LangChain Reference home pageLangChain ReferenceLangChain Reference
  • GitHub
  • Main Docs
Deep Agents
LangChain
LangGraph
Integrations
LangSmith
  • Overview
  • Client
  • AsyncClient
  • Run Helpers
  • Run Trees
  • Evaluation
  • Schemas
  • Utilities
  • Wrappers
  • Anonymizer
  • Testing
  • Expect API
  • Middleware
  • Pytest Plugin
  • Deployment SDK
⌘I

LangChain Assistant

Ask a question to get started

Enter to send•Shift+Enter new line

Menu

OverviewClientAsyncClientRun HelpersRun TreesEvaluationSchemasUtilitiesWrappersAnonymizerTestingExpect APIMiddlewarePytest PluginDeployment SDK
Language
Theme
Pythonlangsmith_openapi_clientresourcesrunsRunsResourcequery_v2
Method●Since v0.9

query_v2

Copy
query_v2(
  self,
  *,
  cursor: str
View source on GitHub
|
Omit
=
omit
,
filter
:
str
|
Omit
=
omit
,
has_error
:
bool
|
Omit
=
omit
,
ids
:
SequenceNotStr
[
str
]
|
Omit
=
omit
,
is_root
:
bool
|
Omit
=
omit
,
max_start_time
:
Union
[
str
,
datetime
]
|
Omit
=
omit
,
min_start_time
:
Union
[
str
,
datetime
]
|
Omit
=
omit
,
page_size
:
int
|
Omit
=
omit
,
project_ids
:
SequenceNotStr
[
str
]
|
Omit
=
omit
,
reference_dataset_id
:
str
|
Omit
=
omit
,
reference_examples
:
SequenceNotStr
[
str
]
|
Omit
=
omit
,
run_type
:
Literal
[
'TOOL'
,
'CHAIN'
,
'LLM'
,
'RETRIEVER'
,
'EMBEDDING'
,
'PROMPT'
,
'PARSER'
]
|
Omit
=
omit
,
selects
:
List
[
Literal
[
'ID'
,
'NAME'
,
'RUN_TYPE'
,
'STATUS'
,
'START_TIME'
,
'END_TIME'
,
'LATENCY_SECONDS'
,
'FIRST_TOKEN_TIME'
,
'ERROR'
,
'ERROR_PREVIEW'
,
'EXTRA'
,
'METADATA'
,
'EVENTS'
,
'INPUTS'
,
'INPUTS_PREVIEW'
,
'OUTPUTS'
,
'OUTPUTS_PREVIEW'
,
'MANIFEST'
,
'PARENT_RUN_IDS'
,
'PROJECT_ID'
,
'TRACE_ID'
,
'THREAD_ID'
,
'DOTTED_ORDER'
,
'IS_ROOT'
,
'REFERENCE_EXAMPLE_ID'
,
'REFERENCE_DATASET_ID'
,
'TOTAL_TOKENS'
,
'PROMPT_TOKENS'
,
'COMPLETION_TOKENS'
,
'TOTAL_COST'
,
'PROMPT_COST'
,
'COMPLETION_COST'
,
'PROMPT_TOKEN_DETAILS'
,
'COMPLETION_TOKEN_DETAILS'
,
'PROMPT_COST_DETAILS'
,
'COMPLETION_COST_DETAILS'
,
'PRICE_MODEL_ID'
,
'TAGS'
,
'APP_PATH'
,
'ATTACHMENTS'
,
'THREAD_EVALUATION_TIME'
,
'IS_IN_DATASET'
,
'SHARE_URL'
,
'FEEDBACK_STATS'
]
]
|
Omit
=
omit
,
trace_filter
:
str
|
Omit
=
omit
,
trace_id
:
str
|
Omit
=
omit
,
tree_filter
:
str
|
Omit
=
omit
,
accept
:
str
|
Omit
=
omit
,
extra_headers
:
Headers
|
None
=
None
,
extra_query
:
Query
|
None
=
None
,
extra_body
:
Body
|
None
=
None
,
timeout
:
float
|
httpx
.
Timeout
|
None
|
NotGiven
=
not_given
)
->
SyncItemsCursorPostPagination
[
QueryRunResponse
]

Parameters

NameTypeDescription
cursorstr | Omit
Default:omit

cursor is the opaque string from a previous response's next_cursor. Treat it as opaque and pass it back unmodified.

filterstr | Omit
Default:omit

filter narrows results to runs matching this LangSmith filter expression, evaluated against each individual run. For example: and(eq(run_type, "llm"), gt(latency, 5)) or eq(status, "error"). See https://docs.langchain.com/langsmith/trace-query-syntax#filter-query-language for syntax.

