ޠj]SSKJr SSKrSSKrSSKrSSKJrJrJr SSK J r SSK J r SSK JrJrJrJrJrJrJr SSKJr SSKJr SS KJr SS KJr SS KJr SS KJ r J!r! SS K"J#r# SSK$J%r%J&r& SSK'J(r(J)r) SSK*J+r+ SSK,J-r- SSK.J/r/J0r0 SSK1J2r2 SSK3J4r4J5r5J6r6J7r7J8r8J9r9 SSK:J;r; SSKr> SSK?J@r@JArAJBrBJCrCJDrD SSKEJFrF SSKGJHrHJIrI SrJ"SS\\4\645rK\S&SSSSS.S'Sjjj5rL\S(Sj5rL\S)S j5rLS&SSSSS.S*S!jjjrL\"S"5rM\"S#5rN"S$S%\\F5rOg)+) annotationsN) AwaitableCallableSequence) dataclass) timedelta)AnyGenericTypeVarcastget_args get_originoverload) BaseCache)BaseCheckpointSaver) BaseStore)Unpack)_serde)CACHE_NS_WRITESPREVIOUS)is_async_callable)coerce_timeout_policysync_timeout_unsupported)MISSINGDeprecatedKwargs)EphemeralValue) LastValue)ENDSTART)Pregel)PSyncAsyncFutureT_call_with_optionsget_runnable_for_entrypoint identifier) PregelNode) ChannelWriteChannelWriteEntry) _DC_KWARGS CachePolicy RetryPolicy StreamMode TimeoutPolicy)ContextT)LangGraphDeprecatedSinceV05LangGraphDeprecatedSinceV10)task entrypointc^\rSrSrSSSS.S SjjrS SjrS SjrS SjrSrg) _TaskFunction;N) cache_policytimeoutnamecUbK[US5(a4[R"URUR5nXVlUnOXQlXlX lX0lX@l [R"X5 g)N__func__) hasattr functoolspartialr;__self____name__func retry_policyr7r8update_wrapper)selfrArBr7r8r9instance_methods Q/var/www/html/gaurav/venv/lib/python3.13/site-packages/langgraph/func/__init__.py__init___TaskFunction.__init__<si  tZ((#,"3"3DMM4=="Q+/(&!%  ((   ,c n[URUUURURURS9$)N)rBr7r8)r$rArBr7r8)rDargskwargss rF__call___TaskFunction.__call__Vs5! II  ****LL   rIcURb5UR[[UR5=(d S445 ggzClear the cache for this task.N __dynamic__)r7clearrr&rArDcaches rF clear_cache_TaskFunction.clear_cache`s5    ( KK/:dii+@+QMRT U )rIc# URb=UR[[UR5=(d S445IShvN ggN7frP)r7aclearrr&rArSs rF aclear_cache_TaskFunction.aclear_cacheesJ    (,,!:dii#8#IMJL   ) sAAAA)r7rArBr8) rA*Callable[P, Awaitable[T]] | Callable[P, T]rBzSequence[RetryPolicy]r7,CachePolicy[Callable[P, str | bytes]] | Noner8zTimeoutPolicy | Noner9 str | NonereturnNone)rKzP.argsrLzP.kwargsr^zSyncAsyncFuture[T])rTrr^r_) r@ __module__ __qualname____firstlineno__rGrMrUrY__static_attributes__rIrFr5r5;s_ FJ(,-8-, - C - & -- -4 V rIr5)r9rBr7r8c gNrd)__func_or_none__r9rBr7r8rLs rFr2r2msrIcgrfrdrgs rFr2r2|sNQrIcgrfrdris rFr2r2sCFrIc ^^^^ URS[5=n[La[R"S[SS9 UcUn[ U5m UcSO[ U[5(aU4OUmSUUUU 4SjjnUbU"U5$U$)a Define a LangGraph task using the `task` decorator. !!! important "Requires python 3.11 or higher for async functions" The `task` decorator supports both sync and async functions. To use async functions, ensure that you are using Python 3.11 or higher. Tasks can only be called from within an [`entrypoint`][langgraph.func.entrypoint] or from within a `StateGraph`. A task can be called like a regular function with the following differences: - When a checkpointer is enabled, the function inputs and outputs must be serializable. - The decorated function can only be called from within an entrypoint or `StateGraph`. - Calling the function produces a future. This makes it easy to parallelize tasks. Args: name: An optional name for the task. If not provided, the function name will be used. retry_policy: An optional retry policy (or list of policies) to use for the task in case of a failure. cache_policy: An optional cache policy to use for the task. This allows caching of the task results. timeout: Timeout for each task attempt. A number or `timedelta` is a hard wall-clock cap and is not refreshed. Use `TimeoutPolicy` to configure both a wall-clock `run_timeout` and an `idle_timeout` refreshed by progress signals. For long-running work that doesn't naturally emit progress, call `runtime.heartbeat()` from inside the task. When the timeout fires, `NodeTimeoutError` is raised and the retry policy (if any) decides whether to retry. Supported only for async tasks; sync tasks cannot be safely cancelled in-process. Returns: A callable function when used as a decorator. Example: Sync Task ```python from