Skip to main content

​
API Overview

​
class AggregationType

Aggregation functions supported by feedback and call stats metrics.

​
class AliasesListReq

Pydantic Fields:
  • project_id: <class 'str'>
  • wb_user_id: str | None

​
class AliasesListRes

Pydantic Fields:
  • aliases: list[str]

​
class AnnotationQueueAddCallsReq

Request to add calls to an annotation queue in batch. Extends AnnotationQueueAddCallsBody by adding queue_id for internal API usage. Pydantic Fields:
  • project_id: <class 'str'>
  • call_ids: list[str]
  • display_fields: list[str]
  • queue_id: <class 'str'>
  • wb_user_id: str | None

​
class AnnotationQueueAddCallsRes

Response from adding calls to a queue. Pydantic Fields:
  • added_count: <class 'int'>
  • duplicates: <class 'int'>

​
class AnnotationQueueCreateReq

Request to create a new annotation queue. Pydantic Fields:
  • project_id: <class 'str'>
  • name: <class 'str'>
  • description: <class 'str'>
  • scorer_refs: list[str]
  • wb_user_id: str | None

​
class AnnotationQueueCreateRes

Response from creating an annotation queue. Pydantic Fields:
  • id: <class 'str'>

​
class AnnotationQueueDeleteReq

Request to delete (soft-delete) an annotation queue. Pydantic Fields:
  • project_id: <class 'str'>
  • queue_id: <class 'str'>
  • wb_user_id: str | None

​
class AnnotationQueueDeleteRes

Response from deleting an annotation queue. Pydantic Fields:
  • queue: <class 'AnnotationQueueSchema'>

​
class AnnotationQueueItemSchema

Schema for annotation queue item responses. Pydantic Fields:
  • id: <class 'str'>
  • project_id: <class 'str'>
  • queue_id: <class 'str'>
  • call_id: <class 'str'>
  • call_started_at: <class 'datetime.datetime'>
  • call_ended_at: datetime.datetime | None
  • call_op_name: <class 'str'>
  • call_trace_id: <class 'str'>
  • display_fields: list[str]
  • added_by: str | None
  • annotation_state: typing.Literal['unstarted', 'in_progress', 'completed', 'skipped']
  • annotator_user_id: str | None
  • created_at: <class 'datetime.datetime'>
  • created_by: <class 'str'>
  • updated_at: <class 'datetime.datetime'>
  • deleted_at: datetime.datetime | None
  • position_in_queue: int | None

​
class AnnotationQueueItemsQueryReq

Request to query items in an annotation queue. Extends AnnotationQueueItemsQueryBody by adding queue_id for internal API usage. Pydantic Fields:
  • project_id: <class 'str'>
  • filter: weave.trace_server.common_interface.AnnotationQueueItemsFilter | None
  • sort_by: list[weave.trace_server.common_interface.SortBy] | None
  • limit: int | None
  • offset: int | None
  • include_position: <class 'bool'>
  • queue_id: <class 'str'>

​
class AnnotationQueueItemsQueryRes

Response from querying annotation queue items. Pydantic Fields:
  • items: list[AnnotationQueueItemSchema]

​
class AnnotationQueueReadReq

Request to read a specific annotation queue. Pydantic Fields:
  • project_id: <class 'str'>
  • queue_id: <class 'str'>

​
class AnnotationQueueReadRes

Response from reading an annotation queue. Pydantic Fields:
  • queue: <class 'AnnotationQueueSchema'>

​
class AnnotationQueueSchema

Schema for annotation queue responses. Pydantic Fields:
  • id: <class 'str'>
  • project_id: <class 'str'>
  • name: <class 'str'>
  • description: <class 'str'>
  • scorer_refs: list[str]
  • created_at: <class 'datetime.datetime'>
  • created_by: <class 'str'>
  • updated_at: <class 'datetime.datetime'>
  • deleted_at: datetime.datetime | None

​
class AnnotationQueueStatsSchema

Statistics for a single annotation queue. Pydantic Fields:
  • queue_id: <class 'str'>
  • total_items: <class 'int'>
  • completed_items: <class 'int'>

​
class AnnotationQueueUpdateReq

Request to update an annotation queue. All fields except project_id and queue_id are optional - only provided fields will be updated. Pydantic Fields:
  • project_id: <class 'str'>
  • queue_id: <class 'str'>
  • name: str | None
  • description: str | None
  • scorer_refs: list[str] | None
  • wb_user_id: str | None

​
class AnnotationQueueUpdateRes

Response from updating an annotation queue. Pydantic Fields:
  • queue: <class 'AnnotationQueueSchema'>

​
class AnnotationQueuesQueryReq

Request to query annotation queues for a project. Pydantic Fields:
  • project_id: <class 'str'>
  • name: str | None
  • sort_by: list[weave.trace_server.common_interface.SortBy] | None
  • limit: int | None
  • offset: int | None

​
class AnnotationQueuesQueryRes

Response from querying annotation queues. Pydantic Fields:
  • queues: list[AnnotationQueueSchema]

​
class AnnotationQueuesStatsReq

Request to get stats for multiple annotation queues. Pydantic Fields:
  • project_id: <class 'str'>
  • queue_ids: list[str]

​
class AnnotationQueuesStatsRes

Response with stats for multiple annotation queues. Pydantic Fields:
  • stats: list[AnnotationQueueStatsSchema]

​
class AnnotatorQueueItemsProgressUpdateReq

Request to update the annotation state of a queue item for the current annotator. Valid state transitions:
  • (absence) -> ‘in_progress’: Mark item as in progress (only when no record exists)
  • (absence) -> ‘completed’ or ‘skipped’: Directly complete/skip item
  • ‘in_progress’ or ‘unstarted’ -> ‘completed’ or ‘skipped’: Complete/skip started item
  • same_state -> same_state: Idempotent no-op (returns existing item unchanged)
Pydantic Fields:
  • project_id: <class 'str'>
  • queue_id: <class 'str'>
  • item_id: <class 'str'>
  • annotation_state: <class 'str'>
  • wb_user_id: str | None

​
class AnnotatorQueueItemsProgressUpdateRes

Response from updating annotation state. Pydantic Fields:
  • item: <class 'AnnotationQueueItemSchema'>

​
class CallBatchEndMode

Pydantic Fields:
  • mode: <class 'str'>
  • req: <class 'CallEndReq'>

​
class CallBatchStartMode

Pydantic Fields:
  • mode: <class 'str'>
  • req: <class 'CallStartReq'>

​
class CallCreateBatchReq

Pydantic Fields:
  • batch: list[CallBatchStartMode | CallBatchEndMode]

​
class CallCreateBatchRes

Pydantic Fields:
  • res: list[CallStartRes | CallEndRes]

​
class CallEndReq

Pydantic Fields:
  • end: <class 'EndedCallSchemaForInsert'>

​
class CallEndRes

​
class CallEndV2Req

Request for ending a single call via v2 API. Pydantic Fields:
  • end: <class 'EndedCallSchemaForInsertWithStartedAt'>

​
class CallEndV2Res

Response for ending a single call via v2 API.

​
class CallMetricSpec

Specification for a call-level metric to aggregate (not grouped by model). Pydantic Fields:
  • metric: typing.Literal['latency_ms', 'call_count', 'error_count']
  • aggregations: list[AggregationType]
  • percentiles: list[float]

​
class CallReadReq

Pydantic Fields:
  • project_id: <class 'str'>
  • id: <class 'str'>
  • include_costs: bool | None
  • include_storage_size: bool | None
  • include_total_storage_size: bool | None

​
class CallReadRes

Pydantic Fields:
  • call: CallSchema | None

​
class CallSchema

Pydantic Fields:
  • id: <class 'str'>
  • project_id: <class 'str'>
  • op_name: <class 'str'>
  • display_name: str | None
  • trace_id: <class 'str'>
  • parent_id: str | None
  • thread_id: str | None
  • turn_id: str | None
  • started_at: <class 'datetime.datetime'>
  • attributes: dict[str, typing.Any]
  • inputs: dict[str, typing.Any]
  • ended_at: datetime.datetime | None
  • exception: str | None
  • output: typing.Any | None
  • summary: SummaryMap | None
  • wb_user_id: str | None
  • wb_username: str | None
  • wb_run_id: str | None
  • wb_run_step: int | None
  • wb_run_step_end: int | None
  • deleted_at: datetime.datetime | None
  • expire_at: datetime.datetime | None
  • storage_size_bytes: int | None
  • total_storage_size_bytes: int | None

​
method serialize_typed_dicts

​
class CallStartReq

Pydantic Fields:
  • start: <class 'StartedCallSchemaForInsert'>

​
class CallStartRes

Pydantic Fields:
  • id: <class 'str'>
  • trace_id: <class 'str'>

​
class CallStartV2Req

Request for starting a single call via v2 API. Pydantic Fields:
  • start: <class 'StartedCallSchemaForInsert'>

​
class CallStartV2Res

Response for starting a single call via v2 API. Pydantic Fields:
  • id: <class 'str'>
  • trace_id: <class 'str'>

​
class CallStatsReq

Request for aggregated call statistics over a time range. Pydantic Fields:
  • project_id: <class 'str'>
  • start: <class 'datetime.datetime'>
  • end: datetime.datetime | None
  • granularity: int | None
  • usage_metrics: list[UsageMetricSpec] | None
  • call_metrics: list[CallMetricSpec] | None
  • filter: CallsFilter | None
  • timezone: <class 'str'>

​
method validate_date_range

Ensure call stats requests are bounded to a safe date range.

