MCPcopy Create free account

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

Functions1,515 in github.com/langchain-ai/langgraph

↓ 106 callersMethodinvoke
Run the graph with a single input and config. Args: input: The input data for the graph. It can be a dictionary or any other type
libs/langgraph/langgraph/pregel/__init__.py:1527
↓ 100 callersMethodadd_node
Adds a new node to the state graph. Will take the name of the function/runnable as the node name. Args: node (RunnableLik
libs/langgraph/langgraph/graph/state.py:207
↓ 99 callersMethodcompile
Compiles the state graph into a `CompiledGraph` object. The compiled graph implements the `Runnable` interface and can be invoked, st
libs/langgraph/langgraph/graph/state.py:400
↓ 89 callersMethodadd_edge
Adds a directed edge from the start node to the end node. If the graph transitions to the start_key node, it will always transition to the en
libs/langgraph/langgraph/graph/state.py:364
↓ 74 callersMethodset_entry_point
Specifies the first node to be called in the graph. Equivalent to calling `add_edge(START, key)`. Parameters: key (str):
libs/langgraph/langgraph/graph/graph.py:300
↓ 73 callersMethodget
(self)
libs/langgraph/langgraph/channels/topic.py:73
↓ 72 callersMethodainvoke
Asynchronously invoke the graph on a single input. Args: input: The input data for the computation. It can be a dictionary or any
libs/langgraph/langgraph/pregel/__init__.py:1579
↓ 59 callersMethodadd_conditional_edges
Add a conditional edge from the starting node to any number of destination nodes. Args: source (str): The starting node. This con
libs/langgraph/langgraph/graph/graph.py:233
↓ 50 callersMethodset_finish_point
Marks a node as a finish point of the graph. If the graph reaches this node, it will cease execution. Parameters: key (s
libs/langgraph/langgraph/graph/graph.py:339
↓ 41 callersMethodjoin
* Block until a run is done. * * @param threadId The ID of the thread. * @param runId The ID of the run. * @returns
libs/sdk-js/src/client.ts:906
↓ 41 callersMethodsubscribe_to
( cls, channels: str, *, key: Optional[str] = None, tags: Optional[lis
libs/langgraph/langgraph/pregel/__init__.py:111
↓ 40 callersMethodwrite_to
Writes to channels the result of the lambda, or None to skip writing.
libs/langgraph/langgraph/pregel/__init__.py:161
↓ 39 callersMethodastream
Stream graph steps for a single input. Args: input: The input to the graph. config: The configuration to use for the
libs/langgraph/langgraph/pregel/__init__.py:1321
↓ 39 callersMethodpost
Send a POST request.
libs/sdk-py/langgraph_sdk/client.py:212
↓ 39 callersMethodstream
Stream graph steps for a single input. Args: input: The input to the graph. config: The configuration to use for the
libs/langgraph/langgraph/pregel/__init__.py:1115
↓ 36 callersMethodfetch
( path: string, options?: RequestInit & { json?: unknown; params?: Record<string, unknown>
libs/sdk-js/src/client.ts:106
↓ 35 callersMethoddumps
(self, obj: Any)
libs/checkpoint/langgraph/checkpoint/serde/base.py:28
↓ 32 callersFunctionawith_checkpointer
( checkpointer_name: Optional[str], )
libs/langgraph/tests/conftest.py:205
↓ 32 callersMethodcompile
( self, checkpointer: Checkpointer = None, interrupt_before: Optional[Union[All, list[
libs/langgraph/langgraph/graph/graph.py:406
↓ 28 callersMethodadd_node
( self, node: RunnableLike, *, metadata: Optional[dict[str, Any]] = None,
libs/langgraph/langgraph/graph/graph.py:154
↓ 28 callersMethodget
Retrieve a single item. Args: namespace: Hierarchical path for the item. key: Unique identifier within the namespace.
libs/checkpoint/langgraph/store/base/__init__.py:206
↓ 26 callersMethodjoin
(self, channels: Sequence[str])
libs/langgraph/langgraph/pregel/read.py:207
↓ 25 callersMethodget_graph
Returns a drawable representation of the computation graph.
libs/langgraph/langgraph/graph/graph.py:517
↓ 22 callersMethodaget_state
Get the current state of the graph.
libs/langgraph/langgraph/pregel/__init__.py:626
↓ 22 callersMethodfrom_conn_string
Create a new BasePostgresStore instance from a connection string. Args: conn_string (str): The Postgres connection info string.
