langchain API reference

400 public APIs from langchain (langchain-ai/langchain) — 127 classes, 57 functions, 216 methods. Signatures extracted by static analysis of the actual source.

Repository: langchain-ai/langchain

Kind	Count
Classes	127
Functions	57
Methods	216

API list

funclibs.core.langchain_core._api.beta_decorator.emit_warning() -> None

Emit the warning.

funclibs.core.langchain_core._api.beta_decorator.finalize(_:Callable[..., Any], new_doc:str) -> T

Finalize the annotation of a class.

funclibs.core.langchain_core._api.beta_decorator.surface_langchain_beta_warnings() -> None

Unmute LangChain beta warnings.

func

libs.core.langchain_core._api.beta_decorator.warn_beta(*message:str='', *name:str='', *obj_type:str='', *addendum:str='') -> None

Display a standardized beta annotation.

funclibs.core.langchain_core._api.beta_decorator.warn_if_direct_instance(self:Any, *args:Any, **kwargs:Any) -> Any

Warn that the class is in beta.

funclibs.core.langchain_core._api.deprecation.emit_warning() -> None

Emit the warning.

funclibs.core.langchain_core._api.deprecation.finalize(_:Callable[..., Any], new_doc:str) -> T

Finalize the deprecation of a class.

funclibs.core.langchain_core._api.deprecation.surface_langchain_deprecation_warnings() -> None

Unmute LangChain deprecation warnings.

funclibs.core.langchain_core._api.deprecation.warn_if_direct_instance(self:Any, *args:Any, **kwargs:Any) -> Any

Warn that the class is in beta.

funclibs.core.langchain_core._security._policy.validate_hostname(hostname:str, policy:SSRFPolicy) -> None

Validate a hostname against the SSRF policy.

funclibs.core.langchain_core._security._policy.validate_resolved_ip(ip_str:str, policy:SSRFPolicy) -> None

Validate a resolved IP address against the SSRF policy.

funclibs.core.langchain_core._security._policy.validate_url_sync(url:str, policy:SSRFPolicy=DEFAULT_SSRF_POLICY) -> None

Synchronous URL validation (no DNS resolution).

func

libs.core.langchain_core._security._ssrf_protection.is_safe_url(url:str | AnyHttpUrl, *allow_private:bool=False, *allow_http:bool=True) -> bool

Non-throwing version of `validate_safe_url`.

func

libs.core.langchain_core._security._ssrf_protection.validate_safe_url(url:str | AnyHttpUrl, *allow_private:bool=False, *allow_http:bool=True) -> str

Validate a URL for SSRF protection.

func

libs.core.langchain_core._security._transport.ssrf_safe_client(policy:SSRFPolicy=DEFAULT_SSRF_POLICY, **kwargs:object) -> httpx.Client

Create an `httpx.Client` with SSRF protection.

classlibs.core.langchain_core.agents.AgentAction

Represents a request to execute an action by an agent.

methodlibs.core.langchain_core.agents.AgentAction.get_lc_namespace() -> list[str]

Get the namespace of the LangChain object.

methodlibs.core.langchain_core.agents.AgentAction.is_lc_serializable() -> bool

`AgentAction` is serializable.

classlibs.core.langchain_core.agents.AgentFinish

Final return value of an `ActionAgent`.

methodlibs.core.langchain_core.agents.AgentFinish.get_lc_namespace() -> list[str]

Get the namespace of the LangChain object.

methodlibs.core.langchain_core.agents.AgentFinish.is_lc_serializable() -> bool

Return `True` as this class is serializable.

methodlibs.core.langchain_core.agents.AgentFinish.messages() -> Sequence[BaseMessage]

Messages that correspond to this observation.

classlibs.core.langchain_core.agents.AgentStep

Result of running an `AgentAction`.

methodlibs.core.langchain_core.agents.AgentStep.messages() -> Sequence[BaseMessage]

Messages that correspond to this observation.

classlibs.core.langchain_core.caches.BaseCache

Interface for a caching layer for LLMs and Chat models.

