MCPcopy Create free account

hub / github.com/langchain-ai/langgraph / functions

Functions7,100 in github.com/langchain-ai/langgraph

↓ 2 callersFunction_build_deferred_after_interrupt
(checkpointer: BaseCheckpointSaver)
libs/langgraph/tests/test_delta_channel_fork.py:732
↓ 2 callersMethod_build_delta_channels_writes_history
Demux stage 2 rows per channel; produce per-channel histories. stage2_rows carry `channel` on every row. We build per-channel `writes
libs/checkpoint-postgres/langgraph/checkpoint/postgres/base.py:452
↓ 2 callersFunction_build_delta_stage1_sql
Build stage 1 SQL with K parallel version lookups + seed probes. For channels=["messages", "files"] (with `paged=True`) the result is::
libs/checkpoint-postgres/langgraph/checkpoint/postgres/base.py:179
↓ 2 callersFunction_build_delta_stage2_sql
Build stage 2 SQL as a per-channel UNION ALL. For each channel with a non-empty chain, emit one branch reading `checkpoint_writes` for that s
libs/checkpoint-postgres/langgraph/checkpoint/postgres/base.py:271
↓ 2 callersFunction_build_image
( runner: CommandRunner, spec: BuildSpec, tag: str, *, verbose: bool )
libs/cli/langgraph_cli/deploy.py:1179
↓ 2 callersFunction_build_interrupt_graph
()
libs/langgraph/tests/test_pregel_stream_events_v3.py:79
↓ 2 callersMethod_build_mixed_thread
Four-checkpoint chain spanning the migration boundary: * `cp0` — pre-delta ancestor OLDER than the seed. Its write (`OLDER-WRITE`)
libs/checkpoint/tests/test_memory.py:579
↓ 2 callersFunction_build_python_install_commands
( config: Config, install_cmd: str )
libs/cli/langgraph_cli/config.py:1181
↓ 2 callersFunction_build_server_info
Build ServerInfo from config configurable. The server puts assistant_id/graph_id in config configurable and the authenticated user dict in co
libs/langgraph/langgraph/pregel/main.py:4371
↓ 2 callersFunction_build_without_delta_writes
(checkpointer: BaseCheckpointSaver, tag: str)
libs/langgraph/tests/test_delta_channel_fork.py:63
↓ 2 callersFunction_bump_keys
(node: str, channel: str)
libs/langgraph/langgraph/pregel/_checkpoint.py:329
↓ 2 callersFunction_call_with_options
( func: Callable[P, Awaitable[T]] | Callable[P, T], args: tuple[Any, ...], kwargs: dict[str, Any],
libs/langgraph/langgraph/pregel/_call.py:276
↓ 2 callersMethod_capturing_runner
Like ``_runner`` but exposes the coroutine for arg introspection. Caller must close ``captured["coro"]``.
libs/cli/tests/unit_tests/test_deploy_helpers.py:892
↓ 2 callersFunction_checkpointer_memory
()
libs/langgraph/tests/conftest_checkpointer.py:45
↓ 2 callersFunction_checkpointer_memory
()
libs/prebuilt/tests/conftest_checkpointer.py:17
↓ 2 callersFunction_close_after
Close a handle, optionally after a brief delay. Used to detach closing the old stream from the synchronous rotation step so the new stream ca
libs/sdk-py/langgraph_sdk/stream/controller.py:80
↓ 2 callersMethod_close_or_fail_handle
( self, handle: SubgraphRunStream | AsyncSubgraphRunStream, status: SubgraphStatus,
libs/langgraph/langgraph/stream/transformers.py:775
↓ 2 callersFunction_coerce_context
Coerce context input to the appropriate schema type. If context is a dict and context_schema is a dataclass or pydantic model, we coerce. Els
libs/langgraph/langgraph/pregel/main.py:4402
↓ 2 callersFunction_coerce_parent_runtime
Normalize the value stored under `CONFIG_KEY_RUNTIME` into a `Runtime`. During a graph run this is always a `Runtime` the framework created and
libs/langgraph/langgraph/pregel/main.py:4354
↓ 2 callersFunction_coerce_pending_error
(value: Any)
libs/langgraph/langgraph/pregel/_algo.py:764
↓ 2 callersMethod_collect_scheduled_tasks
Return a snapshot of in-flight tasks scheduled via transformers.
