’s annotation status.

Input Parameters

string ("PENDING" | "COMPLETED")
Item status. Defaults to PENDING for new queue items.
string
required
Unique identifier of the annotation queue to add the item to.
string
required
ID of the trace, observation, or session to annotate.
string ("TRACE" | "OBSERVATION" | "SESSION")
required
Type of the object to add to the annotation queue.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_ASSIGN_ANNOTATION_QUEUE_USERAssign a user to a Langfuse annotation queue by queue ID and user ID. Returns the user, queue, and project IDs for the created assignment.

Input Parameters

string
required
Unique identifier of the user to assign to the queue.
string
required
Unique identifier of the annotation queue to assign the user to.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_CHECK_HEALTHCheck the health of the Langfuse API and database. Returns the server version and health status.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_CREATE_ANNOTATION_QUEUECreate an annotation queue in the authenticated Langfuse project for human evaluation, using the supplied score configuration IDs. Returns the created queue and its ID.

Input Parameters

string
required
Name of the annotation queue to create.
string
Optional description of the annotation queue.
array
required
Score configuration IDs to use for human evaluation in this queue.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_CREATE_COMMENTCreate a comment on an existing Langfuse trace, observation, session, or prompt in the specified project. Supports Markdown content and an optional author who belongs to the project’s organization. Returns the created comment ID.

Input Parameters

string
required
Comment content, optionally including Markdown; limited to 5000 characters.
string
required
ID of an existing object to attach the comment to; invalid IDs cause an error.
string
required
ID of the project to attach the comment to.
string
required
Type of object to attach the comment to: TRACE, OBSERVATION, SESSION, or PROMPT (uppercase).
string
Optional ID of the comment author. The user must belong to the organization that owns the project, otherwise an error is returned.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_CREATE_DATASETCreate a dataset in the connected Langfuse project, optionally with a description, metadata, and JSON Schemas for item inputs and expected outputs. This creates the dataset container; add dataset items separately.

Input Parameters

string
required
Name of the dataset to create.
string
Arbitrary JSON metadata associated with the dataset.
string
Optional dataset description.
string
JSON Schema for validating dataset item inputs. When set, all new and existing dataset items are validated against it.
string
JSON Schema for validating dataset item expected outputs. When set, all new and existing dataset items are validated against it.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_CREATE_DATASET_ITEMCreate a Langfuse dataset item with input, expected output, and metadata. Providing an existing item ID updates that item in the same dataset.

Input Parameters

string
Optional item ID for upsert. Must be unique within the project and cannot be reused across datasets; at most 255 characters.
string
Arbitrary JSON input for the dataset item.
string ("ACTIVE" | "ARCHIVED")
Item status. Defaults to ACTIVE for newly created items.
string
Arbitrary JSON metadata associated with the dataset item.
string
required
Name of the dataset to contain the item.
string
ID of the trace that sourced this dataset item.
string
Arbitrary JSON expected output for the dataset item.
string
ID of the observation that sourced this dataset item.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_CREATE_EVALUATION_RULECreate a Langfuse evaluation rule for incoming observations, using stable evaluator IDs and their latest versions. Explicitly choose enabled: true starts automatic evaluations and may incur model costs; false creates a disabled draft. Omitted filters match all observations and omitted sampling evaluates every match. Rule names need not be unique.

Input Parameters

string
required
Human-readable rule name; need not be unique.
array
AND-combined observation filters. Omit for all observations. Select experiment datasets using datasetId/stringOptions with dataset IDs, and experiment roots using isExperimentItemRootSpan/boolean. Metadata uses stringObject with key; tags and calledToolNames use arrayOptions; parentObservationId uses null; toolCalls uses number.
boolean
required
Required explicit choice: true starts live evaluations immediately and may incur model costs; false creates a disabled draft. True requires evaluators.
number
Fraction of matches to evaluate (0–1). Omit for provider default 1 (every match); explicit null is not accepted.
array
required
Evaluators to attach. An empty list is allowed only for a disabled draft.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_CREATE_EVALUATORCreate a version-1 evaluator in the authenticated Langfuse project. Choose llm_as_judge with a prompt and structured score output, or code with source code and runtime language. Names need not be unique. An evaluator defines how to score data; evaluation rules separately determine which data to evaluate.