​
class CallStatsRes

Response containing time-series call statistics. Pydantic Fields:
  • start: <class 'datetime.datetime'>
  • end: <class 'datetime.datetime'>
  • granularity: <class 'int'>
  • timezone: <class 'str'>
  • usage_buckets: list[dict[str, typing.Any]]
  • call_buckets: list[dict[str, typing.Any]]

​
class CallUpdateReq

Pydantic Fields:
  • project_id: <class 'str'>
  • call_id: <class 'str'>
  • display_name: str | None
  • wb_user_id: str | None

​
class CallUpdateRes

​
class CallsDeleteReq

Pydantic Fields:
  • project_id: <class 'str'>
  • call_ids: list[str]
  • wb_user_id: str | None

​
class CallsDeleteRes

Pydantic Fields:
  • num_deleted: <class 'int'>

​
class CallsFilter

Pydantic Fields:
  • op_names: list[str] | None
  • input_refs: list[str] | None
  • output_refs: list[str] | None
  • parent_ids: list[str] | None
  • trace_ids: list[str] | None
  • call_ids: list[str] | None
  • thread_ids: list[str] | None
  • turn_ids: list[str] | None
  • trace_roots_only: bool | None
  • wb_user_ids: list[str] | None
  • wb_run_ids: list[str] | None

​
class CallsQueryReq

Pydantic Fields:
  • project_id: <class 'str'>
  • filter: CallsFilter | None
  • limit: int | None
  • offset: int | None
  • sort_by: list[weave.trace_server.common_interface.SortBy] | None
  • query: weave.trace_server.interface.query.Query | None
  • include_costs: bool | None
  • include_feedback: bool | None
  • include_storage_size: bool | None
  • include_total_storage_size: bool | None
  • include_usernames: bool | None
  • columns: list[str] | None
  • expand_columns: list[str] | None
  • return_expanded_column_values: bool | None

​
class CallsQueryRes

Pydantic Fields:
  • calls: list[CallSchema]

​
class CallsQueryStatsReq

Pydantic Fields:
  • project_id: <class 'str'>
  • filter: CallsFilter | None
  • query: weave.trace_server.interface.query.Query | None
  • limit: int | None
  • include_total_storage_size: bool | None
  • expand_columns: list[str] | None

​
class CallsQueryStatsRes

Pydantic Fields:
  • count: <class 'int'>
  • has_more: <class 'bool'>
  • total_storage_size_bytes: int | None

​
class CallsScoreReq

Request to enqueue scoring jobs for a list of calls. Scoring is performed asynchronously by the call_scoring_worker, which consumes messages from Kafka and applies each scorer_ref to each call_id. Pydantic Fields:
  • project_id: <class 'str'>
  • call_ids: list[str]
  • scorer_refs: list[str]
  • wb_user_id: str | None

​
class CallsScoreRes

Empty response for calls_score. Defined as a model (rather than returning None) to follow the convention used throughout this interface and to allow fields to be added later without a breaking change.

​
class CallsUpsertCompleteReq

Request for upserting a batch of completed calls. Pydantic Fields:
  • batch: list[CompletedCallSchemaForInsert]

​
class CallsUpsertCompleteRes

Response for upserting a batch of completed calls.

​
class CallsUsageReq

Request to compute aggregated usage for multiple root calls. This endpoint returns usage metrics for each requested root call, where each root’s metrics include the sum of its own usage plus all descendants’ usage. Note: All matching calls are loaded into memory for aggregation. For very large result sets (>10k calls), consider batching root call IDs or using narrower filters at the application layer. Pydantic Fields:
  • project_id: <class 'str'>
  • call_ids: list[str]
  • include_costs: <class 'bool'>
  • limit: <class 'int'>

​
class CallsUsageRes

Response with aggregated usage metrics per root call. Pydantic Fields:
  • call_usage: dict[str, dict[str, LLMAggregatedUsage]]
  • unfinished_call_ids: list[str]

​
class CompletedCallSchemaForInsert

Schema for inserting a completed call directly. This represents a call that is already finished at insertion time, with both start and end information provided together. Used by the calls_complete endpoint. Pydantic Fields:
  • project_id: <class 'str'>
  • id: <class 'str'>
  • trace_id: <class 'str'>
  • op_name: <class 'str'>
  • started_at: <class 'datetime.datetime'>
  • ended_at: <class 'datetime.datetime'>
  • display_name: str | None
  • parent_id: str | None
  • thread_id: str | None
  • turn_id: str | None
  • attributes: dict[str, typing.Any]
  • inputs: dict[str, typing.Any]
  • output: typing.Any | None
  • summary: <class 'SummaryInsertMap'>
  • otel_dump: dict[str, typing.Any] | None
  • exception: str | None
  • wb_user_id: str | None
  • wb_run_id: str | None
  • wb_run_step: int | None
  • wb_run_step_end: int | None

​
method serialize_typed_dicts

​
class CompletionsCreateReq

Pydantic Fields:
  • project_id: <class 'str'>
  • inputs: <class 'CompletionsCreateRequestInputs'>
  • wb_user_id: str | None
  • track_llm_call: bool | None
  • trace_id: str | None
  • parent_id: str | None
  • conversation_id: str | None
  • conversation_name: str | None
  • source: str | None

​
class CompletionsCreateRequestInputs

Pydantic Fields:
  • model: <class 'str'>
  • messages: <class 'list'>
  • timeout: float | str | None
  • temperature: float | None
  • top_p: float | None
  • n: int | None
  • stop: str | list | None
  • max_completion_tokens: int | None
  • max_tokens: int | None
  • modalities: list | None
  • presence_penalty: float | None
  • frequency_penalty: float | None
  • stream: bool | None
  • logit_bias: dict | None
  • user: str | None
  • response_format: dict | type[pydantic.main.BaseModel] | None
  • seed: int | None
  • tools: list | None
  • tool_choice: str | dict | None
  • logprobs: bool | None
  • top_logprobs: int | None
  • parallel_tool_calls: bool | None
  • extra_headers: dict | None
  • functions: list | None
  • function_call: str | None
  • api_version: str | None
  • prompt: str | None
  • template_vars: dict[str, typing.Any] | None
  • vertex_credentials: str | None

​
class CompletionsCreateRes

Pydantic Fields:
  • response: dict[str, typing.Any]
  • weave_call_id: str | None
  • span_id: str | None
  • trace_id: str | None
  • conversation_id: str | None

​
class CostCreateInput

Pydantic Fields:
  • prompt_token_cost: <class 'float'>
  • completion_token_cost: <class 'float'>
  • cache_read_input_token_cost: <class 'float'>
  • cache_creation_input_token_cost: <class 'float'>
  • prompt_token_cost_unit: str | None
  • completion_token_cost_unit: str | None
  • effective_date: datetime.datetime | None
  • provider_id: str | None

​
class CostCreateReq

Pydantic Fields:
  • project_id: <class 'str'>
  • costs: dict[str, CostCreateInput]
  • wb_user_id: str | None

​
class CostCreateRes

Pydantic Fields:
  • ids: list[tuple[str, str]]

​
class CostPurgeReq

Pydantic Fields:
  • project_id: <class 'str'>
  • query: <class 'weave.trace_server.interface.query.Query'>

​
class CostPurgeRes

​
class CostQueryOutput

Pydantic Fields:
  • id: str | None
  • llm_id: str | None
  • prompt_token_cost: float | None
  • completion_token_cost: float | None
  • prompt_token_cost_unit: str | None
  • completion_token_cost_unit: str | None
  • effective_date: datetime.datetime | None
  • provider_id: str | None

​
class CostQueryReq

Pydantic Fields:
  • project_id: <class 'str'>
  • fields: list[str] | None
  • query: weave.trace_server.interface.query.Query | None
  • sort_by: list[weave.trace_server.common_interface.SortBy] | None
  • limit: int | None
  • offset: int | None

​
class CostQueryRes

Pydantic Fields:
  • results: list[CostQueryOutput]