libs/langgraph/langgraph/stream/_mux.py:451
↓ 2 callersFunction_collect_stream_modes
Return the union of `required_stream_modes` across registered transformers. Transformers declare the stream modes they need to function, and
libs/langgraph/langgraph/pregel/main.py:404
↓ 2 callersMethod_combine_tool_outputs
( self, outputs: list[ToolMessage | Command | list[ToolMessage | Command]], input_type
libs/prebuilt/langgraph/prebuilt/tool_node.py:862
↓ 2 callersFunction_config_with_channel_read
Build a config that mimics `CONFIG_KEY_READ` as Pregel installs it. Pregel always installs a `functools.partial(local_read, scratchpad, chann
libs/prebuilt/tests/test_on_tool_call.py:1324
↓ 2 callersFunction_configure_graph_callbacks
( cls: type[_GraphManagerT], callbacks: object | None, *, run_id: UUID | None, )
libs/langgraph/langgraph/callbacks.py:154
↓ 2 callersFunction_convert_future_exc
(exc: BaseException)
libs/langgraph/langgraph/_internal/_future.py:31
↓ 2 callersFunction_copy_graph_manager
( manager: _GraphCallbackManager | _AsyncGraphCallbackManager, cls: type[_GraphManagerT], run_id:
libs/langgraph/langgraph/callbacks.py:194
↓ 2 callersFunction_create_config_with_runtime
Create a RunnableConfig with mocked runtime for direct ToolNode testing.
libs/prebuilt/tests/test_injected_state_not_required.py:62
↓ 2 callersFunction_create_deployment
( client: HostBackendClient, step: int, *, name: str | None, source: str, source_confi
libs/cli/langgraph_cli/deploy.py:854
↓ 2 callersFunction_create_mock_runtime
Create a mock Runtime object for testing ToolNode outside of graph context. This helper is needed because ToolNode._func expects a Runtime parame
libs/prebuilt/tests/test_tool_node.py:59
↓ 2 callersFunction_create_root_model
Create a base class.
libs/langgraph/langgraph/_internal/_pydantic.py:61
↓ 2 callersMethod_cursor
Get a cursor for the SQLite database. Args: transaction: Whether to use a transaction for database operations. Yields:
libs/checkpoint-sqlite/langgraph/store/sqlite/aio.py:224
↓ 2 callersMethod_dedup_iter
(self, source: Any)
libs/sdk-py/langgraph_sdk/stream/sync_controller.py:252
↓ 2 callersMethod_defaults
( self, config: RunnableConfig, *, stream_mode: StreamMode | Sequence[StreamMo
libs/langgraph/langgraph/pregel/main.py:2621
↓ 2 callersFunction_delta_channels_to_replay
DeltaChannels whose value at `checkpoint` the ancestor walk rebuilds. A `_DeltaSnapshot` blob or a plain value (migration) resolves directly via
libs/langgraph/langgraph/pregel/_checkpoint.py:355
↓ 2 callersFunction_describe_listeners
(listeners: Sequence[Listener])
libs/cli/langgraph_cli/deploy.py:279
↓ 2 callersFunction_drive
(graph: Any, config: RunnableConfig, tag: str, n: int)
libs/checkpoint-sqlite/tests/test_delta_channel_migration.py:80
↓ 2 callersFunction_dump_blobs
( serde: SerializerProtocol, thread_id: str, checkpoint_ns: str, values: dict[str, Any], v
libs/checkpoint-postgres/langgraph/checkpoint/postgres/shallow.py:148
↓ 2 callersMethod_dump_writes
( self, thread_id: str, checkpoint_ns: str, checkpoint_id: str, task_i
libs/checkpoint-postgres/langgraph/checkpoint/postgres/base.py:571
↓ 2 callersMethod_embed_one
Embed a single text.
libs/checkpoint-sqlite/tests/test_store.py:49
↓ 2 callersMethod_embed_one
Embed a single text.
libs/checkpoint-postgres/tests/embed_test_utils.py:25
↓ 2 callersMethod_embed_one
Embed a single text.
libs/checkpoint/tests/embed_test_utils.py:25
↓ 2 callersFunction_ensure_future
( coro_or_future: Coroutine[None, None, T] | Awaitable[T], *, loop: asyncio.AbstractEventLoop,
libs/langgraph/langgraph/_internal/_future.py:143
↓ 2 callersFunction_ensure_index_config
Process and validate index configuration.
