Title: langgraph | LangChain Reference
Open Graph Title: langgraph
X Title: langgraph
Description: Python API reference for langgraph. Part of the LangChain ecosystem.
Open Graph Description: Python API reference for langgraph. Part of the LangChain ecosystem.
X Description: Python API reference for langgraph. Part of the LangChain ecosystem.
Opengraph URL: https://reference.langchain.com/python/langgraph
Domain: reference.langchain.com
| og:image | https://reference.langchain.com/og/python/langgraph |
| og:image:width | 1200 |
| og:image:height | 630 |
| og:image:alt | langgraph |
| og:type | article |
| twitter:card | summary_large_image |
| twitter:image | https://reference.langchain.com/og/python/langgraph |
Links:
| LangChain Reference home page | https://reference.langchain.com/ |
| GitHub | https://github.com/langchain-ai |
| Main Docs | https://docs.langchain.com/oss/python/langgraph |
| Deep Agents | https://reference.langchain.com/python/deepagents |
| LangChain | https://reference.langchain.com/python/langchain/overview |
| LangGraph | https://reference.langchain.com/python/langgraph/overview |
| Integrations | https://reference.langchain.com/python/integrations/overview |
| LangSmith | https://reference.langchain.com/python/langsmith |
| Overview | https://reference.langchain.com/python/langgraph/overview |
| Overview | https://reference.langchain.com/python/langgraph |
| Graphs | https://reference.langchain.com/python/langgraph/graphs |
| Functional API | https://reference.langchain.com/python/langgraph/func |
| Pregel | https://reference.langchain.com/python/langgraph/pregel |
| Checkpointing | https://reference.langchain.com/python/langgraph/checkpoints |
| Storage | https://reference.langchain.com/python/langgraph/store |
| Caching | https://reference.langchain.com/python/langgraph/cache |
| Types | https://reference.langchain.com/python/langgraph/types |
| Runtime | https://reference.langchain.com/python/langgraph/runtime |
| Config | https://reference.langchain.com/python/langgraph/config |
| Errors | https://reference.langchain.com/python/langgraph/errors |
| Constants | https://reference.langchain.com/python/langgraph/constants |
| Channels | https://reference.langchain.com/python/langgraph/channels |
| Agents | https://reference.langchain.com/python/langgraph/agents |
| LangGraph Checkpoint | https://reference.langchain.com/python/langgraph.checkpoint |
| LangGraph Store | https://reference.langchain.com/python/langgraph.store |
| Checkpoint Postgres | https://reference.langchain.com/python/langgraph.checkpoint.postgres |
| Store Postgres | https://reference.langchain.com/python/langgraph.store.postgres |
| Checkpoint SQLite | https://reference.langchain.com/python/langgraph.checkpoint.sqlite |
| LangGraph Prebuilt | https://reference.langchain.com/python/langgraph.prebuilt |
| LangGraph CLI | https://reference.langchain.com/python/langgraph-cli |
| LangGraph SDK | https://reference.langchain.com/python/langgraph-sdk |
| LangGraph Supervisor | https://reference.langchain.com/python/langgraph-supervisor |
| LangGraph Swarm | https://reference.langchain.com/python/langgraph-swarm |
| https://chat.langchain.com/ | |
| Overview | https://reference.langchain.com/python/langgraph |
| Graphs | https://reference.langchain.com/python/langgraph/graphs |
| Functional API | https://reference.langchain.com/python/langgraph/func |
| Pregel | https://reference.langchain.com/python/langgraph/pregel |
| Checkpointing | https://reference.langchain.com/python/langgraph/checkpoints |
| Storage | https://reference.langchain.com/python/langgraph/store |
| Caching | https://reference.langchain.com/python/langgraph/cache |
| Types | https://reference.langchain.com/python/langgraph/types |
| Runtime | https://reference.langchain.com/python/langgraph/runtime |
| Config | https://reference.langchain.com/python/langgraph/config |
| Errors | https://reference.langchain.com/python/langgraph/errors |
| Constants | https://reference.langchain.com/python/langgraph/constants |
| Channels | https://reference.langchain.com/python/langgraph/channels |
| Agents | https://reference.langchain.com/python/langgraph/agents |
| LangGraph Checkpoint | https://reference.langchain.com/python/langgraph.checkpoint |
| LangGraph Store | https://reference.langchain.com/python/langgraph.store |
| Checkpoint Postgres | https://reference.langchain.com/python/langgraph.checkpoint.postgres |
| Store Postgres | https://reference.langchain.com/python/langgraph.store.postgres |
| Checkpoint SQLite | https://reference.langchain.com/python/langgraph.checkpoint.sqlite |
| LangGraph Prebuilt | https://reference.langchain.com/python/langgraph.prebuilt |
| LangGraph CLI | https://reference.langchain.com/python/langgraph-cli |
| LangGraph SDK | https://reference.langchain.com/python/langgraph-sdk |
| LangGraph Supervisor | https://reference.langchain.com/python/langgraph-supervisor |
| LangGraph Swarm | https://reference.langchain.com/python/langgraph-swarm |
| https://pypi.org/project/langgraph/#history | |
| https://opensource.org/licenses/MIT | |
| https://pypistats.org/packages/langgraph | |
| https://github.com/langchain-ai/langgraph/issues | |
| https://x.com/langchain_oss | |
| LangGraph.js | https://github.com/langchain-ai/langgraphjs |
| LangSmith | https://www.langchain.com/langsmith |
| LangSmith | https://www.langchain.com/langsmith |
| LangChain | https://docs.langchain.com/oss/python/langchain/overview |
| agents | https://docs.langchain.com/oss/python/langchain/agents |
| API reference | https://reference.langchain.com/python/langgraph/ |
| LangGraph Docs | https://docs.langchain.com/oss/python/langgraph/overview |
| LangGraph Quickstart | https://docs.langchain.com/oss/python/langgraph/quickstart |
| Releases | https://docs.langchain.com/oss/python/release-policy |
| Versioning | https://docs.langchain.com/oss/python/versioning |
| Contributing Guide | https://docs.langchain.com/oss/python/contributing/overview |
| Pregel | https://research.google/pubs/pub37252/ |
| Apache Beam | https://beam.apache.org/ |
| NetworkX | https://networkx.org/documentation/latest/ |
| ClassGraphInterruptEventGraph lifecycle event emitted when execution pauses for interrupts. | https://reference.langchain.com/python/langgraph/callbacks/GraphInterruptEvent |
| ClassGraphResumeEventGraph lifecycle event emitted when execution resumes from a checkpoint. | https://reference.langchain.com/python/langgraph/callbacks/GraphResumeEvent |
| ClassGraphCallbackHandlerBase class for graph-level lifecycle callbacks. Subclass this handler to observe graph lifecycle transitions that are specific to LangGraph execution, rather than generic LangChain runnable callbacks | https://reference.langchain.com/python/langgraph/callbacks/GraphCallbackHandler |
| ClassToolOutputMixin | https://reference.langchain.com/python/langgraph/types/ToolOutputMixin |
| ClassTaskPayloadPayload for a task start event. | https://reference.langchain.com/python/langgraph/types/TaskPayload |
| ClassTaskResultPayloadPayload for a task result event. | https://reference.langchain.com/python/langgraph/types/TaskResultPayload |