​
class DatasetCreateBody

Pydantic Fields:
  • name: str | None
  • description: str | None
  • rows: list[dict[str, typing.Any]]

​
class DatasetCreateReq

Pydantic Fields:
  • name: str | None
  • description: str | None
  • rows: list[dict[str, typing.Any]]
  • project_id: <class 'str'>
  • wb_user_id: str | None

​
class DatasetCreateRes

Pydantic Fields:
  • digest: <class 'str'>
  • object_id: <class 'str'>
  • version_index: <class 'int'>

​
class DatasetDeleteReq

Pydantic Fields:
  • project_id: <class 'str'>
  • object_id: <class 'str'>
  • digests: list[str] | None
  • wb_user_id: str | None

​
class DatasetDeleteRes

Pydantic Fields:
  • num_deleted: <class 'int'>

​
class DatasetListReq

Pydantic Fields:
  • project_id: <class 'str'>
  • limit: int | None
  • offset: int | None
  • wb_user_id: str | None

​
class DatasetReadReq

Pydantic Fields:
  • project_id: <class 'str'>
  • object_id: <class 'str'>
  • digest: <class 'str'>
  • wb_user_id: str | None

​
class DatasetReadRes

Pydantic Fields:
  • object_id: <class 'str'>
  • digest: <class 'str'>
  • version_index: <class 'int'>
  • created_at: <class 'datetime.datetime'>
  • name: <class 'str'>
  • description: str | None
  • rows: <class 'str'>

​
class DatasetSourceLinkPayload

A single dataset row and the sources to link to it. Pydantic Fields:
  • row_digest: <class 'str'>
  • sources: list[SourceRef]
  • link_metadata: dict[str, typing.Any] | None

​
class DatasetSourceLinkSchema

Schema for a single dataset source link row. Pydantic Fields:
  • id: <class 'str'>
  • row_digest: <class 'str'>
  • source_kind: <enum 'SourceKind'>
  • source_id: <class 'str'>
  • source_trace_id: <class 'str'>
  • source_started_at: <class 'datetime.datetime'>
  • source_display_name: <class 'str'>
  • link_metadata: dict[str, typing.Any] | None
  • added_by: str | None
  • created_at: <class 'datetime.datetime'>
  • updated_at: <class 'datetime.datetime'>
  • deleted_at: datetime.datetime | None

​
class DatasetSourcesLinkDeleteReq

Request to soft-delete dataset source links by id. Pydantic Fields:
  • project_id: <class 'str'>
  • link_ids: list[str]
  • wb_user_id: str | None

​
class DatasetSourcesLinkDeleteRes

Response from deleting dataset source links. Pydantic Fields:
  • entries: list[DatasetSourcesLinkDeleteResEntry]

​
class DatasetSourcesLinkDeleteResEntry

Result for a single link deletion. Pydantic Fields:
  • link_id: <class 'str'>
  • deleted: <class 'bool'>

​
class DatasetSourcesLinkReq

Request to link dataset rows to their provenance sources. Pydantic Fields:
  • project_id: <class 'str'>
  • dataset_object_id: <class 'str'>
  • dataset_digest: <class 'str'>
  • links: list[DatasetSourceLinkPayload]
  • include_created_status: <class 'bool'>
  • wb_user_id: str | None

​
class DatasetSourcesLinkRes

Response from linking dataset rows to sources. One entry per flattened (row_digest, source) tuple, in input order. Pydantic Fields:
  • entries: list[DatasetSourcesLinkResEntry]

​
class DatasetSourcesLinkResEntry

Result for a single flattened (row_digest, source) link. Pydantic Fields:
  • link_id: <class 'str'>
  • created: bool | None

​
class DatasetSourcesQueryReq

Forward query: dataset -> sources. Pydantic Fields:
  • project_id: <class 'str'>
  • dataset_object_id: <class 'str'>
  • row_digests: list[str] | None
  • source_kinds: list[SourceKind] | None
  • include_deleted: <class 'bool'>
  • limit: int | None
  • offset: int | None
  • wb_user_id: str | None

​
class DatasetSourcesQueryRes

Response from the forward dataset -> sources query. Pydantic Fields:
  • links: list[DatasetSourceLinkSchema]

​
class EndedCallSchemaForInsert

Pydantic Fields:
  • project_id: <class 'str'>
  • id: <class 'str'>
  • trace_id: str | None
  • is_eval: bool | None
  • ended_at: <class 'datetime.datetime'>
  • started_at: datetime.datetime | None
  • exception: str | None
  • output: typing.Any | None
  • summary: <class 'SummaryInsertMap'>
  • wb_run_step_end: int | None

​
method serialize_typed_dicts

​
class EndedCallSchemaForInsertWithStartedAt

Deprecated alias. started_at now lives on the parent EndedCallSchemaForInsert; prefer that. Kept so external SDK pins on the WithStartedAt name keep importing. Remove once all in-tree callers migrate. Pydantic Fields:
  • project_id: <class 'str'>
  • id: <class 'str'>
  • trace_id: str | None
  • is_eval: bool | None
  • ended_at: <class 'datetime.datetime'>
  • started_at: datetime.datetime | None
  • exception: str | None
  • output: typing.Any | None
  • summary: <class 'SummaryInsertMap'>
  • wb_run_step_end: int | None

​
method serialize_typed_dicts

​
class EvalResultsEvaluationSummary

Pydantic Fields:
  • evaluation_call_id: <class 'str'>
  • trial_count: <class 'int'>
  • scorer_stats: list[EvalResultsScorerStats]
  • predict_total_tokens: int | None
  • predict_total_cost: float | None
  • evaluation_ref: str | None
  • model_ref: str | None
  • display_name: str | None
  • trace_id: str | None
  • started_at: str | None

​
class EvalResultsFilter

A filter scoped to an optional evaluation. Pydantic Fields:
  • evaluation_call_id: str | None
  • query: <class 'weave.trace_server.interface.query.Query'>

​
class EvalResultsQueryBody

Pydantic Fields:
  • evaluation_call_ids: list[str] | None
  • evaluation_run_ids: list[str] | None
  • require_intersection: <class 'bool'>
  • include_raw_data_rows: <class 'bool'>
  • resolve_row_refs: <class 'bool'>
  • include_rows: <class 'bool'>
  • include_summary: <class 'bool'>
  • summary_require_intersection: bool | None
  • include_predict_and_score_children: <class 'bool'>
  • include_costs: <class 'bool'>
  • sort_by: list[EvalResultsSortBy] | None
  • filters: list[EvalResultsFilter] | None
  • filter_logic_operator: typing.Literal['and', 'or']
  • limit: int | None
  • offset: <class 'int'>

​
method validate_identifiers

Validate that at least one evaluation identifier is provided.

​
class EvalResultsQueryReq

Pydantic Fields:
  • evaluation_call_ids: list[str] | None
  • evaluation_run_ids: list[str] | None
  • require_intersection: <class 'bool'>
  • include_raw_data_rows: <class 'bool'>
  • resolve_row_refs: <class 'bool'>
  • include_rows: <class 'bool'>
  • include_summary: <class 'bool'>
  • summary_require_intersection: bool | None
  • include_predict_and_score_children: <class 'bool'>
  • include_costs: <class 'bool'>
  • sort_by: list[EvalResultsSortBy] | None
  • filters: list[EvalResultsFilter] | None
  • filter_logic_operator: typing.Literal['and', 'or']
  • limit: int | None
  • offset: <class 'int'>
  • project_id: <class 'str'>

​
method validate_identifiers

Validate that at least one evaluation identifier is provided.