Input Parameters

string
required
Human-readable evaluator name; need not be unique.
string ("llm_as_judge" | "code")
required
Evaluator definition type.
string
Required for llm_as_judge: user prompt string or ordered messages. A system message is allowed only first. Omit for code.
string
Required for code: source code executed for matched observations. Omit for llm_as_judge.
string
Optional evaluator description.
object
LLM model configuration; null or omission uses the project’s default evaluation model. Omit for code.
array
LLM default prompt-variable mappings, or null for no default. Map each prompt variable exactly once. Omit for code.
string
Required for llm_as_judge: flat structured score definition. Omit for code.
string ("PYTHON" | "TYPESCRIPT")
Required for code: source runtime language. Omit for llm_as_judge.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_CREATE_MEDIA_UPLOAD_URLObtain a presigned upload URL and media ID for Langfuse media associated with either a trace (optionally an observation) or a dataset item. Requires the media MIME type, byte length, SHA-256 hash, and containing field. Only requests the URL; does not upload a file. The URL can be null if already uploaded.

Input Parameters

string ("input" | "output" | "expectedOutput" | "metadata")
required
Field containing the media: input/output/metadata for a trace, or input/expectedOutput/metadata for a dataset item.
string
Associated trace ID. Null for dataset item media uploads.
string
Associated dataset ID. Null for trace/observation uploads.
string
required
Base64-encoded SHA-256 digest of the media bytes (44 characters), not a hex digest.
string ("image/png" | "image/jpeg" | "image/jpg" | "image/webp" | "image/gif" | "image/svg+xml" | "image/tiff" | "image/bmp" | "image/avif" | "image/heic" | "audio/mpeg" | "audio/mp3" | "audio/wav" | "audio/ogg" | "audio/oga" | "audio/aac" | "audio/mp4" | "audio/flac" | "audio/opus" | "audio/webm" | "video/mp4" | "video/webm" | "video/ogg" | "video/mpeg" | "video/quicktime" | "video/x-msvideo" | "video/x-matroska" | "text/plain" | "text/html" | "text/css" | "text/csv" | "text/markdown" | "text/x-python" | "application/javascript" | "text/x-typescript" | "application/x-yaml" | "application/pdf" | "application/msword" | "application/vnd.ms-excel" | "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet" | "application/zip" | "application/json" | "application/xml" | "application/octet-stream" | "application/vnd.openxmlformats-officedocument.wordprocessingml.document" | "application/vnd.openxmlformats-officedocument.presentationml.presentation" | "application/rtf" | "application/x-ndjson" | "application/vnd.apache.parquet" | "application/gzip" | "application/x-tar" | "application/x-7z-compressed")
required
MIME type of the media record.
integer
required
Size of the media record in bytes.
string
Associated dataset item ID; the item need not exist yet. Pair with datasetId.
string
Associated observation ID within the trace; null for trace-level media.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_CREATE_MODELCreate a custom Langfuse model definition for usage-to-USD cost calculation and optional tokenization. Supply a model name, matching regex, usage unit, and either pricing tiers (recommended) or legacy flat prices. Each tiered model needs exactly one default tier with priority 0 and no conditions.

Input Parameters

string ("CHARACTERS" | "TOKENS" | "MILLISECONDS" | "SECONDS" | "IMAGES" | "REQUESTS")
required
Unit of usage for this model.
string
required
Model definition name. Custom definitions override built-ins; newer applicable definitions take precedence.
string
ISO date-time; apply only to generations newer than this date.
number
Deprecated flat USD price per input unit. Use pricingTiers instead.
number
Deprecated flat USD price per total unit; cannot coexist with inputPrice or outputPrice. Use pricingTiers instead.
number
Deprecated flat USD price per output unit. Use pricingTiers instead.
string ("openai" | "claude")
Tokenizer applied to matching observations.
string
required
Regex matching generation.model; use (?i)^modelname$ for an exact case-insensitive match.
array
Pricing tiers, mutually exclusive with flat prices. Include exactly one default tier with priority 0 and no conditions. Names and priorities must be unique. If omitted, provide flat prices to create a Standard tier.
string
JSON configuration for the selected tokenizer.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_CREATE_PROMPTCreate a new version of a named Langfuse text or chat prompt. Chat prompts require type=‘chat’ and support messages and named placeholders. Optionally attach arbitrary JSON configuration, deployment labels, tags, and a commit message.

Input Parameters

string
required
Full prompt name, including any folder path; at most 255 characters.
array
Tags to apply to all versions of this prompt.
string ("text" | "chat")
Prompt type. Required for chat prompts; text prompts may omit this field or supply null.
string
Arbitrary JSON configuration attached to this prompt version.
array
Deployment labels for this prompt version.
string
required
Text template, or ordered chat messages and named placeholders when type is chat.
string
Commit message for this prompt version.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_CREATE_SCOREAttach an evaluation score to exactly one Langfuse trace, session, or dataset run, optionally narrowing a trace score to an observation.