| ClassCheckpointTaskA task entry within a CheckpointPayload. The keys present depend on the task's state: Error: id, name, error, state Has result: id, name, result, interrupts, state | https://reference.langchain.com/python/langgraph/types/CheckpointTask |
| ClassCheckpointPayloadPayload for a checkpoint event. | https://reference.langchain.com/python/langgraph/types/CheckpointPayload |
| ClassValuesStreamPartStream part emitted for stream_mode="values". data contains the full state after each step, as returned by read_channels(). | https://reference.langchain.com/python/langgraph/types/ValuesStreamPart |
| ClassUpdatesStreamPartStream part emitted for stream_mode="updates". data maps node names to their outputs. May also contain __interrupt__ (tuple of Interrupt dicts) and __metadata__ keys. | https://reference.langchain.com/python/langgraph/types/UpdatesStreamPart |
| ClassMessagesStreamPartStream part emitted for stream_mode="messages". data is a 2-tuple of (message, metadata) where message is a BaseMessage (e.g. AIMessageChunk) and metadata is a dict containing keys like | https://reference.langchain.com/python/langgraph/types/MessagesStreamPart |
| ClassCustomStreamPartStream part emitted for stream_mode="custom". data is whatever value was passed to StreamWriter inside a node. | https://reference.langchain.com/python/langgraph/types/CustomStreamPart |
| ClassCheckpointStreamPartStream part emitted for stream_mode="checkpoints". | https://reference.langchain.com/python/langgraph/types/CheckpointStreamPart |
| ClassTasksStreamPartStream part emitted for stream_mode="tasks". For task start events, data is a TaskPayload with id, name, input, and triggers keys. For task result events, data is a `TaskResultPayloa | https://reference.langchain.com/python/langgraph/types/TasksStreamPart |
| ClassDebugStreamPartStream part emitted for stream_mode="debug". | https://reference.langchain.com/python/langgraph/types/DebugStreamPart |
| ClassGraphOutputTyped container returned by invoke() / ainvoke() with version="v2". | https://reference.langchain.com/python/langgraph/types/GraphOutput |
| ClassRetryPolicyConfiguration for retrying nodes. | https://reference.langchain.com/python/langgraph/types/RetryPolicy |
| ClassTimeoutPolicyConfiguration for timing out node attempts. Cooperative cancellationTimeouts rely on asyncio cancellation. If your node uses synchronous time.sleep() or other CPU-bound work that | https://reference.langchain.com/python/langgraph/types/TimeoutPolicy |
| ClassCachePolicyConfiguration for caching nodes. | https://reference.langchain.com/python/langgraph/types/CachePolicy |
| ClassTracePolicyConfiguration for how a node's run is traced. Scope: this only transforms what the node's own run records. Child runs created by a traced bound runnable and the root graph run are not affected. P | https://reference.langchain.com/python/langgraph/types/TracePolicy |
| ClassInterruptInformation about an interrupt that occurred in a node. Changed in version v0.4.0 interrupt_id was introduced as a property | https://reference.langchain.com/python/langgraph/types/Interrupt |
| ClassStateUpdate | https://reference.langchain.com/python/langgraph/types/StateUpdate |
| ClassPregelTaskA Pregel task. | https://reference.langchain.com/python/langgraph/types/PregelTask |
| ClassCacheKeyCache key for a task. | https://reference.langchain.com/python/langgraph/types/CacheKey |
| ClassPregelExecutableTask | https://reference.langchain.com/python/langgraph/types/PregelExecutableTask |
| ClassStateSnapshotSnapshot of the state of the graph at the beginning of a step. | https://reference.langchain.com/python/langgraph/types/StateSnapshot |
| ClassSendA message or packet to send to a specific node in the graph. The Send class is used within a StateGraph's conditional edges to dynamically invoke a node with a custom state at the next step. Imp | https://reference.langchain.com/python/langgraph/types/Send |
| ClassCommandOne or more commands to update the graph's state and send messages to nodes. | https://reference.langchain.com/python/langgraph/types/Command |
| ClassOverwriteBypass a reducer and write the wrapped value directly to a BinaryOperatorAggregate channel. Receiving multiple Overwrite values for the same channel in a single super-step will raise an `InvalidU | https://reference.langchain.com/python/langgraph/types/Overwrite |
| ClassLangGraphDeprecationWarningA LangGraph specific deprecation warning. | https://reference.langchain.com/python/langgraph/warnings/LangGraphDeprecationWarning |
| ClassLangGraphDeprecatedSinceV05A specific LangGraphDeprecationWarning subclass defining functionality deprecated since LangGraph v0.5.0 | https://reference.langchain.com/python/langgraph/warnings/LangGraphDeprecatedSinceV05 |
| ClassLangGraphDeprecatedSinceV10A specific LangGraphDeprecationWarning subclass defining functionality deprecated since LangGraph v1.0.0 | https://reference.langchain.com/python/langgraph/warnings/LangGraphDeprecatedSinceV10 |
| ClassLangGraphDeprecatedSinceV11A specific LangGraphDeprecationWarning subclass defining functionality deprecated since LangGraph v1.1.0 | https://reference.langchain.com/python/langgraph/warnings/LangGraphDeprecatedSinceV11 |
| ClassExecutionInfoRead-only execution info/metadata for the execution of current thread/run/node. | https://reference.langchain.com/python/langgraph/runtime/ExecutionInfo |
| ClassServerInfoMetadata injected by LangGraph Server. None when running open-source LangGraph without LangSmith deployments. | https://reference.langchain.com/python/langgraph/runtime/ServerInfo |
| ClassRunControlRun-scoped control surface for cooperative draining. Intended for a single graph run. Create a fresh RunControl per run; reusing a control after request_drain() leaves it drained. Safe to call f | https://reference.langchain.com/python/langgraph/runtime/RunControl |
| ClassRuntimeConvenience class that bundles run-scoped context and other runtime utilities. This class is injected into graph nodes and middleware. It provides access to context, store, stream_writer, `prev | https://reference.langchain.com/python/langgraph/runtime/Runtime |
| ClassErrorCode | https://reference.langchain.com/python/langgraph/errors/ErrorCode |
| ClassGraphBubbleUp | https://reference.langchain.com/python/langgraph/errors/GraphBubbleUp |
| ClassGraphDrainedRaised when a graph run exits early due to a drain request. This indicates the graph stopped cooperatively at a superstep boundary because RunControl.request_drain() was called (e.g., in response t | https://reference.langchain.com/python/langgraph/errors/GraphDrained |
| ClassGraphRecursionErrorRaised when the graph has exhausted the maximum number of steps. This prevents infinite loops. To increase the maximum number of steps, run your graph with a config specifying a higher `recursion_lim | https://reference.langchain.com/python/langgraph/errors/GraphRecursionError |