​
class EvalResultsQueryRes

Pydantic Fields:
  • rows: list[EvalResultsRow]
  • total_rows: <class 'int'>
  • summary: ForwardRef('EvalResultsSummaryRes | None')
  • warnings: list[str]

​
class EvalResultsRow

Pydantic Fields:
  • row_digest: <class 'str'>
  • raw_data_row: typing.Any | None
  • evaluations: list[EvalResultsRowEvaluation]

​
class EvalResultsRowEvaluation

Pydantic Fields:
  • evaluation_call_id: <class 'str'>
  • trials: list[EvalResultsTrial]

​
class EvalResultsScorerStats

Stats for a single flattened score dimension (scorer_key or scorer_key.path.to.leaf). Pydantic Fields:
  • scorer_key: <class 'str'>
  • path: str | None
  • value_type: typing.Optional[typing.Literal['binary', 'continuous', 'text']]
  • trial_count: <class 'int'>
  • numeric_count: <class 'int'>
  • numeric_mean: float | None
  • pass_true_count: <class 'int'>
  • pass_known_count: <class 'int'>
  • pass_rate: float | None
  • pass_signal_coverage: float | None

​
class EvalResultsSortBy

Sort specification for evaluation results, extending SortBy Pydantic Fields:
  • field: <class 'str'>
  • direction: typing.Literal['asc', 'desc']
  • evaluation_call_id: str | None
  • mode: typing.Literal['value', 'difference']

​
class EvalResultsSummaryRes

Pydantic Fields:
  • row_count: <class 'int'>
  • evaluations: list[EvalResultsEvaluationSummary]

​
class EvalResultsTrial

Pydantic Fields:
  • predict_and_score_call_id: <class 'str'>
  • predict_call_id: str | None
  • model_output: typing.Any | None
  • scores: dict[str, typing.Any]
  • model_latency_seconds: float | None
  • total_tokens: int | None
  • total_cost: float | None
  • scorer_call_ids: dict[str, str]
  • genai_span_ref: list[GenAISpanRef] | None

​
class EvaluateModelArgs

Arguments for a full evaluate-model job (loads model + runs predictions + scores). Moved from workers/evaluate_model_worker/evaluate_model_worker.py so both job types (EvaluateModelArgs and RescoringArgs) can be co-located in the same module for the EvalWorkerJob discriminated union. Pydantic Fields:
  • job_type: typing.Literal['evaluate_model']
  • project_id: <class 'str'>
  • evaluation_ref: <class 'str'>
  • model_ref: <class 'str'>
  • wb_user_id: <class 'str'>
  • evaluation_call_id: <class 'str'>

​
class EvaluateModelReq

Pydantic Fields:
  • project_id: <class 'str'>
  • evaluation_ref: <class 'str'>
  • model_ref: <class 'str'>
  • wb_user_id: str | None

​
class EvaluateModelRes

Pydantic Fields:
  • call_id: <class 'str'>

​
class EvaluationCreateBody

Pydantic Fields:
  • name: <class 'str'>
  • description: str | None
  • dataset: <class 'str'>
  • scorers: list[str] | None
  • trials: <class 'int'>
  • evaluation_name: str | None
  • eval_attributes: dict[str, typing.Any] | None

​
class EvaluationCreateReq

Pydantic Fields:
  • name: <class 'str'>
  • description: str | None
  • dataset: <class 'str'>
  • scorers: list[str] | None
  • trials: <class 'int'>
  • evaluation_name: str | None
  • eval_attributes: dict[str, typing.Any] | None
  • project_id: <class 'str'>
  • wb_user_id: str | None

​
class EvaluationCreateRes

Pydantic Fields:
  • digest: <class 'str'>
  • object_id: <class 'str'>
  • version_index: <class 'int'>
  • evaluation_ref: <class 'str'>

​
class EvaluationDeleteReq

Pydantic Fields:
  • project_id: <class 'str'>
  • object_id: <class 'str'>
  • digests: list[str] | None
  • wb_user_id: str | None

​
class EvaluationDeleteRes

Pydantic Fields:
  • num_deleted: <class 'int'>

​
class EvaluationListReq

Pydantic Fields:
  • project_id: <class 'str'>
  • limit: int | None
  • offset: int | None
  • wb_user_id: str | None

​
class EvaluationReadReq

Pydantic Fields:
  • project_id: <class 'str'>
  • object_id: <class 'str'>
  • digest: <class 'str'>
  • wb_user_id: str | None

​
class EvaluationReadRes

Pydantic Fields:
  • object_id: <class 'str'>
  • digest: <class 'str'>
  • version_index: <class 'int'>
  • created_at: <class 'datetime.datetime'>
  • name: <class 'str'>
  • description: str | None
  • dataset: <class 'str'>
  • scorers: list[str]
  • trials: <class 'int'>
  • evaluation_name: str | None
  • evaluate_op: str | None
  • predict_and_score_op: str | None
  • summarize_op: str | None

​
class EvaluationRunCreateBody

Pydantic Fields:
  • evaluation: <class 'str'>
  • model: <class 'str'>
  • source_evaluation_run_id: str | None

​
class EvaluationRunCreateReq

Pydantic Fields:
  • evaluation: <class 'str'>
  • model: <class 'str'>
  • source_evaluation_run_id: str | None
  • project_id: <class 'str'>
  • wb_user_id: str | None

​
class EvaluationRunCreateRes

Pydantic Fields:
  • evaluation_run_id: <class 'str'>

​
class EvaluationRunDeleteReq

Pydantic Fields:
  • project_id: <class 'str'>
  • evaluation_run_ids: list[str]
  • wb_user_id: str | None

​
class EvaluationRunDeleteRes

Pydantic Fields:
  • num_deleted: <class 'int'>

​
class EvaluationRunFilter

Pydantic Fields:
  • evaluations: list[str] | None
  • models: list[str] | None
  • evaluation_run_ids: list[str] | None

​
class EvaluationRunFinishBody

Request body for finishing an evaluation run via REST API. This model excludes project_id and evaluation_run_id since they come from the URL path in RESTful endpoints. Pydantic Fields:
  • summary: dict[str, typing.Any] | None

​
class EvaluationRunFinishReq

Pydantic Fields:
  • summary: dict[str, typing.Any] | None
  • project_id: <class 'str'>
  • evaluation_run_id: <class 'str'>
  • wb_user_id: str | None

​
class EvaluationRunFinishRes

Pydantic Fields:
  • success: <class 'bool'>

​
class EvaluationRunListReq

Pydantic Fields:
  • project_id: <class 'str'>
  • filter: EvaluationRunFilter | None
  • limit: int | None
  • offset: int | None

​
class EvaluationRunReadReq

Pydantic Fields:
  • project_id: <class 'str'>
  • evaluation_run_id: <class 'str'>

​
class EvaluationRunReadRes

Pydantic Fields:
  • evaluation_run_id: <class 'str'>
  • evaluation: <class 'str'>
  • model: <class 'str'>
  • status: str | None
  • started_at: datetime.datetime | None
  • finished_at: datetime.datetime | None
  • summary: dict[str, typing.Any] | None
  • source_evaluation_run_id: str | None

​
class EvaluationStatusComplete

Pydantic Fields:
  • code: typing.Literal['complete']
  • output: dict[str, typing.Any]

​
class EvaluationStatusFailed

Pydantic Fields:
  • code: typing.Literal['failed']
  • error: str | None

​
class EvaluationStatusNotFound

Pydantic Fields:
  • code: typing.Literal['not_found']

​
class EvaluationStatusReq

Pydantic Fields:
  • project_id: <class 'str'>
  • call_id: <class 'str'>

​
class EvaluationStatusRes

Pydantic Fields:
  • status: EvaluationStatusNotFound | EvaluationStatusRunning | EvaluationStatusFailed | EvaluationStatusComplete

​
class EvaluationStatusRunning

Pydantic Fields:
  • code: typing.Literal['running']
  • completed_rows: <class 'int'>
  • total_rows: <class 'int'>

​
class ExportTracePartialSuccess

Pydantic Fields:
  • rejected_spans: <class 'int'>
  • error_message: <class 'str'>

​
class ExtraKeysTypedDict

​
class Feedback

Pydantic Fields:
  • id: <class 'str'>
  • project_id: <class 'str'>
  • weave_ref: <class 'str'>
  • creator: str | None
  • feedback_type: <class 'str'>
  • payload: dict[str, typing.Any]
  • annotation_ref: str | None
  • runnable_ref: str | None
  • call_ref: str | None
  • trigger_ref: str | None
  • queue_id: str | None
  • scorer_tags: list[str]
  • scorer_tag_reasons: dict[str, str]
  • scorer_tag_confidences: dict[str, float]
  • scorer_ratings: dict[str, float]
  • scorer_rating_reasons: dict[str, str]
  • scorer_rating_confidences: dict[str, float]
  • span_agent_name: <class 'str'>
  • span_agent_version: <class 'str'>
  • span_status_code: <class 'str'>
  • wb_user_id: str | None
  • created_at: <class 'datetime.datetime'>

​
class FeedbackAggregateBucket

One (time bucket, group) row of aggregated scorer feedback. Pydantic Fields:
  • time_bucket_start_ms: int | None
  • group: dict[str, str]
  • total_count: <class 'int'>
  • scored_count: <class 'int'>
  • tag_counts: dict[str, int]
  • rating_counts: dict[str, int]
  • rating_sums: dict[str, float]

​
class FeedbackAggregateReq

Query for aggregate scores by time bucket and dimension. Pydantic Fields:
  • project_id: <class 'str'>
  • after_ms: <class 'int'>
  • before_ms: <class 'int'>
  • time_bucket_seconds: int | None
  • feedback_types: list[str]
  • tags: list[str]
  • rating_min: float | None
  • rating_max: float | None
  • monitor_ids: list[str]
  • scorer_ids: list[str]
  • span_agent_names: list[str]
  • span_types: list[typing.Literal['agent_turn', 'agent_conversation']]
  • group_by: list[typing.Literal['scorer_id', 'span_agent_name', 'span_agent_version', 'span_status_code']]