Input Parameters

string
required
Score name.
string
required
Numeric value for NUMERIC or BOOLEAN scores (BOOLEAN uses 1 or 0), or a string for CATEGORICAL, TEXT, or CORRECTION scores.
string ("API" | "ANNOTATION")
Score source. ANNOTATION requires config_id unless data_type is CORRECTION.
string
Human-readable explanation of the score.
object
Arbitrary JSON metadata to associate with the score.
string
Annotation queue associated with this score.
string
Optional caller-supplied score ID.
string
Trace target. May be combined with observation_id.
string
Score configuration ID used to validate and infer compatible score fields.
string ("NUMERIC" | "BOOLEAN" | "CATEGORICAL" | "TEXT" | "CORRECTION")
Score data type. Langfuse infers it when config_id is set; otherwise it defaults to NUMERIC.
string
Session target.
string
Lowercase alphanumeric environment with hyphens or underscores; must not start with ‘langfuse’.
string
Dataset run or experiment target.
string
Observation target within trace_id. Cannot be used alone.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_CREATE_SCORE_CONFIGCreate a score configuration in the authenticated Langfuse project to define numeric bounds, categorical label/value pairs, boolean scores, or text scores. Boolean categories are autogenerated; omit categories for BOOLEAN configs. Use the returned config ID when creating scores validated against this configuration.

Input Parameters

string
required
Score config name, at most 80 characters. Only letters, numbers, underscores, spaces, periods, parentheses, and hyphens are allowed.
string ("NUMERIC" | "BOOLEAN" | "CATEGORICAL" | "TEXT")
required
Type of scores this config defines.
number
Maximum numerical score value; defaults to positive infinity when not set.
number
Minimum numerical score value; defaults to negative infinity when not set.
array
Custom label/value categories for categorical scores. Boolean categories are autogenerated and cannot be passed.
string
Description shown in the Langfuse UI explaining categories, numeric bounds, or config usage.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_DELETE_DATASET_ITEMDelete a Langfuse dataset item by its ID and all its run items. This action is irreversible.

Input Parameters

string
required
Unique ID of the dataset item to delete.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_DELETE_EVALUATION_RULEDelete a Langfuse evaluation rule by its stable ID, including legacy trace and dataset rules. This removes the live-ingestion rule only; associated evaluators and previously produced scores are preserved.

Input Parameters

string
required
Stable evaluation-rule identifier returned by the evaluation-rule endpoints.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_DELETE_EVALUATORDelete a Langfuse evaluator and all of its stored versions by its stable ID. Associated evaluation-rule assignments are also removed. Scores already produced by the evaluator are preserved.

Input Parameters

string
required
Stable evaluator identifier returned by the evaluator endpoints.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_DELETE_LLM_CONNECTIONDelete a Langfuse LLM connection by its ID. Evaluators that depend on the deleted connection are automatically paused.

Input Parameters

string
required
Identifier of the LLM connection to delete.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_DELETE_MODELDelete a project-owned Langfuse model by its ID. Models managed by Langfuse cannot be deleted; create your own definition with the same modelName to override a managed definition instead. Returns an empty response on success.

Input Parameters

string
required
The unique identifier of the model to delete.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_DELETE_PROMPTDelete Langfuse prompt versions by prompt name. Optionally filter deletion by label or version. If neither label nor version is specified, all versions of the prompt are deleted. Returns an empty response on success.

Input Parameters

string
Delete all prompt versions that have this label, when specified.
integer
Delete only this specific prompt version, when specified.
string
required
Single-segment prompt name; slashes, URLs, and dot segments are rejected.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_DELETE_SCOREDelete a Langfuse score by its ID. Supports both trace and session scores. Returns an empty response on success.

Input Parameters

string
required
The unique Langfuse identifier of the score to delete.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_DELETE_TRACEDelete a specific Langfuse trace by its unique trace ID.

Input Parameters

string
required
The unique Langfuse identifier of the trace to delete.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_DELETE_TRACESDelete multiple Langfuse traces by their trace IDs.

Input Parameters

array
required
List of trace IDs to delete.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_GET_ANNOTATION_QUEUERetrieve one Langfuse annotation queue by its ID.

Input Parameters

string
required
Unique identifier of the annotation queue to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_GET_ANNOTATION_QUEUE_ITEMGet a specific item from a Langfuse annotation queue by queue ID and queue item ID. Returns the associated object, annotation status, and timestamps.