libs/checkpoint-postgres/langgraph/store/postgres/base.py:351
↓ 21 callersMethodadd_edge
(self, start_key: str, end_key: str)
libs/langgraph/langgraph/graph/graph.py:210
↓ 21 callersMethodcopy
(self, update: dict[str, Any])
libs/langgraph/langgraph/pregel/__init__.py:258
↓ 21 callersMethodget
Send a GET request.
libs/sdk-py/langgraph_sdk/client.py:198
↓ 20 callersFunctionpatch_configurable
( config: Optional[RunnableConfig], patch: dict[str, Any] )
libs/langgraph/langgraph/utils/config.py:27
↓ 19 callersMethodcursor
Get a cursor for the SQLite database. This method returns a cursor for the SQLite database. It is used internally by the SqliteSaver
libs/checkpoint-sqlite/langgraph/checkpoint/sqlite/__init__.py:155
↓ 19 callersMethodget_state
Get the current state of the graph.
libs/langgraph/langgraph/pregel/__init__.py:592
↓ 18 callersFunction_AnyIdHumanMessage
Create a human message with an any id field.
libs/langgraph/tests/messages.py:39
↓ 17 callersMethodget_tuple
(self, config: RunnableConfig)
libs/langgraph/tests/test_pregel.py:272
↓ 17 callersMethodloads
(self, data: bytes)
libs/checkpoint/langgraph/checkpoint/serde/base.py:31
↓ 16 callersFunctionclean_empty_lines
(input_str: str)
libs/cli/langgraph_cli/util.py:1
↓ 15 callersMethodupdate_state
Update the state of the graph with the given values, as if they came from node `as_node`. If `as_node` is not provided, it will be set to the
libs/langgraph/langgraph/pregel/__init__.py:762
↓ 14 callersMethodaget_tuple
(self, config: RunnableConfig)
libs/langgraph/tests/test_pregel_async.py:93
↓ 14 callersFunctionmerge_configs
Merge multiple configs into one. Args: *configs (Optional[RunnableConfig]): The configs to merge. Returns: RunnableConfig: T
libs/langgraph/langgraph/utils/config.py:56
↓ 14 callersFunctionvalidate_config
(config: Config)
libs/cli/langgraph_cli/config.py:20
↓ 13 callersMethodget
Remove and return an item from the queue. If optional args 'block' is true and 'timeout' is None (the default), block if necessary un
libs/langgraph/langgraph/utils/queue.py:94
↓ 13 callersMethodget_name
( self, suffix: Optional[str] = None, *, name: Optional[str] = None )
libs/langgraph/langgraph/pregel/read.py:68
↓ 13 callersMethodset_conditional_entry_point
Sets a conditional entry point in the graph. Args: path (Union[Callable, Runnable]): The callable that determines the next
libs/langgraph/langgraph/graph/graph.py:313
↓ 12 callersMethodaupdate_state
( self, config: RunnableConfig, values: dict[str, Any] | Any, as_node: Optiona
libs/langgraph/langgraph/pregel/__init__.py:913
↓ 12 callersFunctioncreate_react_agent
Creates a graph that works with a chat model that utilizes tool calling. Args: model: The `LangChain` chat model that supports tool calli
libs/langgraph/langgraph/prebuilt/chat_agent_executor.py:159
↓ 12 callersMethodget_input_schema
( self, config: Optional[RunnableConfig] = None )
libs/langgraph/langgraph/pregel/__init__.py:316
↓ 12 callersMethodlist
* List all runs for a thread. * * @param threadId The ID of the thread. * @param options Filtering and pagination options. * @returns List
libs/sdk-js/src/client.ts:843
↓ 11 callersFunctionadd_messages
Merges two lists of messages, updating existing messages by ID. By default, this ensures the state is "append-only", unless the new message h
libs/langgraph/langgraph/graph/message.py:18
↓ 11 callersMethodalist
Asynchronous version of list. This method is an asynchronous wrapper around list that runs the synchronous method in a separate threa
libs/checkpoint/langgraph/checkpoint/memory/__init__.py:387
↓ 11 callersMethodsend
( self, topic: str, *, key: Optional[bytes] = None, value: Optional[by
libs/scheduler-kafka/langgraph/scheduler/kafka/types.py:82
↓ 11 callersMethodupdate
(self, values: Sequence[Union[Value, list[Value]]])
libs/langgraph/langgraph/channels/topic.py:65
↓ 10 callersMethodcancel
* Cancel a run. * * @param threadId The ID of the thread. * @param runId The ID of the run. * @param wait Whether to block when canceling
libs/sdk-js/src/client.ts:886
↓ 10 callersMethoddelete
Send a DELETE request.