​
class FeedbackAggregateRes

Sparse time-series of aggregated scorer feedback (empty buckets omitted). Pydantic Fields:
  • time_bucket_seconds: int | None
  • after_ms: <class 'int'>
  • before_ms: <class 'int'>
  • buckets: list[FeedbackAggregateBucket]

​
class FeedbackCreateBatchReq

Pydantic Fields:
  • batch: list[FeedbackCreateReq]

​
class FeedbackCreateBatchRes

Pydantic Fields:
  • res: list[FeedbackCreateRes]

​
class FeedbackCreateReq

Pydantic Fields:
  • id: str | None
  • project_id: <class 'str'>
  • weave_ref: <class 'str'>
  • creator: str | None
  • feedback_type: <class 'str'>
  • payload: dict[str, typing.Any]
  • annotation_ref: str | None
  • runnable_ref: str | None
  • call_ref: str | None
  • trigger_ref: str | None
  • queue_id: str | None
  • scorer_tags: list[str]
  • scorer_tag_reasons: dict[str, str]
  • scorer_tag_confidences: dict[str, float]
  • scorer_ratings: dict[str, float]
  • scorer_rating_reasons: dict[str, str]
  • scorer_rating_confidences: dict[str, float]
  • span_agent_name: <class 'str'>
  • span_agent_version: <class 'str'>
  • span_status_code: <class 'str'>
  • wb_user_id: str | None

​
class FeedbackCreateRes

Pydantic Fields:
  • id: <class 'str'>
  • created_at: <class 'datetime.datetime'>
  • wb_user_id: <class 'str'>
  • payload: dict[str, typing.Any]

​
class FeedbackDict

​
class FeedbackMetricSpec

Specification for a feedback payload metric to aggregate. Pydantic Fields:
  • json_path: <class 'str'>
  • value_type: typing.Literal['numeric', 'boolean', 'categorical']
  • aggregations: list[AggregationType]
  • percentiles: list[float]

​
class FeedbackPayloadPath

Discovered path in feedback payload with inferred type. Pydantic Fields:
  • json_path: <class 'str'>
  • value_type: typing.Literal['numeric', 'boolean', 'categorical']

​
class FeedbackPayloadSchemaReq

Request for feedback payload schema discovery. Pydantic Fields:
  • project_id: <class 'str'>
  • start: <class 'datetime.datetime'>
  • end: datetime.datetime | None
  • feedback_type: str | None
  • trigger_ref: str | None
  • sample_limit: <class 'int'>

​
method validate_date_range

Ensure feedback requests are bounded to a safe date range.

​
class FeedbackPayloadSchemaRes

Response with discovered feedback payload paths and types. Pydantic Fields:
  • paths: list[FeedbackPayloadPath]

​
class FeedbackPurgeReq

Pydantic Fields:
  • project_id: <class 'str'>
  • query: <class 'weave.trace_server.interface.query.Query'>

​
class FeedbackPurgeRes

​
class FeedbackQueryReq

Pydantic Fields:
  • project_id: <class 'str'>
  • fields: list[str] | None
  • query: weave.trace_server.interface.query.Query | None
  • sort_by: list[weave.trace_server.common_interface.SortBy] | None
  • limit: int | None
  • offset: int | None

​
class FeedbackQueryRes

Pydantic Fields:
  • result: list[dict[str, typing.Any]]

​
class FeedbackReplaceReq

Pydantic Fields:
  • id: str | None
  • project_id: <class 'str'>
  • weave_ref: <class 'str'>
  • creator: str | None
  • feedback_type: <class 'str'>
  • payload: dict[str, typing.Any]
  • annotation_ref: str | None
  • runnable_ref: str | None
  • call_ref: str | None
  • trigger_ref: str | None
  • queue_id: str | None
  • scorer_tags: list[str]
  • scorer_tag_reasons: dict[str, str]
  • scorer_tag_confidences: dict[str, float]
  • scorer_ratings: dict[str, float]
  • scorer_rating_reasons: dict[str, str]
  • scorer_rating_confidences: dict[str, float]
  • span_agent_name: <class 'str'>
  • span_agent_version: <class 'str'>
  • span_status_code: <class 'str'>
  • wb_user_id: str | None
  • feedback_id: <class 'str'>

​
class FeedbackReplaceRes

Pydantic Fields:
  • id: <class 'str'>
  • created_at: <class 'datetime.datetime'>
  • wb_user_id: <class 'str'>
  • payload: dict[str, typing.Any]

​
class FeedbackStatsReq

Request for aggregated feedback statistics over time buckets. Pydantic Fields:
  • project_id: <class 'str'>
  • start: <class 'datetime.datetime'>
  • end: datetime.datetime | None
  • feedback_type: str | None
  • trigger_ref: str | None
  • granularity: int | None
  • timezone: <class 'str'>
  • metrics: list[FeedbackMetricSpec]

​
method validate_date_range

Ensure feedback requests are bounded to a safe date range.

​
class FeedbackStatsRes

Response with time-series feedback statistics. Pydantic Fields:
  • start: <class 'datetime.datetime'>
  • end: <class 'datetime.datetime'>
  • granularity: <class 'int'>
  • timezone: <class 'str'>
  • buckets: list[dict[str, typing.Any]]
  • window_stats: dict[str, dict[str, float | None]] | None

​
class FileContentReadReq

Pydantic Fields:
  • project_id: <class 'str'>
  • digest: <class 'str'>

​
class FileContentReadRes

Pydantic Fields:
  • content: <class 'bytes'>

​
class FileCreateReq

Pydantic Fields:
  • project_id: <class 'str'>
  • name: <class 'str'>
  • content: <class 'bytes'>
  • expected_digest: str | None

​
class FileCreateRes

Pydantic Fields:
  • digest: <class 'str'>

​
class FilesStatsReq

Pydantic Fields:
  • project_id: <class 'str'>

​
class FilesStatsRes

Pydantic Fields:
  • total_size_bytes: <class 'int'>

​
class FullTraceServerInterface

Complete trace server interface supporting both V1 and Object APIs. This protocol represents a trace server implementation that supports the full set of APIs - both legacy V1 endpoints and modern Object endpoints. Use this type for implementations that need to support both API versions.

​
method agent_agents_query

​
method agent_conversation_chat

​
method agent_conversation_spans

​
method agent_custom_attrs_schema

​
method agent_spans_query

​
method agent_spans_stats

​
method agent_traces_chat

​
method agent_versions_query

​
method aliases_list

​
method annotation_queue_add_calls

​
method annotation_queue_create

​
method annotation_queue_delete

​
method annotation_queue_items_query

​
method annotation_queue_read

​
method annotation_queue_update

​
method annotation_queues_query_stream

​
method annotation_queues_stats

​
method annotator_queue_items_progress_update

​
method call_end

​
method call_end_v2

​
method call_read

​
method call_start

​
method call_start_batch

​
method call_start_v2

​
method call_stats

​
method call_update

​
method calls_complete

​
method calls_delete

​
method calls_query

​
method calls_query_stats

​
method calls_query_stream

​
method calls_score

​
method calls_usage

​
method completions_create

​
method completions_create_stream

​
method cost_create

​
method cost_purge

​
method cost_query

​
method dataset_create

​
method dataset_delete

​
method dataset_list

​
method dataset_read

​
method dataset_sources_query

​
method eval_results_query

​
method evaluate_model

​
method evaluation_create

​
method evaluation_delete

​
method evaluation_list

​
method evaluation_read

​
method evaluation_run_create

​
method evaluation_run_delete

​
method evaluation_run_finish

​
method evaluation_run_list

​
method evaluation_run_read

​
method evaluation_status

​
method feedback_aggregate

​
method feedback_create

​
method feedback_create_batch

​
method feedback_payload_schema

​
method feedback_purge

​
method feedback_query

​
method feedback_replace

​
method feedback_stats

​
method file_content_read

​
method file_create

​
method files_stats

​
method genai_otel_export

​
method image_create

​
method model_create

​
method model_delete

​
method model_list

​
method model_read

​
method obj_add_tags

​
method obj_create

​
method obj_delete

​
method obj_read

​
method obj_remove_aliases

​
method obj_remove_tags

​
method obj_set_aliases

​
method objs_query

​
method op_create

​
method op_delete

​
method op_list

​
method op_read

​
method otel_export

​
method prediction_create

​
method prediction_delete

​
method prediction_finish

​
method prediction_list

​
method prediction_read

​
method project_stats

​
method project_ttl_settings_read

​
method project_ttl_settings_update

​
method refs_read_batch

​
method rescore

​
method score_create

​
method score_delete

​
method score_list

​
method score_read

​
method scorer_create

​
method scorer_delete

​
method scorer_list

​
method scorer_read

​
method source_datasets_query

​
method table_create

​
method table_create_from_digests

​
method table_query

​
method table_query_stats

​
method table_query_stats_batch

​
method table_query_stream

​
method table_update

​
method tags_list

​
method threads_query_stream

​
method trace_usage

​
class GenAISpanRef

Pydantic Fields:
  • trace_id: <class 'str'>
  • span_id: <class 'str'>

​
class ImageGenerationCreateReq

Pydantic Fields:
  • project_id: <class 'str'>
  • inputs: <class 'ImageGenerationRequestInputs'>
  • wb_user_id: str | None
  • track_llm_call: bool | None