Input Parameters

string
required
Unique identifier of the annotation queue item, not the annotated object ID.
string
required
Unique identifier of the annotation queue containing the item.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_GET_COMMENTRetrieve one comment by its unique Langfuse ID in the authenticated project. Returns the comment content, associated object type and ID, timestamps, and author user ID when available.

Input Parameters

string
required
The unique Langfuse identifier of the comment to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_GET_DATASETRetrieve a Langfuse dataset by name, including its metadata and JSON Schemas for dataset item inputs and expected outputs.

Input Parameters

string
required
Single-segment dataset name; slashes, URLs, and dot segments are rejected.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_GET_DATASET_ITEMRetrieve a single Langfuse dataset item by its ID, including its input, expected output, metadata, source IDs, and resolved media references.

Input Parameters

string
required
Unique ID of the dataset item to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_GET_EVALUATION_RULEGet one Langfuse evaluation rule by its stable identifier, including legacy trace or dataset rules. Returns its enabled state, sampling, stored filters, evaluator assignments, variable mappings, creator, and timestamps.

Input Parameters

string
required
Stable evaluation-rule identifier returned by evaluation-rule endpoints.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_GET_EVALUATORGet one evaluator by its stable identifier in the authenticated Langfuse project. Returns its latest definition, version metadata, effective runtime status, and associated evaluation-rule assignments. Use version history for older definitions.

Input Parameters

string
required
Stable evaluator identifier returned by the evaluator endpoints.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_GET_MEDIARetrieve one media record by its unique Langfuse ID in the authenticated project. Returns the MIME type, size in bytes, upload timestamp, and download URL with its expiry. Does not download the media content.

Input Parameters

string
required
The unique Langfuse identifier of the media record to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_GET_MODELRetrieve one Langfuse-managed or project-custom model definition by ID. Returns model matching rules, tokenizer configuration, usage unit, legacy prices, and conditional pricing tiers used for cost calculation.

Input Parameters

string
required
Unique model definition ID, as returned by listing models.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_GET_PROJECTGet the project associated with the connected project-scoped API key, returned in a data list with its organization, metadata, and retention configuration. No project ID is required. To get all projects using an organization-scoped API key, use the provider’s organization API separately.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_GET_PROMPTRetrieve a Langfuse text or chat prompt by name, optionally selecting a deployment label or exact version and resolving dependencies.

Input Parameters

string
Deployment label. Cannot be combined with version; defaults upstream to production when neither selector is set.
boolean
Resolve prompt dependencies. Set false only to inspect the raw stored prompt.
integer
Exact prompt version. Cannot be combined with label.
string
required
Prompt name, including any folder path. Folder separators are URL-encoded as part of the path value.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_GET_SCORE_CONFIGRetrieve one score configuration by ID in the authenticated Langfuse project. Returns its score data type, numeric bounds, categorical labels, description, timestamps, and archive status.

Input Parameters

string
required
Unique Langfuse score configuration ID, as returned by listing or creating score configurations.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_INGEST_TRACESExport OpenTelemetry traces to Langfuse using OTLP HTTP/JSON with real-time v4 ingestion. Supply resourceSpans containing scopeSpans and spans. Acceptance is asynchronous. Inspect partialSuccess: HTTP 200 can include rejected spans or warnings; do not retry partially accepted batches. This action supports JSON, not binary protobuf or gzip.

Input Parameters

array
required
OTLP ExportTraceServiceRequest resource spans. Use hex trace/span IDs and send both timestamps.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_LIST_ANNOTATION_QUEUE_ITEMSList one page of items in a Langfuse annotation queue, optionally filtered by PENDING or COMPLETED status. Increment page while meta.page is less than meta.totalPages to retrieve subsequent pages.

Input Parameters

integer
Page number to retrieve, starting at 1.
integer
Number of items per page.
string ("PENDING" | "COMPLETED")
Filter items by annotation status.
string
required
Unique identifier of the annotation queue.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_LIST_ANNOTATION_QUEUESList annotation queues configured for human evaluation in the connected Langfuse project.

Input Parameters

integer
Maximum queues in this page.
string
Continuation token returned by the previous call; do not construct it manually.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_LIST_COMMENTSList one page of comments in the authenticated Langfuse project. Optionally filter by object type, object ID, or author user ID. Filtering by object ID requires objectType. To retrieve another page, increment page while page is less than meta.totalPages.