| ClassInvalidUpdateErrorRaised when attempting to update a channel with an invalid set of updates. Troubleshooting guides: [INVALID_CONCURRENT_GRAPH_UPDATE](https://docs.langchain.com/oss/python/langgraph/INVALID_CONCU | https://reference.langchain.com/python/langgraph/errors/InvalidUpdateError |
| ClassGraphInterruptRaised when a subgraph is interrupted, suppressed by the root graph. Never raised directly, or surfaced to the user. | https://reference.langchain.com/python/langgraph/errors/GraphInterrupt |
| ClassParentCommand | https://reference.langchain.com/python/langgraph/errors/ParentCommand |
| ClassEmptyInputErrorRaised when graph receives an empty input. | https://reference.langchain.com/python/langgraph/errors/EmptyInputError |
| ClassTaskNotFoundRaised when the executor is unable to find a task (for distributed mode). | https://reference.langchain.com/python/langgraph/errors/TaskNotFound |
| ClassNodeErrorFailure context passed to a node-level error handler. Inject by adding a parameter typed NodeError to a handler registered via StateGraph.add_node(..., error_handler=...): def handler( | https://reference.langchain.com/python/langgraph/errors/NodeError |
| ClassNodeCancelledErrorRaised when a node body raises asyncio.CancelledError itself. asyncio.CancelledError is a BaseException and the pregel runner treats cancelled task futures as silent tear-down (e.g. when | https://reference.langchain.com/python/langgraph/errors/NodeCancelledError |
| ClassNodeTimeoutErrorRaised when a node invocation exceeds one of its configured timeouts. Does not inherit from the built-in TimeoutError (a subclass of OSError) so that the default RetryPolicy treats it as re | https://reference.langchain.com/python/langgraph/errors/NodeTimeoutError |
| ClassNamedBarrierValueA channel that waits until all named values are received before making the value available. | https://reference.langchain.com/python/langgraph/channels/named_barrier_value/NamedBarrierValue |
| ClassNamedBarrierValueAfterFinishA channel that waits until all named values are received before making the value ready to be made available. It is only made available after finish() is called. | https://reference.langchain.com/python/langgraph/channels/named_barrier_value/NamedBarrierValueAfterFinish |
| ClassBaseChannelBase class for all channels. | https://reference.langchain.com/python/langgraph/channels/base/BaseChannel |
| ClassUntrackedValueStores the last value received, never checkpointed. | https://reference.langchain.com/python/langgraph/channels/untracked_value/UntrackedValue |
| ClassEphemeralValueStores the value received in the step immediately preceding, clears after. | https://reference.langchain.com/python/langgraph/channels/ephemeral_value/EphemeralValue |
| ClassLastValueStores the last value received, can receive at most one value per step. | https://reference.langchain.com/python/langgraph/channels/last_value/LastValue |
| ClassLastValueAfterFinishStores the last value received, but only made available after finish(). Once made available, clears the value. | https://reference.langchain.com/python/langgraph/channels/last_value/LastValueAfterFinish |
| ClassBinaryOperatorAggregateStores the result of applying a binary operator to the current value and each new value. import operator total = Channels.BinaryOperatorAggregate(int, operator.add) | https://reference.langchain.com/python/langgraph/channels/binop/BinaryOperatorAggregate |
| ClassTopicA configurable PubSub Topic. | https://reference.langchain.com/python/langgraph/channels/topic/Topic |
| ClassDeltaChannelReducer channel that stores only a sentinel in checkpoint blobs and reconstructs state by replaying ancestor writes through the reducer. BetaDeltaChannel is in beta. The API and | https://reference.langchain.com/python/langgraph/channels/delta/DeltaChannel |
| ClassAnyValueStores the last value received, assumes that if multiple values are received, they are all equal. | https://reference.langchain.com/python/langgraph/channels/any_value/AnyValue |
| ClassAsyncQueueAsync unbounded FIFO queue with a wait() method. Subclassed from asyncio.Queue, adding a wait() method. | https://reference.langchain.com/python/langgraph/_internal/_queue/AsyncQueue |
| ClassSemaphoreSemaphore subclass with a wait() method. | https://reference.langchain.com/python/langgraph/_internal/_queue/Semaphore |
| ClassSyncQueueUnbounded FIFO queue with a wait() method. Adapted from pure Python implementation of queue.SimpleQueue. | https://reference.langchain.com/python/langgraph/_internal/_queue/SyncQueue |
| ClassReplayStateTracks which subgraphs have already loaded their pre-replay checkpoint. During a parent replay, each subgraph's first invocation should restore the checkpoint from before the replay point. Subsequent | https://reference.langchain.com/python/langgraph/_internal/_replay/ReplayState |
| ClassPregelScratchpad | https://reference.langchain.com/python/langgraph/_internal/_scratchpad/PregelScratchpad |
| ClassTypedDictLikeV1Protocol to represent types that behave like TypedDicts Version 1: using ClassVar for keys. | https://reference.langchain.com/python/langgraph/_internal/_typing/TypedDictLikeV1 |
| ClassTypedDictLikeV2Protocol to represent types that behave like TypedDicts Version 2: not using ClassVar for keys. | https://reference.langchain.com/python/langgraph/_internal/_typing/TypedDictLikeV2 |
| ClassDataclassLikeProtocol to represent types that behave like dataclasses. Inspired by the private _DataclassT from dataclasses that uses a similar protocol as a bound. | https://reference.langchain.com/python/langgraph/_internal/_typing/DataclassLike |
| ClassDeprecatedKwargsTypedDict to use for extra keyword arguments, enabling type checking warnings for deprecated arguments. | https://reference.langchain.com/python/langgraph/_internal/_typing/DeprecatedKwargs |
| ClassStrEnumA string enum. | https://reference.langchain.com/python/langgraph/_internal/_runnable/StrEnum |
| ClassRunnableCallableA much simpler version of RunnableLambda that requires sync and async functions. | https://reference.langchain.com/python/langgraph/_internal/_runnable/RunnableCallable |
| ClassRunnableSeqSequence of Runnable, where the output of each is the input of the next. RunnableSeq is a simpler version of RunnableSequence that is internal to LangGraph. | https://reference.langchain.com/python/langgraph/_internal/_runnable/RunnableSeq |
| ClassMessagesState | https://reference.langchain.com/python/langgraph/graph/message/MessagesState |
| ClassStateNodeSpec | https://reference.langchain.com/python/langgraph/graph/_node/StateNodeSpec |
| ClassUIMessageA message type for UI updates in LangGraph. This TypedDict represents a UI message that can be sent to update the UI state. It contains information about the UI component to render and its properties | https://reference.langchain.com/python/langgraph/graph/ui/UIMessage |
| ClassRemoveUIMessageA message type for removing UI components in LangGraph. This TypedDict represents a message that can be sent to remove a UI component from the current state. | https://reference.langchain.com/python/langgraph/graph/ui/RemoveUIMessage |
| ClassStateGraphA graph whose nodes communicate by reading and writing to a shared state.