​
class ImageGenerationCreateRes

Pydantic Fields:
  • response: dict[str, typing.Any]
  • weave_call_id: str | None

​
class ImageGenerationRequestInputs

Pydantic Fields:
  • model: <class 'str'>
  • prompt: <class 'str'>
  • n: int | None

​
class LLMAggregatedUsage

Aggregated usage metrics for a specific LLM. Pydantic Fields:
  • requests: <class 'int'>
  • prompt_tokens: <class 'int'>
  • completion_tokens: <class 'int'>
  • total_tokens: <class 'int'>
  • cache_read_input_tokens: <class 'int'>
  • cache_creation_input_tokens: <class 'int'>
  • prompt_tokens_total_cost: float | None
  • completion_tokens_total_cost: float | None
  • cache_read_input_tokens_total_cost: float | None
  • cache_creation_input_tokens_total_cost: float | None

​
class LLMCostSchema

​
class LLMUsageSchema

​
class ModelCreateBody

Pydantic Fields:
  • name: <class 'str'>
  • description: str | None
  • source_code: <class 'str'>
  • attributes: dict[str, typing.Any] | None

​
class ModelCreateReq

Pydantic Fields:
  • name: <class 'str'>
  • description: str | None
  • source_code: <class 'str'>
  • attributes: dict[str, typing.Any] | None
  • project_id: <class 'str'>
  • wb_user_id: str | None

​
class ModelCreateRes

Pydantic Fields:
  • digest: <class 'str'>
  • object_id: <class 'str'>
  • version_index: <class 'int'>
  • model_ref: <class 'str'>

​
class ModelDeleteReq

Pydantic Fields:
  • project_id: <class 'str'>
  • object_id: <class 'str'>
  • digests: list[str] | None
  • wb_user_id: str | None

​
class ModelDeleteRes

Pydantic Fields:
  • num_deleted: <class 'int'>

​
class ModelListReq

Pydantic Fields:
  • project_id: <class 'str'>
  • limit: int | None
  • offset: int | None

​
class ModelReadReq

Pydantic Fields:
  • project_id: <class 'str'>
  • object_id: <class 'str'>
  • digest: <class 'str'>

​
class ModelReadRes

Pydantic Fields:
  • object_id: <class 'str'>
  • digest: <class 'str'>
  • version_index: <class 'int'>
  • created_at: <class 'datetime.datetime'>
  • name: <class 'str'>
  • description: str | None
  • source_code: <class 'str'>
  • attributes: dict[str, typing.Any] | None

​
class OTelExportReq

Pydantic Fields:
  • processed_spans: list[ProcessedResourceSpans]
  • project_id: <class 'str'>
  • wb_user_id: str | None

​
class OTelExportRes

Pydantic Fields:
  • partial_success: ExportTracePartialSuccess | None

​
class ObjAddTagsReq

Pydantic Fields:
  • project_id: <class 'str'>
  • object_id: <class 'str'>
  • digest: <class 'str'>
  • tags: list[str]
  • wb_user_id: str | None

​
method validate_tags

​
class ObjAddTagsRes

​
class ObjCreateReq

Pydantic Fields:
  • obj: <class 'ObjSchemaForInsert'>

​
class ObjCreateRes

Pydantic Fields:
  • digest: <class 'str'>
  • object_id: str | None

​
class ObjDeleteReq

Pydantic Fields:
  • project_id: <class 'str'>
  • object_id: <class 'str'>
  • digests: list[str] | None

​
class ObjDeleteRes

Pydantic Fields:
  • num_deleted: <class 'int'>

​
class ObjQueryReq

Pydantic Fields:
  • project_id: <class 'str'>
  • filter: ObjectVersionFilter | None
  • limit: int | None
  • offset: int | None
  • sort_by: list[weave.trace_server.common_interface.SortBy] | None
  • metadata_only: bool | None
  • include_storage_size: bool | None
  • include_tags_and_aliases: bool | None

​
class ObjQueryRes

Pydantic Fields:
  • objs: list[ObjSchema]

​
class ObjReadReq

Pydantic Fields:
  • project_id: <class 'str'>
  • object_id: <class 'str'>
  • digest: <class 'str'>
  • metadata_only: bool | None
  • include_tags_and_aliases: bool | None

​
class ObjReadRes

Pydantic Fields:
  • obj: <class 'ObjSchema'>

​
class ObjRemoveAliasesReq

Pydantic Fields:
  • project_id: <class 'str'>
  • object_id: <class 'str'>
  • aliases: list[str]
  • wb_user_id: str | None

​
method validate_aliases

​
class ObjRemoveAliasesRes

​
class ObjRemoveTagsReq

Pydantic Fields:
  • project_id: <class 'str'>
  • object_id: <class 'str'>
  • digest: <class 'str'>
  • tags: list[str]
  • wb_user_id: str | None

​
class ObjRemoveTagsRes

​
class ObjSchema

Pydantic Fields:
  • project_id: <class 'str'>
  • object_id: <class 'str'>
  • created_at: <class 'datetime.datetime'>
  • deleted_at: datetime.datetime | None
  • digest: <class 'str'>
  • version_index: <class 'int'>
  • is_latest: <class 'int'>
  • kind: <class 'str'>
  • base_object_class: str | None
  • leaf_object_class: str | None
  • val: typing.Any
  • wb_user_id: str | None
  • size_bytes: int | None
  • tags: list[str] | None
  • aliases: list[str] | None

​
class ObjSchemaForInsert

Pydantic Fields:
  • project_id: <class 'str'>
  • object_id: <class 'str'>
  • val: typing.Any
  • builtin_object_class: str | None
  • set_base_object_class: str | None
  • expected_digest: str | None
  • wb_user_id: str | None

​
method model_post_init

​
class ObjSetAliasesReq

Pydantic Fields:
  • project_id: <class 'str'>
  • object_id: <class 'str'>
  • digest: <class 'str'>
  • aliases: list[str]
  • wb_user_id: str | None

​
method validate_aliases

​
class ObjSetAliasesRes

​
class ObjectInterface

Object API endpoints for Trace Server. This protocol contains object management APIs that provide cleaner, more RESTful interfaces. Implementations should support both this protocol and TraceServerInterface to maintain backward compatibility.

​
method call_end_v2

​
method call_start_v2

​
method calls_complete

​
method dataset_create

​
method dataset_delete

​
method dataset_list

​
method dataset_read

​
method eval_results_query

​
method evaluation_create

​
method evaluation_delete

​
method evaluation_list

​
method evaluation_read

​
method evaluation_run_create

​
method evaluation_run_delete

​
method evaluation_run_finish

​
method evaluation_run_list

​
method evaluation_run_read

​
method model_create

​
method model_delete

​
method model_list

​
method model_read

​
method op_create

​
method op_delete

​
method op_list

​
method op_read

​
method prediction_create

​
method prediction_delete

​
method prediction_finish

​
method prediction_list

​
method prediction_read

​
method score_create

​
method score_delete

​
method score_list

​
method score_read

​
method scorer_create

​
method scorer_delete

​
method scorer_list

​
method scorer_read

​
class ObjectVersionFilter

Pydantic Fields:
  • base_object_classes: list[str] | None
  • exclude_base_object_classes: list[str] | None
  • leaf_object_classes: list[str] | None
  • object_ids: list[str] | None
  • is_op: bool | None
  • latest_only: bool | None
  • tags: list[str] | None
  • aliases: list[str] | None

​
class OpCreateBody

Request body for creating an Op object via REST API. This model excludes project_id since it comes from the URL path in RESTful endpoints. Pydantic Fields:
  • name: str | None
  • source_code: str | None

​
class OpCreateReq

Request model for creating an Op object. Extends OpCreateBody by adding project_id for internal API usage. Pydantic Fields:
  • name: str | None
  • source_code: str | None
  • project_id: <class 'str'>
  • wb_user_id: str | None

​
class OpCreateRes

Response model for creating an Op object. Pydantic Fields:
  • digest: <class 'str'>
  • object_id: <class 'str'>
  • version_index: <class 'int'>

​
class OpDeleteReq

Pydantic Fields:
  • project_id: <class 'str'>
  • object_id: <class 'str'>
  • digests: list[str] | None
  • wb_user_id: str | None