Input Parameters

integer
Page number, starting at 1.
integer
Items per page. Reduce this value if large pages cause API issues.
string
Filter by object ID. Also provide objectType or the API returns an error.
string
Filter by object type (trace, observation, session, prompt).
string
Filter by the comment author’s user ID.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_LIST_DATASET_ITEMSList dataset items, optionally scoped to a dataset, source trace or observation, or historical dataset version.

Input Parameters

integer
Maximum dataset items in this page.
string
Return the dataset state at this UTC RFC 3339 timestamp. Requires dataset_name.
string
Continuation token returned by the previous call. Omit for the first page and do not construct it manually.
string
Dataset name to list items from.
string
Filter by source trace ID.
string
Filter by source observation ID.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_LIST_DATASET_RUN_ITEMSList run items for a specific Langfuse dataset and run name.

Input Parameters

integer
Provider page number, starting at 1.
integer
Maximum run items to return on this page.
string
required
Dataset run name to filter by.
string
required
Unique identifier of the dataset to filter by.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_LIST_DATASETSList datasets available to the connected Langfuse project.

Input Parameters

integer
Maximum datasets in this page.
string
Continuation token returned by the previous call; do not construct it manually.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_LIST_EVALUATION_RULESList one page of evaluation rules in the authenticated Langfuse project, newest creation first. Includes legacy trace and dataset rules for inspection and migration, with stored filters and evaluator assignments. Pass meta.cursor unchanged as cursor to retrieve the next page; an absent or null cursor means there are no more pages.

Input Parameters

integer
Maximum rules to return; defaults to 50 and cannot exceed 100.
string
Opaque cursor from the previous page’s meta.cursor; pass it unchanged.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_LIST_EVALUATORSList one page of evaluators in the authenticated Langfuse project, newest creation first. Each evaluator includes its latest definition, version metadata and evaluation-rule assignments. Pass meta.cursor unchanged as cursor to retrieve the next page; an absent or null cursor means there are no more pages.

Input Parameters

integer
Maximum evaluators to return; defaults to 50 and cannot exceed 100.
string
Opaque cursor from the previous page’s meta.cursor; pass it unchanged.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_LIST_EVALUATOR_VERSIONSList one page of an evaluator’s version history, newest first, for history and audit use cases. Returns each version’s definition and creator metadata. Pass meta.cursor unchanged as cursor for the next page; an absent or null cursor means there are no more pages. For only the latest definition, use Get evaluator.

Input Parameters

integer
Maximum versions to return; defaults to 50 and cannot exceed 100.
string
Opaque cursor from the previous page’s meta.cursor; pass it unchanged.
string
required
Stable evaluator identifier returned by the evaluator endpoints.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_LIST_EXPERIMENT_ITEMSList Langfuse experiment items started on or after a required datetime, ordered by time descending. Export inputs, outputs, expected outputs, metadata, and optional item/trace scores by selecting field groups. Returns one page; pass meta.cursor with the same filters to fetch the next.

Input Parameters

integer
Items per page (maximum 100; provider default 50).
string
Versioned base64url cursor from meta.cursor in the previous response. Omit for the first page and repeat the same filters for subsequent pages.
string
Comma-separated field groups: core, dataset, io, metadata, itemMetadata, experimentMetadata, scores. Defaults to core,dataset when omitted.
string
Comma-separated dataset IDs to include.
string
JSON-encoded array of structured filter conditions. Supported columns: experimentId, experimentName, experimentItemId, datasetId.
integer
Scores per item when scores are requested (maximum and default 50).
string
Comma-separated experiment IDs to include.
string
Include experiment items started before this ISO 8601 datetime.
string
Comma-separated experiment names to include.
string
required
Include experiment items started on or after this ISO 8601 datetime.
string
Comma-separated experiment item IDs to include.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_LIST_EXPERIMENTSList Langfuse experiments active from a required start time, optionally specifying an end time and including metadata and directly attached scores.

Input Parameters

integer
Maximum experiments in this page (1-100).
string
Comma-separated experiment names.
string
Comma-separated field groups to return: core, metadata, scores.
string
Comma-separated dataset IDs.
string
JSON-encoded structured filters over id, name, and datasetId.
string
Continuation cursor returned by the previous call. Omit for the first page.
integer
Maximum attached scores per experiment when fields includes scores (1-50).
string
Include experiments starting before this ISO 8601 timestamp.
string
Comma-separated experiment IDs.
string
required
Include experiments active on or after this ISO 8601 timestamp.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_LIST_LLM_CONNECTIONSList one page of LLM provider connections in the authenticated Langfuse project, including model configuration and masked secrets. To retrieve another page, increment page while page is less than meta.totalPages.