libs/sdk-py/langgraph_sdk/client.py:260
↓ 10 callersFunctionempty_checkpoint
()
libs/checkpoint/langgraph/checkpoint/base/__init__.py:102
↓ 10 callersFunctionensure_config
Ensure that a config is a dict with all keys present. Args: config (Optional[RunnableConfig], optional): The config to ensure.
libs/langgraph/langgraph/utils/config.py:249
↓ 10 callersMethodget
* Get a run by ID. * * @param threadId The ID of the thread. * @param runId The ID of the run. * @returns The run.
libs/sdk-js/src/client.ts:874
↓ 10 callersMethodget_output_schema
( self, config: Optional[RunnableConfig] = None )
libs/langgraph/langgraph/pregel/__init__.py:348
↓ 10 callersMethodget_state_history
Get the history of the state of the graph.
libs/langgraph/langgraph/pregel/__init__.py:660
↓ 10 callersMethodsubmit
( # type: ignore[valid-type] self, fn: Callable[P, T], *args: P.args, __name_
libs/langgraph/langgraph/pregel/executor.py:54
↓ 9 callersMethodaget
Asynchronously retrieve a single item. Args: namespace: Hierarchical path for the item. key: Unique identifier within
libs/checkpoint/langgraph/store/base/__init__.py:311
↓ 9 callersMethodaget_state_history
Get the history of the state of the graph.
libs/langgraph/langgraph/pregel/__init__.py:709
↓ 9 callersMethodloads_typed
(self, data: tuple[str, bytes])
libs/checkpoint/langgraph/checkpoint/serde/base.py:37
↓ 9 callersFunctionpatch_config
Patch a config with new values. Args: config (Optional[RunnableConfig]): The config to patch. callbacks (Optional[BaseCallbackMan
libs/langgraph/langgraph/utils/config.py:128
↓ 9 callersMethodrun
( self, writer: Callable[ [Sequence[Union[str, Send]], RunnableConfig], Optional[C
libs/langgraph/langgraph/graph/graph.py:57
↓ 8 callersFunction_AnyIdToolMessage
Create a tool message with an any id field.
libs/langgraph/tests/messages.py:46
↓ 8 callersFunctionconfig_to_docker
(config_path: pathlib.Path, config: Config, base_image: str)
libs/cli/langgraph_cli/config.py:305
↓ 8 callersFunctioncreate_checkpoint
Create a checkpoint for the given channels.
libs/checkpoint/langgraph/checkpoint/base/__init__.py:126
↓ 8 callersMethoddumps_typed
(self, obj: Any)
libs/checkpoint/langgraph/checkpoint/serde/base.py:34
↓ 8 callersFunctionget_checkpoint_id
Get checkpoint ID in a backwards-compatible manner (fallback on thread_ts).
libs/checkpoint/langgraph/checkpoint/base/__init__.py:438
↓ 8 callersMethodlist_namespaces
List and filter namespaces in the store. Used to explore the organization of data, find specific collections, or navigate the namespa
libs/checkpoint/langgraph/store/base/__init__.py:260
↓ 8 callersMethodon_chain_end
( self, response: Any, *, run_id: UUID, parent_run_id: Optional[UUID]
libs/langgraph/langgraph/pregel/messages.py:123
↓ 8 callersMethodon_chain_error
( self, error: BaseException, *, run_id: UUID, parent_run_id: Optional
libs/langgraph/langgraph/pregel/messages.py:159
↓ 8 callersMethodon_chain_start
( self, serialized: Dict[str, Any], inputs: Dict[str, Any], *, run_id:
libs/langgraph/langgraph/pregel/messages.py:106
↓ 8 callersMethodput
Store or update an item. Args: namespace: Hierarchical path for the item. key: Unique identifier within the namespace
libs/checkpoint/langgraph/store/base/__init__.py:240
↓ 7 callersFunction_AnyIdAIMessage
Create ai message with an any id field.