The signature of each node is State -> Partial | https://reference.langchain.com/python/langgraph/graph/state/StateGraph |
| ClassCompiledStateGraph | https://reference.langchain.com/python/langgraph/graph/state/CompiledStateGraph |
| ClassBranchSpec | https://reference.langchain.com/python/langgraph/graph/_branch/BranchSpec |
| ClassNodeBuilder | https://reference.langchain.com/python/langgraph/pregel/main/NodeBuilder |
| ClassPregelPregel manages the runtime behavior for LangGraph applications. Overview Pregel combines actors and channels into a single application. **Acto | https://reference.langchain.com/python/langgraph/pregel/main/Pregel |
| ClassPregelProtocol | https://reference.langchain.com/python/langgraph/pregel/protocol/PregelProtocol |
| ClassStreamProtocol | https://reference.langchain.com/python/langgraph/pregel/protocol/StreamProtocol |
| ClassStreamToolCallHandlerCallback handler that emits tool-call lifecycle events on the stream. Fires on LangChain's on_tool_* callbacks and pushes to the tools stream mode. Emits tool-started / tool-output-delta / `t | https://reference.langchain.com/python/langgraph/pregel/_tools/StreamToolCallHandler |
| ClassEdge | https://reference.langchain.com/python/langgraph/pregel/_draw/Edge |
| ClassTriggerEdge | https://reference.langchain.com/python/langgraph/pregel/_draw/TriggerEdge |
| ClassWritesProtocolProtocol for objects containing writes to be applied to checkpoint. Implemented by PregelTaskWrites and PregelExecutableTask. | https://reference.langchain.com/python/langgraph/pregel/_algo/WritesProtocol |
| ClassPregelTaskWritesSimplest implementation of WritesProtocol, for usage with writes that don't originate from a runnable task, eg. graph input, update_state, etc. | https://reference.langchain.com/python/langgraph/pregel/_algo/PregelTaskWrites |
| ClassCall | https://reference.langchain.com/python/langgraph/pregel/_algo/Call |
| ClassLazyAtomicCounter | https://reference.langchain.com/python/langgraph/pregel/_algo/LazyAtomicCounter |
| ClassPregelLoop | https://reference.langchain.com/python/langgraph/pregel/_loop/PregelLoop |
| ClassSyncPregelLoop | https://reference.langchain.com/python/langgraph/pregel/_loop/SyncPregelLoop |
| ClassAsyncPregelLoop | https://reference.langchain.com/python/langgraph/pregel/_loop/AsyncPregelLoop |
| ClassChannelWriteEntry | https://reference.langchain.com/python/langgraph/pregel/_write/ChannelWriteEntry |
| ClassChannelWriteTupleEntry | https://reference.langchain.com/python/langgraph/pregel/_write/ChannelWriteTupleEntry |
| ClassChannelWriteImplements the logic for sending writes to CONFIG_KEY_SEND. Can be used as a runnable or as a static method to call imperatively. | https://reference.langchain.com/python/langgraph/pregel/_write/ChannelWrite |
| ClassChannelReadImplements the logic for reading state from CONFIG_KEY_READ. Usable both as a runnable as well as a static method to call imperatively. | https://reference.langchain.com/python/langgraph/pregel/_read/ChannelRead |
| ClassPregelNodeA node in a Pregel graph. This won't be invoked as a runnable by the graph itself, but instead acts as a container for the components necessary to make a PregelExecutableTask for a node. | https://reference.langchain.com/python/langgraph/pregel/_read/PregelNode |
| ClassSyncAsyncFuture | https://reference.langchain.com/python/langgraph/pregel/_call/SyncAsyncFuture |
| ClassFuturesDict | https://reference.langchain.com/python/langgraph/pregel/_runner/FuturesDict |
| ClassPregelRunnerResponsible for executing a set of Pregel tasks concurrently, committing their writes, yielding control to caller when there is output to emit, and interrupting other tasks if appropriate. | https://reference.langchain.com/python/langgraph/pregel/_runner/PregelRunner |
| ClassTaskStatusThe status of one task, read from the writes recorded for its superstep. | https://reference.langchain.com/python/langgraph/pregel/_task_status/TaskStatus |
| ClassSubmit | https://reference.langchain.com/python/langgraph/pregel/_executor/Submit |
| ClassBackgroundExecutorA context manager that runs sync tasks in the background. Uses a thread pool executor to delegate tasks to separate threads. On exit, cancels any (not yet started) tasks with `cancel_on_exit=Tru | https://reference.langchain.com/python/langgraph/pregel/_executor/BackgroundExecutor |
| ClassAsyncBackgroundExecutorA context manager that runs async tasks in the background. Uses the current event loop to delegate tasks to asyncio tasks. On exit, cancels any tasks with __cancel_on_exit__=True waits for all t | https://reference.langchain.com/python/langgraph/pregel/_executor/AsyncBackgroundExecutor |
| ClassRemoteExceptionException raised when an error occurs in the remote graph. | https://reference.langchain.com/python/langgraph/pregel/remote/RemoteException |
| ClassRemoteGraphThe RemoteGraph class is a client implementation for calling remote APIs that implement the LangGraph Server API specification. For example, the RemoteGraph class can be used to call APIs from de | https://reference.langchain.com/python/langgraph/pregel/remote/RemoteGraph |
| ClassStreamMessagesHandlerA callback handler that implements stream_mode=messages. Collects messages from: (1) chat model stream events; and (2) node outputs. | https://reference.langchain.com/python/langgraph/pregel/_messages/StreamMessagesHandler |
| ClassStreamMessagesHandlerV2v2 variant of StreamMessagesHandler. Declaring _V2StreamingCallbackHandler as a base flips BaseChatModel.invoke to route through _stream_chat_model_events (firing on_stream_event) instead o | https://reference.langchain.com/python/langgraph/pregel/_messages/StreamMessagesHandlerV2 |
| ClassGraphRunStreamSync run stream with caller-driven pumping. The caller's iteration on any projection (values, messages, raw events, or output) drives the graph forward. No background thread is used — the calle | https://reference.langchain.com/python/langgraph/stream/run_stream/GraphRunStream |
| ClassAsyncGraphRunStreamAsync run stream with caller-driven pumping. Async iteration on any projection drives the graph forward — there is no background task. Concurrent consumers share a single-flight pump via an `asyncio. | https://reference.langchain.com/python/langgraph/stream/run_stream/AsyncGraphRunStream |
| ClassSubgraphRunStreamSync handle for a discovered subgraph (extends GraphRunStream). | https://reference.langchain.com/python/langgraph/stream/run_stream/SubgraphRunStream |
| ClassAsyncSubgraphRunStreamAsync handle for a discovered subgraph (extends AsyncGraphRunStream). | https://reference.langchain.com/python/langgraph/stream/run_stream/AsyncSubgraphRunStream |
| ClassStreamChannelSingle-consumer drainable queue for streaming events, with optional protocol auto-forwarding. When constructed with a name, the StreamMux auto-wires every push() to also inject a ProtocolEvent | https://reference.langchain.com/python/langgraph/stream/stream_channel/StreamChannel |
| ClassStreamMuxCentral event dispatcher for the streaming infrastructure. Owns the main event log and routes events through a transformer pipeline. StreamChannels with a name discovered in transformer projections a | https://reference.langchain.com/python/langgraph/stream/_mux/StreamMux |
| ClassProtocolEventA protocol event emitted by the streaming infrastructure. Wraps a raw stream part (values, messages, custom, etc.) in a uniform envelope with a monotonic sequence number assigned by the root StreamMu | https://reference.langchain.com/python/langgraph/stream/_types/ProtocolEvent |
| ClassStreamTransformerExtension point for custom stream projections. Transformers observe protocol events flowing through the StreamMux and build typed derived projections (StreamChannels, promises, etc.). Set `_native = | https://reference.langchain.com/python/langgraph/stream/_types/StreamTransformer |
| ClassValuesTransformerCapture values events as a drainable stream of state snapshots. Provides the run.values projection. run.output, run.interrupted and run.interrupts are tracked directly by the run stream and d | https://reference.langchain.com/python/langgraph/stream/transformers/ValuesTransformer |