Input Parameters

integer
Page number, starting at 1.
integer
Number of LLM connections per page.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_LIST_MODELSList Langfuse-managed and project-custom model pricing definitions used for usage and cost calculation.

Input Parameters

integer
Maximum model definitions in this page.
string
Continuation token returned by the previous call. Omit for the first page and do not construct this token manually.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_LIST_OBSERVATIONSSearch Langfuse observations such as generations, spans, events, agents, and tool calls, selecting only the field groups needed.

Input Parameters

string
Filter by observation name.
string ("DEBUG" | "DEFAULT" | "WARNING" | "ERROR")
Filter by observation level.
integer
Maximum observations in this page (1-1000).
string
Comma-separated field groups to return: core, basic, time, io, metadata, model, usage, prompt, metrics, trace_context.
string
Filter by associated user ID.
string
Filter by observation version.
string
Filter by trace ID.
string
Filter by session ID.
string
JSON-encoded structured filter array. When set, it takes precedence over individual filters.
string
Continuation cursor returned by the previous call. Omit for the first page.
array
Return observations from any of these environments.
string
Include observations starting before this ISO 8601 timestamp.
string
Comma-separated metadata keys whose values should not be truncated.
string
Include observations starting at or after this ISO 8601 timestamp.
string ("GENERATION" | "SPAN" | "EVENT" | "AGENT" | "TOOL" | "CHAIN" | "RETRIEVER" | "EVALUATOR" | "EMBEDDING" | "GUARDRAIL")
Filter by observation type.
boolean
Filter by logical root status.
string
Filter by physical parent observation ID.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_LIST_PROMPTSList one page of prompt names, types, versions, labels, tags and latest matching configuration in the authenticated Langfuse project. Optionally filter by name, label, tag, update dates or advanced JSON conditions. Returns metadata rather than prompt content; use Get Prompt to retrieve a template. Increment page while meta.page is less than meta.totalPages to retrieve subsequent pages.

Input Parameters

string
Filter by prompt tag.
string
Filter by prompt name.
integer
Page number, starting at 1.
string
Filter by prompt deployment label.
integer
Number of items per page.
string
JSON string of AND-combined conditions, each with type, column, operator, and value. Overrides name, label, tag and date filters; [] applies no filters. Types: string (id/name/type; =, contains, does not contain, starts with, ends with, is not empty); stringOptions (id/name/type; any of, none of; non-empty string array); number (version; =, >, <, >=, <=); datetime (createdAt/updatedAt; >, <, >=, <=; ISO 8601 value); arrayOptions (labels/tags; any of, all of, none of; non-empty string array); stringObject (config; also requires key; =, contains, does not contain, starts with, ends with, is set, is not set; string value, empty for presence checks). Equality is case-sensitive; searches are case-insensitive SQL patterns (% and _ are wildcards, backslash escapes them and must be JSON-escaped; asterisks are literal). Empty config searches mean is set. Filters apply to versions before aggregation, affecting returned versions, labels and lastConfig.
string
Include prompt versions created or updated before this ISO 8601 datetime.
string
Include prompt versions created or updated on or after this ISO 8601 datetime.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_LIST_SCORE_CONFIGSList one page of score configurations in the authenticated Langfuse project, including score types, numeric bounds, categorical labels, and archive status. To retrieve another page, increment page while page is less than meta.totalPages.

Input Parameters

integer
Page number, starting at 1. Omit for the first page.
integer
Items per page. Reduce this value if large pages cause API issues.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_LIST_SCORESSearch numeric, boolean, categorical, text, and correction scores with subject and annotation context.

Input Parameters

integer
Maximum scores in this page (1-100); larger values are rejected.
array
Score names to return.
array
Optional score field groups to include.
array
Exact score values to match; requires one compatible data type.
array
Score sources to return.
array
Annotation queue IDs to return.
array
Score IDs to return.
array
Trace IDs to return; mutually exclusive with session and experiment IDs.
number
Inclusive numeric upper bound; requires data_types=NUMERIC.
number
Inclusive numeric lower bound; requires data_types=NUMERIC.
array
Score configuration IDs to return.
array
Score data types to return.
string
Continuation cursor returned by the previous call.
array
Session IDs to return; mutually exclusive with trace, observation, and experiment IDs.
array
Environments to return.
string
Exclusive score timestamp upper bound.
array
Dataset run or experiment IDs to return; mutually exclusive with other subject filters.
string
Inclusive score timestamp lower bound.
array
Annotation author user IDs to return.
array
Observation IDs to return; requires trace_ids.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_QUERY_METRICSRun an aggregate Langfuse metrics query over observations or numeric, boolean, or categorical scores.