libs/checkpoint-sqlite/langgraph/store/sqlite/base.py:1486
↓ 2 callersFunction_ensure_index_config
( index_config: PostgresIndexConfig, )
libs/checkpoint-postgres/langgraph/store/postgres/base.py:1453
↓ 2 callersFunction_escape_glob_literal
Escape GLOB metacharacters so `text` is matched literally. GLOB has no `ESCAPE` clause, so metacharacters are wrapped in a character class in
libs/checkpoint-sqlite/langgraph/store/sqlite/base.py:111
↓ 2 callersFunction_escape_like_literal
Escape LIKE metacharacters so `text` is matched literally. Namespace labels may contain `_` and `%`, which would otherwise act as wildcards:
libs/checkpoint-postgres/langgraph/store/postgres/base.py:1283
↓ 2 callersFunction_event_items
(mux: StreamMux)
libs/langgraph/tests/test_stream_subgraph_transformer.py:176
↓ 2 callersMethod_execute_tool_async
Execute tool call asynchronously with configured error handling. Args: request: Tool execution request. input_type: I
libs/prebuilt/langgraph/prebuilt/tool_node.py:1069
↓ 2 callersFunction_extract_env_json
Helper to extract and parse a JSON value from an ENV line in a Dockerfile.
libs/cli/tests/unit_tests/test_config.py:1326
↓ 2 callersMethod_extract_state
Extract state from input. Three input shapes: - `ToolCallWithContext` dict — legacy Send payload carrying an inlined state
libs/prebuilt/langgraph/prebuilt/tool_node.py:1281
↓ 2 callersMethod_extract_texts
( self, put_ops: dict[tuple[tuple[str, ...], str], PutOp] )
libs/checkpoint/langgraph/store/memory/__init__.py:418
↓ 2 callersMethod_fail
(self, message: str)
libs/prebuilt/langgraph/prebuilt/_tool_call_stream.py:85
↓ 2 callersMethod_fail_active_message_streams
(self, err: BaseException)
libs/sdk-py/langgraph_sdk/_async/stream.py:1351
↓ 2 callersMethod_fail_active_message_streams
(self, err: BaseException)
libs/sdk-py/langgraph_sdk/_sync/stream.py:1238
↓ 2 callersMethod_fail_active_tool_calls
(self, err: BaseException)
libs/sdk-py/langgraph_sdk/_async/stream.py:1362
↓ 2 callersMethod_fail_active_tool_calls
(self, err: BaseException)
libs/sdk-py/langgraph_sdk/_sync/stream.py:1249
↓ 2 callersFunction_fetch
(request_payload: dict)
libs/cli/langgraph_cli/deploy.py:2615
↓ 2 callersFunction_fetch_deployment
( client: HostBackendClient, step: int, selector: ById )
libs/cli/langgraph_cli/deploy.py:792
↓ 2 callersMethod_fetch_state
Fetch the current thread state from the REST endpoint.
libs/sdk-py/langgraph_sdk/_async/stream.py:1903
↓ 2 callersMethod_fetch_state
Fetch the current thread state from the REST endpoint.
libs/sdk-py/langgraph_sdk/_sync/stream.py:1553
↓ 2 callersFunction_filter_graph_handlers
( handlers: list[BaseCallbackHandler], )
libs/langgraph/langgraph/callbacks.py:117
↓ 2 callersFunction_filter_validation_errors
Filter validation errors to only include LLM-controlled arguments. When a tool invocation fails validation, only errors for arguments that the LL
libs/prebuilt/langgraph/prebuilt/tool_node.py:510
↓ 2 callersMethod_filter_with_since
(self, params: dict[str, Any])
libs/sdk-py/langgraph_sdk/stream/sync_controller.py:246
↓ 2 callersMethod_filter_with_since
(self, params: dict[str, Any])
libs/sdk-py/langgraph_sdk/stream/controller.py:380
↓ 2 callersFunction_find_deployment
( client: HostBackendClient, step: int, selector: ByName | ByAgent, *, not_found_message:
libs/cli/langgraph_cli/deploy.py:802
↓ 2 callersMethod_finish
( self, writer: _Writer, input: Any, result: Any, config: RunnableConf
libs/langgraph/langgraph/graph/_branch.py:192
↓ 2 callersMethod_finish
(self, output: Any)
libs/prebuilt/langgraph/prebuilt/_tool_call_stream.py:80
↓ 2 callersMethod_finish
(self, status: SubgraphStatus, error: str | None = None)
libs/sdk-py/langgraph_sdk/_sync/stream.py:740
↓ 2 callersMethod_finish
(self, output)
libs/sdk-py/tests/streaming/test_decoders.py:185
↓ 2 callersMethod_first
( self, *, input_keys: str | Sequence[str], updated_channels: set[str] | None )
libs/langgraph/langgraph/pregel/_loop.py:860
↓ 2 callersMethod_generate
Top Level call
libs/langgraph/tests/fake_chat.py:22
↓ 2 callersFunction_get_all_injected_args
Extract all injected arguments from tool in a single pass. This function analyzes both the tool's input schema and function signature to iden
libs/prebuilt/langgraph/prebuilt/tool_node.py:1967
↓ 2 callersMethod_get_batch_GET_ops_queries
Build queries to fetch (and optionally refresh the TTL of) multiple keys per namespace. Returns a list of PreparedGetQuery objects,
libs/checkpoint-sqlite/langgraph/store/sqlite/base.py:882
↓ 2 callersMethod_get_batch_GET_ops_queries
Build queries to fetch (and optionally refresh the TTL of) multiple keys per namespace. Each returned element is a tuple of:
libs/checkpoint-postgres/langgraph/store/postgres/base.py:249
↓ 2 callersMethod_get_batch_list_namespaces_queries
( self, list_ops: Sequence[tuple[int, ListNamespacesOp]], )
libs/checkpoint-postgres/langgraph/store/postgres/base.py:590
↓ 2 callersMethod_get_config
(self, checkpoint: Checkpoint)
libs/langgraph/langgraph/pregel/remote.py:397
↓ 2 callersMethod_get_drawable_nodes
( self, graph: dict[str, list[dict[str, Any]]] )
libs/langgraph/langgraph/pregel/remote.py:232
↓ 2 callersFunction_get_headers
Combine api_key and custom user-provided headers.