| ClassCustomTransformerCapture custom events as a drainable stream of arbitrary payloads. Nodes emit custom data via get_stream_writer(). This transformer surfaces those events on run.custom as a StreamChannel[Any], | https://reference.langchain.com/python/langgraph/stream/transformers/CustomTransformer |
| ClassUpdatesTransformerCapture updates events as a drainable stream of node outputs. Surfaces stream_mode="updates" data on run.updates as a StreamChannel[dict[str, Any]]. Each item is a dict mapping a node (or task) | https://reference.langchain.com/python/langgraph/stream/transformers/UpdatesTransformer |
| ClassMessagesTransformerCapture messages events as ChatModelStream objects. The messages projection yields one ChatModelStream (or AsyncChatModelStream) per LLM call. Consumers iterate run.messages to get stream handl | https://reference.langchain.com/python/langgraph/stream/transformers/MessagesTransformer |
| ClassLifecyclePayloadPayload of a lifecycle event surfaced on the lifecycle channel. Auto-forwarded as lifecycle protocol events (no custom: prefix because LifecycleTransformer is a native transformer) so remote | https://reference.langchain.com/python/langgraph/stream/transformers/LifecyclePayload |
| ClassLifecycleTransformerSurface subgraph lifecycle as lifecycle protocol events. Pushes LifecyclePayload to a StreamChannel named lifecycle. The channel is auto-forwarded by the mux so payloads land in the main even | https://reference.langchain.com/python/langgraph/stream/transformers/LifecycleTransformer |
| ClassSubgraphTransformerDiscover subgraph invocations as in-process navigation handles. Per discovered direct-child subgraph, builds a SubgraphRunStream (or AsyncSubgraphRunStream) wrapping a child mini-mux scoped to th | https://reference.langchain.com/python/langgraph/stream/transformers/SubgraphTransformer |
| ClassCheckpointsTransformerCapture checkpoint events as a drainable stream. Surfaces stream_mode="checkpoints" data on run.checkpoints as a StreamChannel[dict[str, Any]]. Each item is in the same format as returned by `g | https://reference.langchain.com/python/langgraph/stream/transformers/CheckpointsTransformer |
| ClassDebugTransformerCapture debug events as a drainable stream. Surfaces stream_mode="debug" data on run.debug as a StreamChannel[dict[str, Any]]. Each item is a debug event with step-level detail (checkpoint snap | https://reference.langchain.com/python/langgraph/stream/transformers/DebugTransformer |
| ClassTasksTransformerCapture raw task events as a drainable stream. Surfaces stream_mode="tasks" data on run.tasks as a StreamChannel[dict[str, Any]]. Each item is a task payload (start or result). `LifecycleTrans | https://reference.langchain.com/python/langgraph/stream/transformers/TasksTransformer |
| ClassManagedValue | https://reference.langchain.com/python/langgraph/managed/base/ManagedValue |
| ClassIsLastStepManager | https://reference.langchain.com/python/langgraph/managed/is_last_step/IsLastStepManager |
| ClassRemainingStepsManager | https://reference.langchain.com/python/langgraph/managed/is_last_step/RemainingStepsManager |
| ClassentrypointDefine a LangGraph workflow using the entrypoint decorator. Function signature The decorated function must accept a single parameter, which serves as the input to the function. This input | https://reference.langchain.com/python/langgraph/func/entrypoint |
| ClassfinalA primitive that can be returned from an entrypoint. This primitive allows to save a value to the checkpointer distinct from the return value from the entrypoint. | https://reference.langchain.com/python/langgraph/func/entrypoint/final |
| ClassNodeInterruptdeprecatedRaised by a node to interrupt execution. | https://reference.langchain.com/python/langgraph/errors/NodeInterrupt |
| ClassMessageGraphdeprecatedA StateGraph where every node receives a list of messages as input and returns one or more messages as output. MessageGraph is a subclass of StateGraph whose entire state is a single, append-only* li | https://reference.langchain.com/python/langgraph/graph/message/MessageGraph |
| Functionget_config | https://reference.langchain.com/python/langgraph/config/get_config |
| Functionget_storeAccess LangGraph store from inside a graph node or entrypoint task at runtime. Can be called from inside any StateGraph node or functional API [task][langgraph.func. | https://reference.langchain.com/python/langgraph/config/get_store |
| Functionget_stream_writerAccess LangGraph StreamWriter from inside a graph node or entrypoint task at runtime. Can be called from inside any StateGraph node o | https://reference.langchain.com/python/langgraph/config/get_stream_writer |
| Functionget_sync_graph_callback_manager_for_configBuild a sync graph lifecycle callback manager from a runnable config. This helper filters config["callbacks"] down to handlers that inherit from GraphCallbackHandler and binds the provided `run_i | https://reference.langchain.com/python/langgraph/callbacks/get_sync_graph_callback_manager_for_config |
| Functionget_async_graph_callback_manager_for_configBuild an async graph lifecycle callback manager from a runnable config. This helper filters config["callbacks"] down to handlers that inherit from GraphCallbackHandler and binds the provided `run | https://reference.langchain.com/python/langgraph/callbacks/get_async_graph_callback_manager_for_config |
| Functionensure_valid_checkpointer | https://reference.langchain.com/python/langgraph/types/ensure_valid_checkpointer |
| Functionomit_payloadTracePolicy helper that records an empty payload, dropping the value entirely. Use as process_inputs and/or process_outputs on a TracePolicy to keep a node's span and its timing while omittin | https://reference.langchain.com/python/langgraph/types/omit_payload |
| FunctioninterruptInterrupt the graph with a resumable exception from within a node. The interrupt function enables human-in-the-loop workflows by pausing graph execution and surfacing a value to the client. This va | https://reference.langchain.com/python/langgraph/types/interrupt |
| Functionget_runtimeGet the runtime for the current graph run. | https://reference.langchain.com/python/langgraph/runtime/get_runtime |
| Functioncreate_error_message | https://reference.langchain.com/python/langgraph/errors/create_error_message |
| Functionis_invalid_resumeWhether error was raised because a resume value didn't match response_schema. interrupt() raises a pydantic.ValidationError in that case. ToolNode uses this to tell it apart from invalid to | https://reference.langchain.com/python/langgraph/errors/is_invalid_resume |
| Functionrecast_checkpoint_nsRemove task IDs from checkpoint namespace. | https://reference.langchain.com/python/langgraph/_internal/_config/recast_checkpoint_ns |
| Functionpatch_configurable | https://reference.langchain.com/python/langgraph/_internal/_config/patch_configurable |
| Functionpatch_checkpoint_map | https://reference.langchain.com/python/langgraph/_internal/_config/patch_checkpoint_map |
| Functionmerge_configsMerge multiple configs into one. | https://reference.langchain.com/python/langgraph/_internal/_config/merge_configs |
| Functionpatch_configPatch a config with new values. | https://reference.langchain.com/python/langgraph/_internal/_config/patch_config |
| Functionget_callback_manager_for_configGet a callback manager for a config. | https://reference.langchain.com/python/langgraph/_internal/_config/get_callback_manager_for_config |
| Functionget_async_callback_manager_for_configGet an async callback manager for a config. | https://reference.langchain.com/python/langgraph/_internal/_config/get_async_callback_manager_for_config |
| Functionensure_configReturn a config with all keys, merging any provided configs. | https://reference.langchain.com/python/langgraph/_internal/_config/ensure_config |
| Functionfilter_to_user_tagsDrop langgraph's internal seq:step:* bookkeeping tags. seq:step:N tags are added internally to mark sequence steps; everything else (user-supplied tags and any other framework tags) is kept. Retu | https://reference.langchain.com/python/langgraph/_internal/_config/filter_to_user_tags |
| Functiondefault_retry_on | https://reference.langchain.com/python/langgraph/_internal/_retry/default_retry_on |
| Functionchain_future | https://reference.langchain.com/python/langgraph/_internal/_future/chain_future |