Input Parameters

string ("observations" | "scores-numeric" | "scores-boolean" | "scores-categorical")
required
Langfuse data view to aggregate.
array
Optional typed conditions used to restrict source rows.
array
required
One or more measures and aggregations to calculate.
array
Optional ordered list of result sort rules.
integer
Maximum aggregate rows to return (1-1000).
array
Optional low-cardinality fields by which to group results.
string
required
Exclusive ISO 8601 end of the metrics time range; must be after from_timestamp.
string
required
Inclusive ISO 8601 start of the metrics time range.
integer
Number of histogram bins when using histogram aggregation (1-100).
string ("auto" | "minute" | "hour" | "day" | "week" | "month")
Optional time bucket granularity for grouping results.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_REMOVE_ANNOTATION_QUEUE_ASSIGNMENTRemove a user’s assignment to a Langfuse annotation queue by queue ID and user ID. Returns whether the assignment was removed.

Input Parameters

string
required
Unique identifier of the user whose assignment to the queue is removed.
string
required
Unique identifier of the annotation queue.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_REMOVE_ANNOTATION_QUEUE_ITEMRemove an item from a Langfuse annotation queue using the queue ID and annotation queue item ID.

Input Parameters

string
required
Unique identifier of the annotation queue item to remove.
string
required
Unique identifier of the annotation queue containing the item.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_SUBMIT_FEEDBACKSubmit feedback to Langfuse about its skills, MCP tools, CLI, docs, or public API. Only call after the user has explicitly approved the feedback content for submission; any supplied goal must also be user-approved. Do not include secrets, credentials, customer data, trace payloads, or unrelated use-case details. Not available in the HIPAA cloud region. Returns a feedback correlation ID.

Input Parameters

string
Optional user-approved goal or use case (1–1500 characters when provided). Do not include secrets, customer data, trace payloads, or broad unrelated context.
string
required
Specific skill name, MCP tool name, CLI command, API endpoint path, or docs page path. Use an identifier, not a sentence (1–200 characters).
string
required
Concise feedback text explicitly approved by the user for submission to Langfuse (1–3000 characters). Do not include secrets, credentials, customer data, trace payloads, or unrelated use-case details.
string ("skill" | "mcp-tool" | "cli" | "docs" | "public-api" | "other")
required
Category of the thing the feedback is about.
string
Optional HTTP(S) reference URL; Langfuse stores it as text and does not fetch it.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_UPDATE_ANNOTATION_QUEUE_ITEMUpdate a Langfuse annotation queue item’s status to PENDING or COMPLETED using its queue ID and item ID. Returns the updated queue item.

Input Parameters

string
required
Unique identifier of the annotation queue item to update.
string ("PENDING" | "COMPLETED")
New annotation status for the queue item.
string
required
Unique identifier of the annotation queue.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_UPDATE_EVALUATION_RULEUpdate a Langfuse evaluation rule by its stable ID. Supply only fields to change; explicit nulls are forwarded. Filters and evaluator assignments replace their complete lists. An empty assignment list disables the rule; enabling requires a nonempty resulting list and may incur model costs. Legacy trace and dataset rules only allow deactivation with enabled=false; their name, filters, sampling, and assignments cannot change.

Input Parameters

string
New human-readable rule name.
array
Complete replacement AND-combined observation filters. An empty list matches every incoming observation. Omit to keep the current filters.
boolean
New live-execution state. Enabling may incur model costs and requires a nonempty resulting evaluator assignment list.
number
New fraction of matches to evaluate. Omit to retain the current value.
string
required
Stable evaluation-rule identifier.
array
Complete replacement evaluator list; an empty list disables the rule. Omit to keep current assignments. Null/omitted variableMapping inherits the evaluator’s latest defaults.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_UPDATE_EVALUATORUpdate a Langfuse evaluator by stable identifier. Supply name or description for a metadata-only change without creating a version. To replace a definition, include type and all required definition fields; definitions are replaced, not merged. The evaluator type cannot change. Null description clears it; null or omitted modelConfig selects the project default model. Definition replacement may reactivate evaluators paused for invalid or missing model configuration; other pause reasons require an explicit reactivation check.