​
class OpDeleteRes

Pydantic Fields:
  • num_deleted: <class 'int'>

​
class OpListReq

Pydantic Fields:
  • project_id: <class 'str'>
  • limit: int | None
  • offset: int | None
  • wb_user_id: str | None

​
class OpReadReq

Pydantic Fields:
  • project_id: <class 'str'>
  • object_id: <class 'str'>
  • digest: <class 'str'>
  • wb_user_id: str | None

​
class OpReadRes

Response model for reading an Op object. The code field contains the actual source code of the op. Pydantic Fields:
  • object_id: <class 'str'>
  • digest: <class 'str'>
  • version_index: <class 'int'>
  • created_at: <class 'datetime.datetime'>
  • code: <class 'str'>

​
class PredictionCreateBody

Request body for creating a Prediction via REST API. This model excludes project_id since it comes from the URL path in RESTful endpoints. Pydantic Fields:
  • model: <class 'str'>
  • inputs: dict[str, typing.Any]
  • output: typing.Any
  • evaluation_run_id: str | None
  • genai_span_ref: list[GenAISpanRef] | None

​
class PredictionCreateReq

Request model for creating a Prediction. Extends PredictionCreateBody by adding project_id for internal API usage. Pydantic Fields:
  • model: <class 'str'>
  • inputs: dict[str, typing.Any]
  • output: typing.Any
  • evaluation_run_id: str | None
  • genai_span_ref: list[GenAISpanRef] | None
  • project_id: <class 'str'>
  • wb_user_id: str | None

​
class PredictionCreateRes

Pydantic Fields:
  • prediction_id: <class 'str'>

​
class PredictionDeleteReq

Pydantic Fields:
  • project_id: <class 'str'>
  • prediction_ids: list[str]
  • wb_user_id: str | None

​
class PredictionDeleteRes

Pydantic Fields:
  • num_deleted: <class 'int'>

​
class PredictionFinishReq

Pydantic Fields:
  • project_id: <class 'str'>
  • prediction_id: <class 'str'>
  • wb_user_id: str | None

​
class PredictionFinishRes

Pydantic Fields:
  • success: <class 'bool'>

​
class PredictionListReq

Pydantic Fields:
  • project_id: <class 'str'>
  • evaluation_run_id: str | None
  • limit: int | None
  • offset: int | None
  • wb_user_id: str | None

​
class PredictionListRes

Pydantic Fields:
  • predictions: list[PredictionReadRes]

​
class PredictionReadReq

Pydantic Fields:
  • project_id: <class 'str'>
  • prediction_id: <class 'str'>
  • wb_user_id: str | None

​
class PredictionReadRes

Pydantic Fields:
  • prediction_id: <class 'str'>
  • model: <class 'str'>
  • inputs: dict[str, typing.Any]
  • output: typing.Any
  • evaluation_run_id: str | None
  • wb_user_id: str | None

​
class ProcessedResourceSpans

Pydantic Fields:
  • entity: <class 'str'>
  • project: <class 'str'>
  • run_id: str | None
  • resource_spans: <class 'opentelemetry.proto.trace.v1.trace_pb2.ResourceSpans'>

​
class ProjectStatsReq

Pydantic Fields:
  • project_id: <class 'str'>
  • include_trace_storage_size: bool | None
  • include_object_storage_size: bool | None
  • include_table_storage_size: bool | None
  • include_file_storage_size: bool | None

​
class ProjectStatsRes

Pydantic Fields:
  • trace_storage_size_bytes: <class 'int'>
  • objects_storage_size_bytes: <class 'int'>
  • tables_storage_size_bytes: <class 'int'>
  • files_storage_size_bytes: <class 'int'>

​
class ProjectTTLSettingsReadReq

Pydantic Fields:
  • project_id: <class 'str'>

​
class ProjectTTLSettingsReadRes

Pydantic Fields:
  • retention_days: int | None

​
class ProjectTTLSettingsUpdateReq

Pydantic Fields:
  • project_id: <class 'str'>
  • retention_days: int | None
  • wb_user_id: str | None

​
class ProjectTTLSettingsUpdateRes

Pydantic Fields:
  • retention_days: int | None

​
class RefsReadBatchReq

Pydantic Fields:
  • refs: list[str]

​
class RefsReadBatchRes

Pydantic Fields:
  • vals: list[typing.Any]

​
class RescoreBody

Request body for rescoring via REST API (excludes server-set fields). Pydantic Fields:
  • source_evaluation_run_id: <class 'str'>
  • scorer_refs: list[str]

​
class RescoreReq

Full rescore request including server-set fields. Pydantic Fields:
  • source_evaluation_run_id: <class 'str'>
  • scorer_refs: list[str]
  • project_id: <class 'str'>
  • wb_user_id: str | None

​
class RescoreRes

Response for a rescore request. Pydantic Fields:
  • call_id: <class 'str'>
  • evaluation_run_id: <class 'str'>

​
class RescoringArgs

Arguments for a rescore job dispatched to the evaluate-model worker. Differs from EvaluateModelArgs: no model is loaded, no predictions are run. Only scorer(s) are applied to existing predictions from source_evaluation_run_id. Pydantic Fields:
  • job_type: typing.Literal['rescore']
  • project_id: <class 'str'>
  • source_evaluation_run_id: <class 'str'>
  • scorer_refs: list[str]
  • wb_user_id: str | None
  • new_evaluation_run_id: <class 'str'>

​
class ScoreCreateBody

Request body for creating a Score via REST API. This model excludes project_id since it comes from the URL path in RESTful endpoints. Pydantic Fields:
  • prediction_id: <class 'str'>
  • scorer: <class 'str'>
  • value: typing.Any
  • evaluation_run_id: str | None

​
class ScoreCreateReq

Request model for creating a Score. Extends ScoreCreateBody by adding project_id for internal API usage. Pydantic Fields:
  • prediction_id: <class 'str'>
  • scorer: <class 'str'>
  • value: typing.Any
  • evaluation_run_id: str | None
  • project_id: <class 'str'>
  • wb_user_id: str | None

​
class ScoreCreateRes

Pydantic Fields:
  • score_id: <class 'str'>

​
class ScoreDeleteReq

Pydantic Fields:
  • project_id: <class 'str'>
  • score_ids: list[str]
  • wb_user_id: str | None

​
class ScoreDeleteRes

Pydantic Fields:
  • num_deleted: <class 'int'>

​
class ScoreListReq

Pydantic Fields:
  • project_id: <class 'str'>
  • evaluation_run_id: str | None
  • limit: int | None
  • offset: int | None
  • wb_user_id: str | None

​
class ScoreReadReq

Pydantic Fields:
  • project_id: <class 'str'>
  • score_id: <class 'str'>
  • wb_user_id: str | None

​
class ScoreReadRes

Pydantic Fields:
  • score_id: <class 'str'>
  • scorer: <class 'str'>
  • value: typing.Any
  • evaluation_run_id: str | None
  • wb_user_id: str | None

​
class ScorerCreateBody

Pydantic Fields:
  • name: <class 'str'>
  • description: str | None
  • op_source_code: <class 'str'>

​
class ScorerCreateReq

Pydantic Fields:
  • name: <class 'str'>
  • description: str | None
  • op_source_code: <class 'str'>
  • project_id: <class 'str'>
  • wb_user_id: str | None

​
class ScorerCreateRes

Pydantic Fields:
  • digest: <class 'str'>
  • object_id: <class 'str'>
  • version_index: <class 'int'>
  • scorer: <class 'str'>

​
class ScorerDeleteReq

Pydantic Fields:
  • project_id: <class 'str'>
  • object_id: <class 'str'>
  • digests: list[str] | None
  • wb_user_id: str | None

​
class ScorerDeleteRes

Pydantic Fields:
  • num_deleted: <class 'int'>

​
class ScorerListReq

Pydantic Fields:
  • project_id: <class 'str'>
  • limit: int | None
  • offset: int | None
  • wb_user_id: str | None

​
class ScorerReadReq

Pydantic Fields:
  • project_id: <class 'str'>
  • object_id: <class 'str'>
  • digest: <class 'str'>
  • wb_user_id: str | None

​
class ScorerReadRes

Pydantic Fields:
  • object_id: <class 'str'>
  • digest: <class 'str'>
  • version_index: <class 'int'>
  • created_at: <class 'datetime.datetime'>
  • name: <class 'str'>
  • description: str | None
  • score_op: <class 'str'>

​
class SourceDatasetMembership

Membership of a single (source, dataset) pair in the reverse query. Pydantic Fields:
  • source_kind: <enum 'SourceKind'>
  • source_id: <class 'str'>
  • source_trace_id: <class 'str'>
  • dataset_object_id: <class 'str'>
  • row_digests: list[str]
  • row_digests_truncated: <class 'bool'>
  • row_digests_total_count: <class 'int'>
  • first_seen_at: <class 'datetime.datetime'>