| Functionrun_coroutine_threadsafeSubmit a coroutine object to a given event loop. Return an asyncio.Future to access the result. | https://reference.langchain.com/python/langgraph/_internal/_future/run_coroutine_threadsafe |
| Functionget_field_defaultDetermine the default value for a field in a state schema. | https://reference.langchain.com/python/langgraph/_internal/_fields/get_field_default |
| Functionget_enhanced_type_hintsAttempt to extract default values and descriptions from provided type, used for config schema. | https://reference.langchain.com/python/langgraph/_internal/_fields/get_enhanced_type_hints |
| Functionget_update_as_tuplesGet Pydantic state update as a list of (key, value) tuples. | https://reference.langchain.com/python/langgraph/_internal/_fields/get_update_as_tuples |
| Functionget_cached_annotated_keysReturn cached annotated keys for a Python class. | https://reference.langchain.com/python/langgraph/_internal/_fields/get_cached_annotated_keys |
| Functioncoerce_timeout_policyNormalize a timeout value to positive-second policy fields. | https://reference.langchain.com/python/langgraph/_internal/_timeout/coerce_timeout_policy |
| Functionsync_timeout_unsupportedBuild the canonical error for using timeout with a sync target. | https://reference.langchain.com/python/langgraph/_internal/_timeout/sync_timeout_unsupported |
| Functiondefault_cache_keyDefault cache key function that uses the arguments and keyword arguments to generate a hashable key. | https://reference.langchain.com/python/langgraph/_internal/_cache/default_cache_key |
| Functionget_fieldsGet the field names of a Pydantic model. | https://reference.langchain.com/python/langgraph/_internal/_pydantic/get_fields |
| Functioncreate_modelCreate a pydantic model with the given field definitions. | https://reference.langchain.com/python/langgraph/_internal/_pydantic/create_model |
| Functionis_supported_by_pydanticCheck if a given "complex" type is supported by pydantic. This will return False for primitive types like int, str, etc. The check is meant for container types like dataclasses, TypedDicts, etc. | https://reference.langchain.com/python/langgraph/_internal/_pydantic/is_supported_by_pydantic |
| Functionapply_checkpointer_allowlist | https://reference.langchain.com/python/langgraph/_internal/_serde/apply_checkpointer_allowlist |
| Functioncurated_core_allowlist | https://reference.langchain.com/python/langgraph/_internal/_serde/curated_core_allowlist |
| Functionbuild_serde_allowlist | https://reference.langchain.com/python/langgraph/_internal/_serde/build_serde_allowlist |
| Functioncollect_allowlist_from_schemas | https://reference.langchain.com/python/langgraph/_internal/_serde/collect_allowlist_from_schemas |
| Functionset_config_contextSet the child Runnable config + tracing context. | https://reference.langchain.com/python/langgraph/_internal/_runnable/set_config_context |
| Functioncreate_task_in_config_contextCreate an asyncio.Task that inherits config as the child runnable context. asyncio.create_task snapshots the current contextvars onto the new task, so calling create_task while the config conte | https://reference.langchain.com/python/langgraph/_internal/_runnable/create_task_in_config_context |
| Functionis_async_callableCheck if a function is async. | https://reference.langchain.com/python/langgraph/_internal/_runnable/is_async_callable |
| Functionis_async_generatorCheck if a function is an async generator. | https://reference.langchain.com/python/langgraph/_internal/_runnable/is_async_generator |
| Functioncoerce_to_runnableCoerce a runnable-like object into a Runnable. | https://reference.langchain.com/python/langgraph/_internal/_runnable/coerce_to_runnable |
| Functionadd_messagesMerges two lists of messages, updating existing messages by ID. By default, this ensures the state is "append-only", unless the new message has the same ID as an existing message. | https://reference.langchain.com/python/langgraph/graph/message/add_messages |
| Functionpush_messageWrite a message manually to the messages / messages-tuple stream mode. Will automatically write to the channel specified in the state_key unless state_key is None. | https://reference.langchain.com/python/langgraph/graph/message/push_message |
| Functionpush_ui_messagePush a new UI message to update the UI state. This function creates and sends a UI message that will be rendered in the UI. It also updates the graph state with the new UI message. | https://reference.langchain.com/python/langgraph/graph/ui/push_ui_message |
| Functiondelete_ui_messageDelete a UI message by ID from the UI state. This function creates and sends a message to remove a UI component from the current state. It also updates the graph state to remove the UI message. | https://reference.langchain.com/python/langgraph/graph/ui/delete_ui_message |
| Functionui_message_reducerMerge two lists of UI messages, supporting removing UI messages. This function combines two lists of UI messages, handling both regular UI messages and remove-ui messages. When a remove-ui messag | https://reference.langchain.com/python/langgraph/graph/ui/ui_message_reducer |
| Functionget_new_channel_versionsGet subset of current_versions that are newer than previous_versions. | https://reference.langchain.com/python/langgraph/pregel/_utils/get_new_channel_versions |
| Functionfind_subgraph_pregel | https://reference.langchain.com/python/langgraph/pregel/_utils/find_subgraph_pregel |
| Functionvalidate_timeout_supported | https://reference.langchain.com/python/langgraph/pregel/_utils/validate_timeout_supported |
| Functionget_function_nonlocalsGet the values a function reaches from outside its own scope. | https://reference.langchain.com/python/langgraph/pregel/_utils/get_function_nonlocals |
| Functionis_xxh3_128_hexdigestCheck if the given string matches the format of xxh3_128_hexdigest. | https://reference.langchain.com/python/langgraph/pregel/_utils/is_xxh3_128_hexdigest |
| Functionread_channel | https://reference.langchain.com/python/langgraph/pregel/_io/read_channel |
| Functionread_channels | https://reference.langchain.com/python/langgraph/pregel/_io/read_channels |
| Functionmap_commandMap input chunk to a sequence of pending writes in the form (channel, value). | https://reference.langchain.com/python/langgraph/pregel/_io/map_command |
| Functionmap_inputMap input chunk to a sequence of pending writes in the form (channel, value). | https://reference.langchain.com/python/langgraph/pregel/_io/map_input |
| Functionmap_output_valuesMap pending writes (a sequence of tuples (channel, value)) to output chunk. | https://reference.langchain.com/python/langgraph/pregel/_io/map_output_values |
| Functionmap_output_updatesMap pending writes (a sequence of tuples (channel, value)) to output chunk. | https://reference.langchain.com/python/langgraph/pregel/_io/map_output_updates |
| Functionrun_with_retryRun a task with retries. | https://reference.langchain.com/python/langgraph/pregel/_retry/run_with_retry |
| Functionarun_with_retryRun a task asynchronously with retries. | https://reference.langchain.com/python/langgraph/pregel/_retry/arun_with_retry |
| Functionempty_checkpoint | https://reference.langchain.com/python/langgraph/pregel/_checkpoint/empty_checkpoint |
| Functionput_writes_accepts_task_pathWhether a saver's put_writes or aput_writes takes task_path. Savers written before the parameter existed don't, so it is passed only when this is true. | https://reference.langchain.com/python/langgraph/pregel/_checkpoint/put_writes_accepts_task_path |
| Functionexit_delta_task_idSynthetic task id for exit-mode DeltaChannel writes. Embeds the superstep in the first UUID group so ORDER BY task_id, idx preserves chronological order while remaining a valid RFC UUID (required b | https://reference.langchain.com/python/langgraph/pregel/_checkpoint/exit_delta_task_id |
| Functionexit_delta_late_task_idSynthetic task id for exit-mode writes of a superstep after the anchor's own. Sorts after every real task id, in step order, so replay keeps them after the anchor's own superstep whether a saver orde | https://reference.langchain.com/python/langgraph/pregel/_checkpoint/exit_delta_late_task_id |