Input Parameters

string
New human-readable evaluator name.
string ("llm_as_judge" | "code")
Required for a complete definition replacement; must match the existing evaluator type. Omit for metadata-only changes.
string
Required for llm_as_judge replacement: complete prompt string or ordered messages. A system message is allowed only first.
string
Required for code replacement: complete source code.
string
New description; explicitly set null to clear it.
string
required
Stable evaluator identifier.
object
LLM model configuration; null or omission selects the project’s default evaluation model. Omit for code.
array
Complete replacement LLM default mappings, or null for no default. Map each prompt variable exactly once. Omit for code.
string
Required for llm_as_judge replacement: complete structured score output definition. Omit for code.
string ("PYTHON" | "TYPESCRIPT")
Required for code replacement: source runtime language.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_UPDATE_MEDIAUpdate an existing Langfuse media record with its upload timestamp and HTTP status, and optionally the upload error message and elapsed time. This records the upload result; it does not upload media content. Omitted optional fields are not sent; explicitly supplied null values are forwarded. Returns an empty response on success.

Input Parameters

string
required
The unique Langfuse identifier of the media record.
string
required
The date and time when the media record was uploaded (ISO 8601).
integer
The time in milliseconds it took to upload the media record, or null.
string
The HTTP error message of the upload, or null.
integer
required
The HTTP status code of the upload.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_UPDATE_PROMPT_LABELSUpdate deployment labels for a specific Langfuse prompt version by name and version. Labels are unique across versions of a prompt; the latest label is reserved and managed by Langfuse. Returns the updated text or chat prompt version.

Input Parameters

string
required
Single-segment prompt name; slashes, URLs, and dot segments are rejected.
integer
required
Version of the prompt to update.
array
required
New labels for this prompt version. Labels are unique across versions. The “latest” label is reserved and managed by Langfuse.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_UPDATE_SCORE_CONFIGUpdate an existing Langfuse score configuration by config ID. Change its name, description, archive status, numerical bounds, or categorical label/value pairs. Omitted fields are not sent; explicitly supplied null values are forwarded. Boolean categories are autogenerated and cannot be passed. Returns the updated configuration.

Input Parameters

string
New name, at most 80 characters. Only letters, numbers, underscores, spaces, periods, parentheses, and hyphens are allowed.
string
required
Unique Langfuse score config identifier.
number
Maximum numerical score value; defaults to positive infinity when not set.
number
Minimum numerical score value; defaults to negative infinity when not set.
array
Custom label/value categories for categorical scores. Boolean categories are autogenerated and cannot be passed.
boolean
Whether the score config is archived.
string
Description shown in the Langfuse UI explaining categories, numeric bounds, or config usage.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_UPSERT_LLM_CONNECTIONCreate or update a Langfuse LLM provider connection by provider name.

Input Parameters

object
Adapter-specific configuration, such as a Bedrock region or Vertex AI location.
string ("anthropic" | "openai" | "azure" | "bedrock" | "google-vertex-ai" | "google-ai-studio")
required
Adapter used to call the LLM provider.
string
Optional custom LLM provider or gateway base URL.
string
required
Unique provider name used to create or update the connection.
string
required
Secret credential Langfuse stores for the LLM provider.
array
Custom model names exposed through this connection.
object
Additional headers sent to the LLM provider.
boolean
Whether to include the adapter’s default models.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LANGFUSE_UPSERT_MODELCreate or replace a project-owned Langfuse model definition by ID for usage cost calculation and optional tokenization. Built-in models cannot be modified. This replaces the model definition; supply its desired configuration.

Input Parameters

string
required
ID of the project-owned model to create or replace.
string ("CHARACTERS" | "TOKENS" | "MILLISECONDS" | "SECONDS" | "IMAGES" | "REQUESTS")
required
Usage unit to which model prices apply.
string
required
Model definition name. Custom definitions override built-ins; the newest applicable start date wins.
string
Apply only to generations newer than this ISO 8601 date.
number
Deprecated: USD per input unit. Prefer pricingTiers.
number
Deprecated: USD per total unit; cannot accompany input/output prices. Prefer pricingTiers.
number
Deprecated: USD per output unit. Prefer pricingTiers.
string ("openai" | "claude")
Tokenizer applied to matching observations, if configured.
string
required
Regex matching generation.model. Use (?i)^modelname$ for an exact case-insensitive match.
array
Pricing tiers, mutually exclusive with flat prices. Include exactly one default tier with isDefault=true, priority=0 and conditions=[]. Names and priorities must be unique and each tier needs a price. If omitted, provide flat prices; Langfuse creates a Standard default tier.
string
Arbitrary JSON configuration for the selected tokenizer.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not