​
class SourceDatasetsQueryReq

Reverse query: sources -> datasets. Pydantic Fields:
  • project_id: <class 'str'>
  • sources: list[SourceRef]
  • include_deleted: <class 'bool'>
  • wb_user_id: str | None

​
class SourceDatasetsQueryRes

Response from the reverse sources -> datasets query. Pydantic Fields:
  • memberships: list[SourceDatasetMembership]

​
class SourceKind

​
class SourceRef

Reference to a provenance source (a call, an agent span, or a conversation). Pydantic Fields:
  • source_kind: <enum 'SourceKind'>
  • source_id: <class 'str'>
  • source_trace_id: <class 'str'>

​
class StartedCallSchemaForInsert

Pydantic Fields:
  • project_id: <class 'str'>
  • id: str | None
  • op_name: <class 'str'>
  • display_name: str | None
  • trace_id: str | None
  • parent_id: str | None
  • thread_id: str | None
  • turn_id: str | None
  • started_at: <class 'datetime.datetime'>
  • attributes: dict[str, typing.Any]
  • inputs: dict[str, typing.Any]
  • otel_dump: dict[str, typing.Any] | None
  • wb_user_id: str | None
  • wb_run_id: str | None
  • wb_run_step: int | None

​
class SummaryInsertMap

​
class SummaryMap

​
class TableAppendSpec

Pydantic Fields:
  • append: <class 'TableAppendSpecPayload'>

​
class TableAppendSpecPayload

Pydantic Fields:
  • row: dict[str, typing.Any]

​
class TableCreateFromDigestsReq

Pydantic Fields:
  • project_id: <class 'str'>
  • row_digests: list[str]
  • expected_digest: str | None

​
class TableCreateFromDigestsRes

Pydantic Fields:
  • digest: <class 'str'>

​
class TableCreateReq

Pydantic Fields:
  • table: <class 'TableSchemaForInsert'>

​
class TableCreateRes

Pydantic Fields:
  • digest: <class 'str'>
  • row_digests: list[str]

​
class TableInsertSpec

Pydantic Fields:
  • insert: <class 'TableInsertSpecPayload'>

​
class TableInsertSpecPayload

Pydantic Fields:
  • index: <class 'int'>
  • row: dict[str, typing.Any]

​
class TablePopSpec

Pydantic Fields:
  • pop: <class 'TablePopSpecPayload'>

​
class TablePopSpecPayload

Pydantic Fields:
  • index: <class 'int'>

​
class TableQueryReq

Pydantic Fields:
  • project_id: <class 'str'>
  • digest: <class 'str'>
  • filter: TableRowFilter | None
  • limit: int | None
  • offset: int | None
  • sort_by: list[weave.trace_server.common_interface.SortBy] | None

​
class TableQueryRes

Pydantic Fields:
  • rows: list[TableRowSchema]

​
class TableQueryStatsBatchReq

Pydantic Fields:
  • project_id: <class 'str'>
  • digests: list[str] | None
  • include_storage_size: bool | None

​
class TableQueryStatsBatchRes

Pydantic Fields:
  • tables: list[TableStatsRow]

​
class TableQueryStatsReq

Pydantic Fields:
  • project_id: <class 'str'>
  • digest: <class 'str'>

​
class TableQueryStatsRes

Pydantic Fields:
  • count: <class 'int'>

​
class TableRowFilter

Pydantic Fields:
  • row_digests: list[str] | None

​
class TableRowSchema

Pydantic Fields:
  • digest: <class 'str'>
  • val: typing.Any
  • original_index: int | None

​
class TableSchemaForInsert

Pydantic Fields:
  • project_id: <class 'str'>
  • rows: list[dict[str, typing.Any]]
  • expected_digest: str | None

​
class TableStatsRow

Pydantic Fields:
  • count: <class 'int'>
  • digest: <class 'str'>
  • storage_size_bytes: int | None

​
class TableUpdateReq

Pydantic Fields:
  • project_id: <class 'str'>
  • base_digest: <class 'str'>
  • updates: list[TableAppendSpec | TablePopSpec | TableInsertSpec]

​
class TableUpdateRes

Pydantic Fields:
  • digest: <class 'str'>
  • updated_row_digests: list[str]

​
class TagsListReq

Pydantic Fields:
  • project_id: <class 'str'>
  • wb_user_id: str | None

​
class TagsListRes

Pydantic Fields:
  • tags: list[str]

​
class ThreadSchema

Pydantic Fields:
  • thread_id: <class 'str'>
  • turn_count: <class 'int'>
  • start_time: <class 'datetime.datetime'>
  • last_updated: <class 'datetime.datetime'>
  • first_turn_id: str | None
  • last_turn_id: str | None
  • p50_turn_duration_ms: float | None
  • p99_turn_duration_ms: float | None

​
class ThreadsQueryFilter

Pydantic Fields:
  • after_datetime: datetime.datetime | None
  • before_datetime: datetime.datetime | None
  • thread_ids: list[str] | None

​
class ThreadsQueryReq

Query threads with aggregated statistics based on turn calls only. Turn calls are the immediate children of thread contexts (where call.id == turn_id). This provides meaningful conversation-level statistics rather than including all nested implementation details. Pydantic Fields:
  • project_id: <class 'str'>
  • filter: ThreadsQueryFilter | None
  • limit: int | None
  • offset: int | None
  • sort_by: list[weave.trace_server.common_interface.SortBy] | None

​
class TraceServerInterface

​
method agent_agents_query

​
method agent_conversation_chat

​
method agent_conversation_spans

​
method agent_custom_attrs_schema

​
method agent_search

​
method agent_spans_query

​
method agent_spans_stats

​
method agent_traces_chat

​
method agent_versions_query

​
method aliases_list

​
method annotation_queue_add_calls

​
method annotation_queue_create

​
method annotation_queue_delete

​
method annotation_queue_items_query

​
method annotation_queue_read

​
method annotation_queue_update

​
method annotation_queues_query_stream

​
method annotation_queues_stats

​
method annotator_queue_items_progress_update

​
method call_end

​
method call_read

​
method call_start

​
method call_start_batch

​
method call_stats

​
method call_update

​
method calls_delete

​
method calls_query

​
method calls_query_stats

​
method calls_query_stream

​
method calls_score

​
method calls_usage

​
method completions_create

​
method completions_create_stream

​
method cost_create

​
method cost_purge

​
method cost_query

​
method dataset_sources_query

​
method evaluate_model

​
method evaluation_status

​
method feedback_aggregate

​
method feedback_create

​
method feedback_create_batch

​
method feedback_payload_schema

​
method feedback_purge

​
method feedback_query

​
method feedback_replace

​
method feedback_stats

​
method file_content_read

​
method file_create

​
method files_stats

​
method genai_otel_export

​
method image_create

​
method obj_add_tags

​
method obj_create

​
method obj_delete

​
method obj_read

​
method obj_remove_aliases

​
method obj_remove_tags

​
method obj_set_aliases

​
method objs_query

​
method otel_export

​
method project_stats

​
method project_ttl_settings_read

​
method project_ttl_settings_update

​
method refs_read_batch

​
method rescore

​
method source_datasets_query

​
method table_create

​
method table_create_from_digests

​
method table_query

​
method table_query_stats

​
method table_query_stats_batch

​
method table_query_stream

​
method table_update

​
method tags_list

​
method threads_query_stream

​
method trace_usage

​
class TraceStatus

​
class TraceUsageReq

Request to compute per-call usage for a trace, with descendant rollup. This endpoint returns usage metrics for each call in the trace, where each call’s metrics include the sum of its own usage plus all descendants’ usage. Use this for trace view where you want to see rolled-up metrics per call. Note: All matching calls are loaded into memory for aggregation. For very large result sets (>10k calls), consider using more specific filters or pagination at the application layer. Pydantic Fields:
  • project_id: <class 'str'>
  • filter: CallsFilter | None
  • query: weave.trace_server.interface.query.Query | None
  • include_costs: <class 'bool'>
  • limit: <class 'int'>

​
class TraceUsageRes

Response with per-call usage metrics (each includes descendant contributions). Pydantic Fields:
  • call_usage: dict[str, dict[str, LLMAggregatedUsage]]
  • unfinished_call_ids: list[str]

​
class UsageMetricSpec

Specification for a usage metric to aggregate (grouped by model). Pydantic Fields:
  • metric: typing.Literal['input_tokens', 'output_tokens', 'total_tokens', 'cache_read_input_tokens', 'cache_creation_input_tokens', 'input_cost', 'output_cost', 'total_cost']
  • aggregations: list[AggregationType]
  • percentiles: list[float]

​
class WeaveSummarySchema