langgraph.func import entrypoint, task @task def add_one_task(a: int) -> int: return a + 1 @entrypoint() def add_one(numbers: list[int]) -> list[int]: futures = [add_one_task(n) for n in numbers] results = [f.result() for f in futures] return results # Call the entrypoint add_one.invoke([1, 2, 3]) # Returns [2, 3, 4] ``` Example: Async Task ```python import asyncio from langgraph.func import entrypoint, task @task async def add_one_task(a: int) -> int: return a + 1 @entrypoint() async def add_one(numbers: list[int]) -> list[int]: futures = [add_one_task(n) for n in numbers] return asyncio.gather(*futures) # Call the entrypoint await add_one.ainvoke([1, 2, 3]) # Returns [2, 3, 4] ``` retryM`retry` is deprecated and will be removed. Please use `retry_policy` instead.category stacklevelrdc>TbM[U5(d=T=(d! [USURR5n[ [ U5SS9e[ UTTTTS9$)Nr@Task)kind)rBr7r8r9)rgetattr __class__r@rstrr5)rAname_r7r9retry_policiestimeout_policys rF decoratortask..decorators`  %.?.E.ENGD*dnn6M6MNE*3u:FC C '%"   rI)rAr[r^zCallable[P, SyncAsyncFuture[T]])getrwarningswarnr0r isinstancer,) rgr9rBr7r8rLrlr{ryrzs ` ` @@rFr2r2shGW--g= [0   L*73N    lK 0 0_    8  (   #)** rIRSc\rSrSrSrS S Sjjr\"S 0\D6"SS\\ \ 455r S Sjr Sr g) r3iaDefine 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 parameter can be of any type. Use a dictionary to pass **multiple parameters** to the function. ### Injectable parameters The decorated function can request access to additional parameters that will be injected automatically at run time. These parameters include: | Parameter | Description | |------------------|------------------------------------------------------------------------------------------------------| | **`config`** | A configuration object (aka `RunnableConfig`) that holds run-time configuration values. | | **`previous`** | The previous return value for the given thread (available only when a checkpointer is provided). | | **`runtime`** | A `Runtime` object that contains information about the current run, including context, store, writer | The entrypoint decorator can be applied to sync functions or async functions. ### State management The **`previous`** parameter can be used to access the return value of the previous invocation of the entrypoint on the same thread id. This value is only available when a checkpointer is provided. If you want **`previous`** to be different from the return value, you can use the `entrypoint.final` object to return a value while saving a different value to the checkpoint. Args: checkpointer: Specify a checkpointer to create a workflow that can persist its state across runs. store: A generalized key-value store. Some implementations may support semantic search capabilities through an optional `index` configuration. cache: A cache to use for caching the results of the workflow. context_schema: Specifies the schema for the context object that will be passed to the workflow. cache_policy: A cache policy to use for caching the results of the workflow. retry_policy: A retry policy (or list of policies) to use for the workflow in case of a failure. timeout: Timeout for each workflow attempt. A number or `timedelta` is a hard wall-clock cap and is not refreshed. Use `TimeoutPolicy` to configure both a wall-clock `run_timeout` and an `idle_timeout` refreshed by progress signals. For long-running work that doesn't naturally emit progress, call `runtime.heartbeat()` from inside the workflow. When the timeout fires, `NodeTimeoutError` is raised and the retry policy (if any) decides whether to retry. Supported only for async workflows; sync workflows cannot be safely cancelled in-process. !!! warning "`config_schema` Deprecated" The `config_schema` parameter is deprecated in v0.6.0 and support will be removed in v2.0.0. Please use `context_schema` instead to specify the schema for run-scoped context. Example: Using entrypoint and tasks ```python import time from langgraph.func import entrypoint, task from langgraph.types import interrupt, Command from langgraph.checkpoint.memory import InMemorySaver @task def compose_essay(topic: str) -> str: time.sleep(1.0) # Simulate slow operation return f"An essay about {topic}" @entrypoint(checkpointer=InMemorySaver()) def review_workflow(topic: str) -> dict: """Manages the workflow for generating and reviewing an essay. The workflow includes: 1. Generating an essay about the given topic. 