has_errorbool | Omit
Default:omit
idsSequenceNotStr[str] | Omit
Default:omit
is_rootbool | Omit
Default:omit
max_start_timeUnion[str, datetime] | Omit
Default:omit
min_start_timeUnion[str, datetime] | Omit
Default:omit
page_sizeint | Omit
Default:omit
project_idsSequenceNotStr[str] | Omit
Default:omit
reference_dataset_idstr | Omit
Default:omit
reference_examplesSequenceNotStr[str] | Omit
Default:omit
run_typeLiteral['TOOL', 'CHAIN', 'LLM', 'RETRIEVER', 'EMBEDDING', 'PROMPT', 'PARSER'] | Omit
Default:omit
selectsList[Literal['ID', 'NAME', 'RUN_TYPE', 'STATUS', 'START_TIME', 'END_TIME', 'LATENCY_SECONDS', 'FIRST_TOKEN_TIME', 'ERROR', 'ERROR_PREVIEW', 'EXTRA', 'METADATA', 'EVENTS', 'INPUTS', 'INPUTS_PREVIEW', 'OUTPUTS', 'OUTPUTS_PREVIEW', 'MANIFEST', 'PARENT_RUN_IDS', 'PROJECT_ID', 'TRACE_ID', 'THREAD_ID', 'DOTTED_ORDER', 'IS_ROOT', 'REFERENCE_EXAMPLE_ID', 'REFERENCE_DATASET_ID', 'TOTAL_TOKENS', 'PROMPT_TOKENS', 'COMPLETION_TOKENS', 'TOTAL_COST', 'PROMPT_COST', 'COMPLETION_COST', 'PROMPT_TOKEN_DETAILS', 'COMPLETION_TOKEN_DETAILS', 'PROMPT_COST_DETAILS', 'COMPLETION_COST_DETAILS'
trace_filterstr | Omit
Default:omit
trace_idstr | Omit
Default:omit
tree_filterstr | Omit
Default:omit
extra_headersHeaders | None
Default:None
extra_queryQuery | None
Default:None
extra_bodyBody | None
Default:None
timeoutfloat | httpx.Timeout | None | NotGiven
Default:not_given

Alpha: The request and response contract may change; Returns a paginated list of runs for the given projects within min/max start_time. Supports filters, cursor pagination, and selects to select fields to return.

,
'PRICE_MODEL_ID'
,
'TAGS'
,
'APP_PATH'
,
'ATTACHMENTS'
,
'THREAD_EVALUATION_TIME'
,
'IS_IN_DATASET'
,
'SHARE_URL'
,
'FEEDBACK_STATS'
]] |
Omit
Default:omit

has_error filters to runs that errored (true) or completed without error (false).

ids optionally limits the request to these run UUIDs.

is_root returns only root runs (true) or only non-root runs (false).

max_start_time is the upper bound for run start_time (RFC3339). Defaults to now.

min_start_time is the lower bound for run start_time (RFC3339). Defaults to 1 day ago.

page_size is the maximum number of runs to return in this response. Defaults to 100 when omitted; must be between 1 and 1000 inclusive when set.

project_ids lists tracing project UUIDs to query. Required unless reference_dataset_id is set. Mutually exclusive with reference_dataset_id — set exactly one of them.

reference_dataset_id resolves session IDs server-side from the dataset. Required unless project_ids is set. Mutually exclusive with project_ids — set exactly one of them. When provided and min_start_time is omitted, the server derives it from the earliest session creation date.

reference_examples optionally limits to runs linked to these dataset example UUIDs.

run_type, when set, restricts results to runs whose run_type equals this value.

trace_filter narrows results to runs whose root trace matches this LangSmith filter expression. Use this to filter by properties of the trace's root run — for example eq(status, "success") to include only traces that completed without error. See https://docs.langchain.com/langsmith/trace-query-syntax#filter-query-language for syntax.

trace_id optionally limits results to runs belonging to this trace UUID.

tree_filter narrows results to runs that belong to a trace containing at least one run matching this LangSmith filter expression anywhere in the run tree (not just the root). Use this to find runs inside traces that involved a specific tool, tag, or model — for example has(tags, "production") or eq(name, "my_tool"). See https://docs.langchain.com/langsmith/trace-query-syntax#filter-query-language for syntax.

Send extra headers

Add additional query parameters to the request

Add additional JSON properties to the request

Override the client-level default timeout for this request, in seconds

selects lists which properties to include on each returned run. If omitted, only id is returned. Properties not listed are omitted from each run object.