methodlibs.core.langchain_core.caches.BaseCache.aclear(**kwargs:Any) -> None

Async clear cache that can take additional keyword arguments.

methodlibs.core.langchain_core.caches.BaseCache.alookup(prompt:str, llm_string:str) -> RETURN_VAL_TYPE | None

Async look up based on `prompt` and `llm_string`.

methodlibs.core.langchain_core.caches.BaseCache.clear(**kwargs:Any) -> None

Clear cache that can take additional keyword arguments.

methodlibs.core.langchain_core.caches.BaseCache.lookup(prompt:str, llm_string:str) -> RETURN_VAL_TYPE | None

Look up based on `prompt` and `llm_string`.

methodlibs.core.langchain_core.caches.BaseCache.update(prompt:str, llm_string:str, return_val:RETURN_VAL_TYPE) -> None

Update cache based on `prompt` and `llm_string`.

classlibs.core.langchain_core.caches.InMemoryCache

Cache that stores things in memory.

methodlibs.core.langchain_core.caches.InMemoryCache.aclear(**kwargs:Any) -> None

Async clear cache.

methodlibs.core.langchain_core.caches.InMemoryCache.alookup(prompt:str, llm_string:str) -> RETURN_VAL_TYPE | None

Async look up based on `prompt` and `llm_string`.

methodlibs.core.langchain_core.caches.InMemoryCache.clear(**kwargs:Any) -> None

Clear cache.

methodlibs.core.langchain_core.caches.InMemoryCache.lookup(prompt:str, llm_string:str) -> RETURN_VAL_TYPE | None

Look up based on `prompt` and `llm_string`.

methodlibs.core.langchain_core.caches.InMemoryCache.update(prompt:str, llm_string:str, return_val:RETURN_VAL_TYPE) -> None

Update cache based on `prompt` and `llm_string`.

classlibs.core.langchain_core.callbacks.base.AsyncCallbackHandler

Base async callback handler.

method

libs.core.langchain_core.callbacks.base.AsyncCallbackHandler.on_agent_action(action:AgentAction, *run_id:UUID, *parent_run_id:UUID | None=None, *tags:list[str] | None=None, **kwargs:Any) -> None

Run on agent action.

method

libs.core.langchain_core.callbacks.base.AsyncCallbackHandler.on_agent_finish(finish:AgentFinish, *run_id:UUID, *parent_run_id:UUID | None=None, *tags:list[str] | None=None, **kwargs:Any) -> None

Run on the agent end.

method

libs.core.langchain_core.callbacks.base.AsyncCallbackHandler.on_chain_end(outputs:dict[str, Any], *run_id:UUID, *parent_run_id:UUID | None=None, *tags:list[str] | None=None, **kwargs:Any) -> None

Run when a chain ends running.

method

libs.core.langchain_core.callbacks.base.AsyncCallbackHandler.on_chain_error(error:BaseException, *run_id:UUID, *parent_run_id:UUID | None=None, *tags:list[str] | None=None, **kwargs:Any) -> None

Run when chain errors.

method

libs.core.langchain_core.callbacks.base.AsyncCallbackHandler.on_llm_end(response:LLMResult, *run_id:UUID, *parent_run_id:UUID | None=None, *tags:list[str] | None=None, **kwargs:Any) -> None

Run when the model ends running.

method

libs.core.langchain_core.callbacks.base.AsyncCallbackHandler.on_llm_error(error:BaseException, *run_id:UUID, *parent_run_id:UUID | None=None, *tags:list[str] | None=None, **kwargs:Any) -> None

Run when LLM errors.

method

libs.core.langchain_core.callbacks.base.AsyncCallbackHandler.on_retriever_end(documents:Sequence[Document], *run_id:UUID, *parent_run_id:UUID | None=None, *tags:list[str] | None=None, **kwargs:Any) -> None

Run on the retriever end.

method

libs.core.langchain_core.callbacks.base.AsyncCallbackHandler.on_retriever_error(error:BaseException, *run_id:UUID, *parent_run_id:UUID | None=None, *tags:list[str] | None=None, **kwargs:Any) -> None