| Functiondelta_channels_to_snapshotReturn the set of DeltaChannel names that should snapshot now. A channel snapshots when EITHER its accumulated update count reaches snapshot_frequency OR the total supersteps since its last snapsho | https://reference.langchain.com/python/langgraph/pregel/_checkpoint/delta_channels_to_snapshot |
| Functionget_updated_channels_from_tasksChannel names written by an update_state superstep (excluding PUSH). | https://reference.langchain.com/python/langgraph/pregel/_checkpoint/get_updated_channels_from_tasks |
| Functionget_delta_channels_from_all_channelsDeltaChannels to snapshot on the first update_state of a fresh thread: the ones it wrote, as the rest have no version and nothing to store. | https://reference.langchain.com/python/langgraph/pregel/_checkpoint/get_delta_channels_from_all_channels |
| Functiondelta_channels_with_pending_writesDeltaChannels a branch starting from this checkpoint must snapshot. A checkpoint's pending writes belong to the child that consumed them, and nothing records which child that was. A new branch snapsh | https://reference.langchain.com/python/langgraph/pregel/_checkpoint/delta_channels_with_pending_writes |
| Functiondelta_channels_overwrittenReturn the names of the DeltaChannels that writes set with an Overwrite. update_state saves a full snapshot of these channels in the checkpoint it creates, like the loop does when a node return | https://reference.langchain.com/python/langgraph/pregel/_checkpoint/delta_channels_overwritten |
| Functioncheckpoint_supersededWhether the thread has moved past saved, the checkpoint config addressed. A checkpoint with a child is never the latest put, so this misses none. A leaf of an abandoned branch counts as well; tel | https://reference.langchain.com/python/langgraph/pregel/_checkpoint/checkpoint_superseded |
| Functionacheckpoint_supersededAsync checkpoint_superseded. | https://reference.langchain.com/python/langgraph/pregel/_checkpoint/acheckpoint_superseded |
| Functioncreate_metadata_for_update_state_apiAdvance counters_since_delta_snapshot for update_state on a non-fresh thread. Mirrors the per-superstep counter bump in _loop._put_checkpoint. | https://reference.langchain.com/python/langgraph/pregel/_checkpoint/create_metadata_for_update_state_api |
| Functioncreate_checkpoint_plan_for_update_state_apiReturn (channels_to_snapshot, metadata) for an update_state head. | https://reference.langchain.com/python/langgraph/pregel/_checkpoint/create_checkpoint_plan_for_update_state_api |
| Functioncreate_checkpointBuild a new Checkpoint from the previous one and live channel state. For each name in channels_to_snapshot, a _DeltaSnapshot(value) blob is written into channel_values[k]. Other delta channels | https://reference.langchain.com/python/langgraph/pregel/_checkpoint/create_checkpoint |
| Functionversions_seen_without_bumpsversions_seen as the nodes read it: an entry a bump advanced goes back to the version the node really read, or away if it never read one. | https://reference.langchain.com/python/langgraph/pregel/_checkpoint/versions_seen_without_bumps |
| Functionchannels_from_checkpointHydrate channels from a checkpoint. For most channels, spec.from_checkpoint(checkpoint["channel_values"][k]) is sufficient. DeltaChannel is the exception: when the channel is absent from `channel | https://reference.langchain.com/python/langgraph/pregel/_checkpoint/channels_from_checkpoint |
| Functionachannels_from_checkpointAsync version of channels_from_checkpoint. See docstring there. | https://reference.langchain.com/python/langgraph/pregel/_checkpoint/achannels_from_checkpoint |
| Functioncopy_checkpoint | https://reference.langchain.com/python/langgraph/pregel/_checkpoint/copy_checkpoint |
| Functiondraw_graphGet the graph for this Pregel instance. | https://reference.langchain.com/python/langgraph/pregel/_draw/draw_graph |
| Functionadd_edgeAdd an edge to the graph. | https://reference.langchain.com/python/langgraph/pregel/_draw/add_edge |
| Functionshould_interruptCheck if the graph should be interrupted based on current state. | https://reference.langchain.com/python/langgraph/pregel/_algo/should_interrupt |
| Functionlocal_readFunction injected under CONFIG_KEY_READ in task config, to read current state. Used by conditional edges to read a copy of the state with reflecting the writes from that node only. | https://reference.langchain.com/python/langgraph/pregel/_algo/local_read |
| FunctionincrementDefault channel versioning function, increments the current int version. | https://reference.langchain.com/python/langgraph/pregel/_algo/increment |
| Functionapply_writesApply writes from a set of tasks (usually the tasks from a Pregel step) to the checkpoint and channels, and return managed values writes to be applied externally. | https://reference.langchain.com/python/langgraph/pregel/_algo/apply_writes |
| Functionprepare_next_tasksPrepare the set of tasks that will make up the next Pregel step. | https://reference.langchain.com/python/langgraph/pregel/_algo/prepare_next_tasks |
| Functionprepare_single_taskPrepares a single task for the next Pregel step, given a task path, which uniquely identifies a PUSH or PULL task within the graph. | https://reference.langchain.com/python/langgraph/pregel/_algo/prepare_single_task |
| Functionprepare_push_task_functionalPrepare a push task with an attached caller. Used for the functional API. | https://reference.langchain.com/python/langgraph/pregel/_algo/prepare_push_task_functional |
| Functionprepare_push_task_send | https://reference.langchain.com/python/langgraph/pregel/_algo/prepare_push_task_send |
| Functionprepare_node_error_handler_taskPrepare an immediate node-level error handler task for a failed task. | https://reference.langchain.com/python/langgraph/pregel/_algo/prepare_node_error_handler_task |
| Functioncheckpoint_null_versionGet the null version for the checkpoint, if available. | https://reference.langchain.com/python/langgraph/pregel/_algo/checkpoint_null_version |
| Functiontask_path_strGenerate a string representation of the task path. | https://reference.langchain.com/python/langgraph/pregel/_algo/task_path_str |
| Functionsanitize_untracked_values_in_sendPop any values belonging to UntrackedValue channels in Send.arg for safe checkpointing. Send is often called with state to be passed to the dest node, which may contain UntrackedValues at the top lev | https://reference.langchain.com/python/langgraph/pregel/_algo/sanitize_untracked_values_in_send |
| FunctionDuplexStream | https://reference.langchain.com/python/langgraph/pregel/_loop/DuplexStream |
| FunctionidentifierReturn the module and name of an object. | https://reference.langchain.com/python/langgraph/pregel/_call/identifier |
| Functionget_runnable_for_entrypoint | https://reference.langchain.com/python/langgraph/pregel/_call/get_runnable_for_entrypoint |
| Functionget_runnable_for_task | https://reference.langchain.com/python/langgraph/pregel/_call/get_runnable_for_task |
| Functioncall | https://reference.langchain.com/python/langgraph/pregel/_call/call |
| Functionread_task_statusesReturn the status of every task that has recorded writes, keyed by task id. Writes from NULL_TASK_ID are input to the superstep, not task activity, so they are not included. | https://reference.langchain.com/python/langgraph/pregel/_task_status/read_task_statuses |
| Functionvalidate_graph | https://reference.langchain.com/python/langgraph/pregel/_validate/validate_graph |
| Functionvalidate_keys | https://reference.langchain.com/python/langgraph/pregel/_validate/validate_keys |
| FunctiongatedA coroutine that waits for a semaphore before running another coroutine. | https://reference.langchain.com/python/langgraph/pregel/_executor/gated |
| Functionnext_tickA function that yields control to other threads before running another function. | https://reference.langchain.com/python/langgraph/pregel/_executor/next_tick |
| Functionmap_debug_tasksProduce "task" events for stream_mode=debug. | https://reference.langchain.com/python/langgraph/pregel/debug/map_debug_tasks |
| Functionis_multiple_channel_writeReturn True if the payload already wraps multiple writes from the same channel. | https://reference.langchain.com/python/langgraph/pregel/debug/is_multiple_channel_write |
| Functionmap_task_result_writesFolds task writes into a result dict and aggregates multiple writes to the same channel. If the channel contains a single write, we record the write in the result dict as {channel: write} If the ch | https://reference.langchain.com/python/langgraph/pregel/debug/map_task_result_writes |