libs/langgraph/tests/messages.py:25
↓ 7 callersMethodabatch
(self, ops: Iterable[Op])
libs/checkpoint/tests/test_store.py:20
↓ 7 callersFunctioncoerce_to_runnable
Coerce a runnable-like object into a Runnable. Args: thing: A runnable-like object. Returns: A Runnable.
libs/langgraph/langgraph/utils/runnable.py:265
↓ 7 callersFunctionread_channels
( channels: Mapping[str, BaseChannel], select: Union[Sequence[str], str], *, skip_empty: bool
libs/langgraph/langgraph/pregel/io.py:29
↓ 7 callersMethodwait
Block until the semaphore can be acquired, but don't acquire it.
libs/langgraph/langgraph/utils/queue.py:53
↓ 6 callersFunctionChannelsManager
Manage channels for the lifetime of a Pregel invocation (multiple steps).
libs/langgraph/langgraph/pregel/manager.py:21
↓ 6 callersMethodabatch
Execute multiple operations asynchronously in a single batch. Args: ops: An iterable of operations to execute. Returns:
libs/checkpoint/langgraph/store/base/__init__.py:195
↓ 6 callersMethodaget_subgraphs
( self, *, namespace: Optional[str] = None, recurse: bool = False )
libs/langgraph/langgraph/pregel/__init__.py:437
↓ 6 callersMethodaput
Save a checkpoint to the database asynchronously. This method saves a checkpoint to the Postgres database. The checkpoint is associated
libs/checkpoint-postgres/langgraph/checkpoint/postgres/aio.py:230
↓ 6 callersMethodfrom_checkpoint
(self, checkpoint: Optional[list[Value]])
libs/langgraph/langgraph/channels/topic.py:55
↓ 6 callersMethodget_subgraphs
( self, *, namespace: Optional[str] = None, recurse: bool = False )
libs/langgraph/langgraph/pregel/__init__.py:386
↓ 6 callersMethodon
(scope: str)
libs/langgraph/langgraph/managed/shared_value.py:46
↓ 6 callersMethodpatch
Send a PATCH request.
libs/sdk-py/langgraph_sdk/client.py:245
↓ 6 callersMethodsetup
(self)
libs/checkpoint/tests/test_memory.py:17
↓ 5 callersMethod_cursor
(self, *, pipeline: bool = False)
libs/checkpoint-postgres/langgraph/checkpoint/postgres/__init__.py:367
↓ 5 callersMethod_cursor
( self, *, pipeline: bool = False )
libs/checkpoint-postgres/langgraph/checkpoint/postgres/aio.py:323
↓ 5 callersMethodabatch
(self, ops: Iterable[Op])
libs/checkpoint-postgres/langgraph/store/postgres/base.py:274
↓ 5 callersFunctionapply_writes
Apply 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 app
libs/langgraph/langgraph/pregel/algo.py:184
↓ 5 callersMethodasearch
Asynchronously search for items within a namespace prefix. Args: namespace_prefix: Hierarchical path prefix to search within.
libs/checkpoint/langgraph/store/base/__init__.py:323
↓ 5 callersMethodbatch
(self, ops: Iterable[Op])
libs/checkpoint-postgres/langgraph/store/postgres/base.py:242
↓ 5 callersMethodbatch
Execute multiple operations synchronously in a single batch. Args: ops: An iterable of operations to execute. Returns:
libs/checkpoint/langgraph/store/base/__init__.py:183
↓ 5 callersMethodcommit
( self, task: PregelExecutableTask, exception: Optional[BaseException] )
libs/langgraph/langgraph/pregel/runner.py:198
↓ 5 callersFunctionconfig_to_compose
( config_path: pathlib.Path, config: Config, base_image: str, watch: bool = False, )
libs/cli/langgraph_cli/config.py:312
↓ 5 callersMethodcopy
* Copy an existing thread * @param threadId ID of the thread to be copied * @returns Newly copied thread
libs/sdk-js/src/client.ts:440
↓ 5 callersFunctioncopy_checkpoint
(checkpoint: Checkpoint)
libs/checkpoint/langgraph/checkpoint/base/__init__.py:114
↓ 5 callersMethodget
(self)
libs/checkpoint/langgraph/checkpoint/serde/types.py:35
↓ 5 callersMethodinvoke
( self, input: Input, config: Optional[RunnableConfig] = None, **kwargs: Any )
libs/langgraph/langgraph/prebuilt/tool_node.py:136
next →1–100 of 1,515, ranked by callers