Run on retriever error.

method

libs.core.langchain_core.callbacks.base.AsyncCallbackHandler.on_retry(retry_state:RetryCallState, *run_id:UUID, *parent_run_id:UUID | None=None, **kwargs:Any) -> Any

Run on a retry event.

method

libs.core.langchain_core.callbacks.base.AsyncCallbackHandler.on_text(text:str, *run_id:UUID, *parent_run_id:UUID | None=None, *tags:list[str] | None=None, **kwargs:Any) -> None

Run on an arbitrary text.

method

libs.core.langchain_core.callbacks.base.AsyncCallbackHandler.on_tool_end(output:Any, *run_id:UUID, *parent_run_id:UUID | None=None, *tags:list[str] | None=None, **kwargs:Any) -> None

Run when the tool ends running.

method

libs.core.langchain_core.callbacks.base.AsyncCallbackHandler.on_tool_error(error:BaseException, *run_id:UUID, *parent_run_id:UUID | None=None, *tags:list[str] | None=None, **kwargs:Any) -> None

Run when tool errors.

classlibs.core.langchain_core.callbacks.base.BaseCallbackHandler

Base callback handler.

methodlibs.core.langchain_core.callbacks.base.BaseCallbackHandler.ignore_agent() -> bool

Whether to ignore agent callbacks.

methodlibs.core.langchain_core.callbacks.base.BaseCallbackHandler.ignore_chain() -> bool

Whether to ignore chain callbacks.

methodlibs.core.langchain_core.callbacks.base.BaseCallbackHandler.ignore_chat_model() -> bool

Whether to ignore chat model callbacks.

methodlibs.core.langchain_core.callbacks.base.BaseCallbackHandler.ignore_custom_event() -> bool

Ignore custom event.

methodlibs.core.langchain_core.callbacks.base.BaseCallbackHandler.ignore_llm() -> bool

Whether to ignore LLM callbacks.

methodlibs.core.langchain_core.callbacks.base.BaseCallbackHandler.ignore_retriever() -> bool

Whether to ignore retriever callbacks.

methodlibs.core.langchain_core.callbacks.base.BaseCallbackHandler.ignore_retry() -> bool

Whether to ignore retry callbacks.

classlibs.core.langchain_core.callbacks.base.BaseCallbackManager

Base callback manager.

method

libs.core.langchain_core.callbacks.base.BaseCallbackManager.add_handler(handler:BaseCallbackHandler, inherit:bool=True) -> None

Add a handler to the callback manager.

method

libs.core.langchain_core.callbacks.base.BaseCallbackManager.add_metadata(metadata:dict[str, Any], inherit:bool=True) -> None

Add metadata to the callback manager.

methodlibs.core.langchain_core.callbacks.base.BaseCallbackManager.add_tags(tags:list[str], inherit:bool=True) -> None

Add tags to the callback manager.

methodlibs.core.langchain_core.callbacks.base.BaseCallbackManager.copy() -> Self

Return a copy of the callback manager.

methodlibs.core.langchain_core.callbacks.base.BaseCallbackManager.is_async() -> bool

Whether the callback manager is async.

methodlibs.core.langchain_core.callbacks.base.BaseCallbackManager.remove_handler(handler:BaseCallbackHandler) -> None

Remove a handler from the callback manager.

methodlibs.core.langchain_core.callbacks.base.BaseCallbackManager.remove_metadata(keys:list[str]) -> None

Remove metadata from the callback manager.

methodlibs.core.langchain_core.callbacks.base.BaseCallbackManager.remove_tags(tags:list[str]) -> None

Remove tags from the callback manager.

classlibs.core.langchain_core.callbacks.base.CallbackManagerMixin

Mixin for callback manager.

classlibs.core.langchain_core.callbacks.base.ChainManagerMixin

Mixin for chain callbacks.

method

libs.core.langchain_core.callbacks.base.ChainManagerMixin.on_agent_action(action:AgentAction, *run_id:UUID, *parent_run_id:UUID | None=None, **kwargs:Any) -> Any