2. Interrupting the workflow for human review of the generated essay. Upon resuming the workflow, compose_essay task will not be re-executed as its result is cached by the checkpointer. Args: topic: The subject of the essay. Returns: dict: A dictionary containing the generated essay and the human review. """ essay_future = compose_essay(topic) essay = essay_future.result() human_review = interrupt({ "question": "Please provide a review", "essay": essay }) return { "essay": essay, "review": human_review, } # Example configuration for the workflow config = { "configurable": { "thread_id": "some_thread" } } # Topic for the essay topic = "cats" # Stream the workflow to generate the essay and await human review for result in review_workflow.stream(topic, config): print(result) # Example human review provided after the interrupt human_review = "This essay is great." # Resume the workflow with the provided human review for result in review_workflow.stream(Command(resume=human_review), config): print(result) ``` Example: Accessing the previous return value When a checkpointer is enabled the function can access the previous return value of the previous invocation on the same thread id. ```python from typing import Optional from langgraph.checkpoint.memory import MemorySaver from langgraph.func import entrypoint @entrypoint(checkpointer=InMemorySaver()) def my_workflow(input_data: str, previous: Optional[str] = None) -> str: return "world" config = {"configurable": {"thread_id": "some_thread"}} my_workflow.invoke("hello", config) ``` Example: Using `entrypoint.final` to save a value The `entrypoint.final` object allows you to return a value while saving a different value to the checkpoint. This value will be accessible in the next invocation of the entrypoint via the `previous` parameter, as long as the same thread id is used. ```python from typing import Any from langgraph.checkpoint.memory import MemorySaver from langgraph.func import entrypoint @entrypoint(checkpointer=InMemorySaver()) def my_workflow( number: int, *, previous: Any = None, ) -> entrypoint.final[int, int]: previous = previous or 0 # This will return the previous value to the caller, saving # 2 * number to the checkpoint, which will be used in the next invocation # for the `previous` parameter. return entrypoint.final(value=previous, save=2 * number) config = {"configurable": {"thread_id": "some_thread"}} my_workflow.invoke(3, config) # 0 (previous was None) my_workflow.invoke(1, config) # 6 (previous was 3 * 2 from the previous invocation) ``` Nc URS[5=n [La4[R"S[SS9 Uc[ [ [U 5nURS[5=n [La)[R"S[SS9 Uc [ SU 5nXl X l X0l XPl X`l [U5UlX@lg) z$Initialize the entrypoint decorator. config_schemazW`config_schema` is deprecated and will be removed. Please use `context_schema` instead.rnroNrlrmz#RetryPolicy | Sequence[RetryPolicy])r}rr~rr1r typer/r0 checkpointerstorerTr7rBrr8context_schema) rDrrrTrr7rBr8rLrrls rFrGentrypoint.__init__s$ZZA AM' Q MMi4  %!