libs/sdk-py/langgraph_sdk/_shared/utilities.py:51
↓ 2 callersFunction_get_json_schema
( typ: type, schemas: dict, channels: dict, name: str, )
libs/langgraph/langgraph/graph/state.py:1944
↓ 2 callersFunction_get_model_input_state
(state: StateSchema)
libs/prebuilt/langgraph/prebuilt/chat_agent_executor.py:636
↓ 2 callersFunction_get_node_name
(node: StateNode[Any, ContextT])
libs/langgraph/langgraph/graph/state.py:124
↓ 2 callersFunction_get_run_metadata_from_response
Extract run metadata from the response headers.
libs/sdk-py/langgraph_sdk/_shared/utilities.py:100
↓ 2 callersFunction_get_source_kind
(config: Config)
libs/cli/langgraph_cli/config.py:376
↓ 2 callersMethod_get_stream_modes
Return a tuple of the final list of stream modes sent to the remote graph and a boolean flag indicating if stream mode 'updates' was p
libs/langgraph/langgraph/pregel/remote.py:672
↓ 2 callersMethod_get_task
Return the shared fetch task, creating it on first call. A cancelled task is intentionally NOT respawned: subsequent awaiters receive
libs/sdk-py/langgraph_sdk/_async/stream.py:309
↓ 2 callersFunction_get_tracing_metadata_defaults
Get tracer-only metadata defaults from configurable values.
libs/langgraph/langgraph/_internal/_config.py:435
↓ 2 callersFunction_get_uv_lock_package_enabled
(package: UvLockPackage)
libs/cli/langgraph_cli/uv_lock.py:240
↓ 2 callersFunction_getattribute
(obj: Any, name: str)
libs/langgraph/langgraph/pregel/_call.py:37
↓ 2 callersFunction_graph_never_run
()
libs/langgraph/tests/test_pregel.py:9566
↓ 2 callersFunction_group_ops
(ops: Iterable[Op])
libs/checkpoint-sqlite/langgraph/store/sqlite/base.py:256
↓ 2 callersFunction_group_ops
(ops: Iterable[Op])
libs/checkpoint-postgres/langgraph/store/postgres/base.py:1385
↓ 2 callersMethod_guard_call
(self, call: Callable[..., Any])
libs/langgraph/langgraph/pregel/_retry.py:249
↓ 2 callersMethod_guard_stream
(self, stream: StreamProtocol)
libs/langgraph/langgraph/pregel/_retry.py:237
↓ 2 callersMethod_guard_stream_writer
( self, stream_writer: Callable[[Any], None] )
libs/langgraph/langgraph/pregel/_retry.py:260
↓ 2 callersMethod_handle_for_event
( self, event: ProtocolEvent )
libs/langgraph/langgraph/stream/transformers.py:801
↓ 2 callersMethod_handle_task_start
(self, ns: tuple[str, ...], data: dict[str, Any])
libs/langgraph/langgraph/stream/transformers.py:518
↓ 2 callersFunction_image_supports_uv
(base_image: str)
libs/cli/langgraph_cli/config.py:1300
↓ 2 callersMethod_infer_as_node
(self, versions_seen: dict[str, ChannelVersions])
libs/langgraph/langgraph/pregel/main.py:1594
↓ 2 callersMethod_ingest_stage1_page
Fold one stage-1 page into the running walk-state mappings. Returns the oldest checkpoint_id seen on this page (smallest, since pages
libs/checkpoint-postgres/langgraph/checkpoint/postgres/base.py:363
← previousnext →801–900 of 7,100, ranked by callers