| Functionmap_debug_task_resultsProduce "task_result" events for stream_mode=debug. | https://reference.langchain.com/python/langgraph/pregel/debug/map_debug_task_results |
| Functionrm_pregel_keysRemove pregel-specific keys from the config. | https://reference.langchain.com/python/langgraph/pregel/debug/rm_pregel_keys |
| Functionmap_debug_checkpointProduce "checkpoint" events for stream_mode=debug. | https://reference.langchain.com/python/langgraph/pregel/debug/map_debug_checkpoint |
| Functiontasks_w_writesApply writes / subgraph states to tasks to be returned in a StateSnapshot. With live=True, tasks report only the interrupts still waiting for an answer, as of the most recent writes. Otherwise task | https://reference.langchain.com/python/langgraph/pregel/debug/tasks_w_writes |
| Functionget_colored_textGet colored text. | https://reference.langchain.com/python/langgraph/pregel/debug/get_colored_text |
| Functionget_bolded_textGet bolded text. | https://reference.langchain.com/python/langgraph/pregel/debug/get_bolded_text |
| Functiongraph_namespaceNamespace of the graph a task runs in, from the task's run metadata. Drops the task's own segment, plus one per enclosing @task call: a call runs in its caller's graph but nests its segment under t | https://reference.langchain.com/python/langgraph/pregel/_messages/graph_namespace |
| Functionensure_message_idsGive the messages written to DeltaChannels stable ids. A DeltaChannel replays its saved writes on every read, and its reducer may not assign missing ids (_messages_delta_reducer doesn't), so a me | https://reference.langchain.com/python/langgraph/pregel/_messages/ensure_message_ids |
| Functionconvert_to_protocol_eventConvert a v2 StreamPart to a ProtocolEvent. | https://reference.langchain.com/python/langgraph/stream/_convert/convert_to_protocol_event |
| Functiontransformer_requires_asyncReturn True if the transformer needs a running event loop. A transformer requires async if it explicitly opts in (requires_async = True) or overrides any of the async-lane methods (aprocess, `afi | https://reference.langchain.com/python/langgraph/stream/_types/transformer_requires_async |
| Functionis_managed_value | https://reference.langchain.com/python/langgraph/managed/base/is_managed_value |
| FunctiontaskDefine a LangGraph task using the task decorator. Requires python 3.11 or higher for async functionsThe task decorator supports both sync and async functions. To use async | https://reference.langchain.com/python/langgraph/func/task |
| Modulelanggraph | https://reference.langchain.com/python/langgraph/langgraph |
| Moduleconfig | https://reference.langchain.com/python/langgraph/config |
| Moduleconstants | https://reference.langchain.com/python/langgraph/constants |
| ModuleversionExports package version. | https://reference.langchain.com/python/langgraph/version |
| ModulecallbacksGraph lifecycle callback interfaces and event payloads. This module defines the public callback surface for observing LangGraph-specific lifecycle transitions such as interrupt and resume. | https://reference.langchain.com/python/langgraph/callbacks |
| Moduletypes | https://reference.langchain.com/python/langgraph/types |
| ModulewarningsLangGraph specific warnings. | https://reference.langchain.com/python/langgraph/warnings |
| Moduleruntime | https://reference.langchain.com/python/langgraph/runtime |
| Moduletyping | https://reference.langchain.com/python/langgraph/typing |
| Moduleerrors | https://reference.langchain.com/python/langgraph/errors |
| Modulechannels | https://reference.langchain.com/python/langgraph/channels |
| Modulenamed_barrier_value | https://reference.langchain.com/python/langgraph/channels/named_barrier_value |
| Modulebase | https://reference.langchain.com/python/langgraph/channels/base |
| Moduleuntracked_value | https://reference.langchain.com/python/langgraph/channels/untracked_value |
| Moduleephemeral_value | https://reference.langchain.com/python/langgraph/channels/ephemeral_value |
| Modulelast_value | https://reference.langchain.com/python/langgraph/channels/last_value |
| Modulebinop | https://reference.langchain.com/python/langgraph/channels/binop |
| Moduletopic | https://reference.langchain.com/python/langgraph/channels/topic |
| Moduledelta | https://reference.langchain.com/python/langgraph/channels/delta |
| Moduleany_value | https://reference.langchain.com/python/langgraph/channels/any_value |
| Modulegraph | https://reference.langchain.com/python/langgraph/graph |
| Modulemessage | https://reference.langchain.com/python/langgraph/graph/message |
| Moduleui | https://reference.langchain.com/python/langgraph/graph/ui |
| Modulestate | https://reference.langchain.com/python/langgraph/graph/state |
| Modulepregel | https://reference.langchain.com/python/langgraph/pregel |
| Modulemain | https://reference.langchain.com/python/langgraph/pregel/main |
| Moduleprotocol | https://reference.langchain.com/python/langgraph/pregel/protocol |
| ModuletypesRe-export types moved to langgraph.types | https://reference.langchain.com/python/langgraph/pregel/types |
| Moduledebug | https://reference.langchain.com/python/langgraph/pregel/debug |
| Moduleremote | https://reference.langchain.com/python/langgraph/pregel/remote |
| ModulestreamStreaming infrastructure for LangGraph. Compile a graph with transformers=[...] and call graph.stream_events(version="v3") / graph.astream_events(version="v3") to drive a transformer pipeline t | https://reference.langchain.com/python/langgraph/stream |
| Modulerun_stream | https://reference.langchain.com/python/langgraph/stream/run_stream |
| Modulestream_channel | https://reference.langchain.com/python/langgraph/stream/stream_channel |
| Moduletransformers | https://reference.langchain.com/python/langgraph/stream/transformers |
| ModuleutilsLegacy utilities module, to be removed in v1. | https://reference.langchain.com/python/langgraph/utils |
| ModuleconfigBackwards compat imports for config utilities, to be removed in v1. | https://reference.langchain.com/python/langgraph/utils/config |
| ModulerunnableBackwards compat imports for runnable utilities, to be removed in v1. | https://reference.langchain.com/python/langgraph/utils/runnable |
| Modulemanaged | https://reference.langchain.com/python/langgraph/managed |
| Modulebase | https://reference.langchain.com/python/langgraph/managed/base |
| Moduleis_last_step | https://reference.langchain.com/python/langgraph/managed/is_last_step |
| Modulefunc | https://reference.langchain.com/python/langgraph/func |
| TypeGraphLifecycleStatusAllowed lifecycle statuses reported in graph lifecycle callback events. | https://reference.langchain.com/python/langgraph/callbacks/GraphLifecycleStatus |
| TypeGraphLifecycleEventUnion of all public graph lifecycle callback event payloads. Use this alias when a callback or helper can receive either interrupt or resume lifecycle events. | https://reference.langchain.com/python/langgraph/callbacks/GraphLifecycleEvent |
| TypeGraphCallbacks | https://reference.langchain.com/python/langgraph/callbacks/GraphCallbacks |
| TypeCheckpointerType of the checkpointer to use for a subgraph. True enables persistent checkpointing for this subgraph. False disables checkpointing, even if the parent graph has a checkpointer. None in | https://reference.langchain.com/python/langgraph/types/Checkpointer |
| TypeAnyFuture | https://reference.langchain.com/python/langgraph/_internal/_future/AnyFuture |
| TypeStateLikeType alias for state-like types. It can either be a TypedDict, dataclass, or Pydantic BaseModel. Note: we cannot use either TypedDict or dataclass directly due to limitations in type checki | https://reference.langchain.com/python/langgraph/_internal/_typing/StateLike |
| TypeRunnableLike | https://reference.langchain.com/python/langgraph/_internal/_runnable/RunnableLike |
| TypeMessages | https://reference.langchain.com/python/langgraph/graph/message/Messages |
| TypeStateNode | https://reference.langchain.com/python/langgraph/graph/_node/StateNode |
| TypeAnyUIMessage | https://reference.langchain.com/python/langgraph/graph/ui/AnyUIMessage |
Viewport: width=device-width, initial-scale=1