%d8nm!DZZ1 1E' A MM_4  ##$I5Q (  ((,W5 ,rIc0\rSrSr%SrS\S'S\S'Srg) entrypoint.finaliaA 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. Example: Decoupling the return value and the save value ```python from langgraph.checkpoint.memory import InMemorySaver from langgraph.func import entrypoint @entrypoint(checkpointer=InMemorySaver()) def my_workflow( number: int, *, previous: Any = None, ) -> entrypoint.final[int, int]: previous = previous or 0 # This will return the previous value to the caller, saving # 2 * number to the checkpoint, which will be used in the next invocation # for the `previous` parameter. return entrypoint.final(value=previous, save=2 * number) config = {"configurable": {"thread_id": "1"}} my_workflow.invoke(3, config) # 0 (previous was None) my_workflow.invoke(1, config) # 6 (previous was 3 * 2 from the previous invocation) ``` rvaluersaverdN)r@r`rarb__doc____annotations__rcrdrIrFfinalrs >T rIrc[R"U5(d"U5(a [S5e[ U5nSn[R "U5n[ [URR55S5nU(d [S5eURUR[RRLaURURO[nSSjnSSjn[[pUR[RRLaUR[ R"La[=pO|[%UR5n U [ R"LaG['UR5n [)U 5S:wa [+S5e['UR5upO UR=p[-UR.[1U[2/[2UR4[7[9[:US 9[9[<US 9/5/S 90[2[?U5[:[AU [:5[<[AU [<50[2[:[:US URBURDURFURHURJ=(d S URLS 9 n [NRP(aj[NRR"XiU /URLb URL/O/-U RTS9nXl+[NRX"U RBU5U l!U $)zConvert a function into a Pregel graph. Args: func: The function to convert. Support both sync and async functions. Returns: A Pregel graph. z3Generators are not supported in the Functional API.updatesNz4Entrypoint function must have at least one parameterc\[U[R5(a UR$U$)zEExtract the return_ value the entrypoint.final object or passthrough.)rr3rrrs rF_pluck_return_value0entrypoint.__call__.._pluck_return_value"s#",UJ4D4D"E"E5;; P5 PrIc\[U[R5(a UR$U$)z?Get save value from the entrypoint.final object or passthrough.)rr3rrrs rF_pluck_save_value.entrypoint.__call__.._pluck_save_value&s#!+E:3C3C!D!D5:: O% OrIrnzPlease an annotation for both the return_ and the save values.For example, `-> entrypoint.final[int, str]` would assign a return_ a type of `int` and save the type `str`.)mapper)boundtriggerschannelsr8writersTrd) nodesrinput_channelsoutput_channelsstream_channels stream_mode stream_eagerrrrTr7rBr)schemasr)rr r^r )-inspectisgeneratorfunctionisasyncgenfunctionNotImplementedErrorr% signaturenextiter parameterskeys ValueError annotation Signatureemptyr return_annotationr3rrr len TypeErrorr r@r'rr8r(r)rrrrrrrTr7rBrrSTRICT_MSGPACK_ENABLEDbuild_serde_allowlistr_serde_allowlistapply_checkpointer_allowlist)rDrArrsigfirst_parameter_name input_typerr output_type save_typeorigintype_annotationsgraphserde_allowlists rFrMentrypoint.__call__s  & &t , ,0J0J40P0P%E ,D1"+ %#D)<)<)>$?F#ST T~~23>>$$**+ NN/ 0 ; ;  Q P"%cY  (9(9(?(? ?%%)9)99*-- i#C$9$9:Z---'/0E0E'F$+,1'O .6c6K6K-L*K.1.C.CCK17 z#W" LL$ 1#>Q R 1(CT U "~j1Y{C0)Ix8 !#**********0b..A!2 D  ( ($::#)<,0,?,?,KD''(QSUO &5 "!'!D!D""O"E  rI)rTr7rrrBrr8)NNNNNNN)rzBaseCheckpointSaver | NonerzBaseStore | NonerTzBaseCache | Nonerztype[ContextT] | Noner7zCachePolicy | NonerB*RetryPolicy | Sequence[RetryPolicy] | Noner8(float | timedelta | TimeoutPolicy | NonerLUnpack[DeprecatedKwargs]r^r_rd)rAzCallable[..., Any]r^r )r@r`rarbrrGrr*r rrrrMrcrdrIrFr3r3sl`48"&"&04+/CG<@$-0$- $- $- . $- ) $-A$-:$-+$- $-L& 1 & & PhrIr3rf)rgr_r9r]rBrr7r\r8rrLrr^zKCallable[[Callable[P, Awaitable[T]] | Callable[P, T]], _TaskFunction[P, T]])rgzCallable[P, Awaitable[T]]r^_TaskFunction[P, T])rgzCallable[P, T]r^r)rgz1Callable[P, Awaitable[T]] | Callable[P, T] | Noner9r]rBrr7r\r8rrLrr^zaCallable[[Callable[P, Awaitable[T]] | Callable[P, T]], _TaskFunction[P, T]] | _TaskFunction[P, T])P __future__rr=rr~collections.abcrrr dataclassesrdatetimertypingr r r r r rrlanggraph.cache.baserlanggraph.checkpoint.baserlanggraph.store.basertyping_extensionsrlanggraph._internalrlanggraph._internal._constantsrrlanggraph._internal._runnablerlanggraph._internal._timeoutrrlanggraph._internal._typingrr"langgraph.channels.ephemeral_valuerlanggraph.channels.last_valuerlanggraph.constantsrrlanggraph.pregelr langgraph.pregel._callr!r"r#r$r%r&langgraph.pregel._readr'langgraph.pregel._writer(r)langgraph.typesr*r+r,r-r.langgraph.typingr/langgraph.warningsr0r1__all__r5r2rrr3rdrIrFrs"99!+9*$&D;B=3*#.C&W /GAqDM/d ! ?CAE8<    =  ?  6 '     Q Q F FKOw?CAE8< wGw w= w ? w 6 w'wwt CL CLf"frI