Run on agent action.

method

libs.core.langchain_core.callbacks.base.ChainManagerMixin.on_agent_finish(finish:AgentFinish, *run_id:UUID, *parent_run_id:UUID | None=None, **kwargs:Any) -> Any

Run on the agent end.

method

libs.core.langchain_core.callbacks.base.ChainManagerMixin.on_chain_end(outputs:dict[str, Any], *run_id:UUID, *parent_run_id:UUID | None=None, **kwargs:Any) -> Any

Run when chain ends running.

method

libs.core.langchain_core.callbacks.base.ChainManagerMixin.on_chain_error(error:BaseException, *run_id:UUID, *parent_run_id:UUID | None=None, **kwargs:Any) -> Any

Run when chain errors.

classlibs.core.langchain_core.callbacks.base.LLMManagerMixin

Mixin for LLM callbacks.

method

libs.core.langchain_core.callbacks.base.LLMManagerMixin.on_llm_end(response:LLMResult, *run_id:UUID, *parent_run_id:UUID | None=None, *tags:list[str] | None=None, **kwargs:Any) -> Any

Run when LLM ends running.

method

libs.core.langchain_core.callbacks.base.LLMManagerMixin.on_llm_error(error:BaseException, *run_id:UUID, *parent_run_id:UUID | None=None, *tags:list[str] | None=None, **kwargs:Any) -> Any

Run when LLM errors.

classlibs.core.langchain_core.callbacks.base.RetrieverManagerMixin

Mixin for `Retriever` callbacks.

method

libs.core.langchain_core.callbacks.base.RetrieverManagerMixin.on_retriever_end(documents:Sequence[Document], *run_id:UUID, *parent_run_id:UUID | None=None, **kwargs:Any) -> Any

Run when `Retriever` ends running.

method

libs.core.langchain_core.callbacks.base.RetrieverManagerMixin.on_retriever_error(error:BaseException, *run_id:UUID, *parent_run_id:UUID | None=None, **kwargs:Any) -> Any

Run when `Retriever` errors.

classlibs.core.langchain_core.callbacks.base.RunManagerMixin

Mixin for run manager.

method

libs.core.langchain_core.callbacks.base.RunManagerMixin.on_retry(retry_state:RetryCallState, *run_id:UUID, *parent_run_id:UUID | None=None, **kwargs:Any) -> Any

Run on a retry event.

method

libs.core.langchain_core.callbacks.base.RunManagerMixin.on_text(text:str, *run_id:UUID, *parent_run_id:UUID | None=None, **kwargs:Any) -> Any

Run on an arbitrary text.

classlibs.core.langchain_core.callbacks.base.ToolManagerMixin

Mixin for tool callbacks.

method

libs.core.langchain_core.callbacks.base.ToolManagerMixin.on_tool_end(output:Any, *run_id:UUID, *parent_run_id:UUID | None=None, **kwargs:Any) -> Any

Run when the tool ends running.

method

libs.core.langchain_core.callbacks.base.ToolManagerMixin.on_tool_error(error:BaseException, *run_id:UUID, *parent_run_id:UUID | None=None, **kwargs:Any) -> Any

Run when tool errors.

classlibs.core.langchain_core.callbacks.file.FileCallbackHandler

Callback handler that writes to a file.

methodlibs.core.langchain_core.callbacks.file.FileCallbackHandler.close() -> None

Close the file if it's open.

methodlibs.core.langchain_core.callbacks.file.FileCallbackHandler.on_chain_end(outputs:dict[str, Any], **kwargs:Any) -> None

Print that we finished a chain.

method

libs.core.langchain_core.callbacks.file.FileCallbackHandler.on_chain_start(serialized:dict[str, Any], inputs:dict[str, Any], **kwargs:Any) -> None

Print that we are entering a chain.

method

libs.core.langchain_core.callbacks.file.FileCallbackHandler.on_text(text:str, color:str | None=None, end:str='', **kwargs:Any) -> None

Handle text output.

classlibs.core.langchain_core.callbacks.manager.AsyncCallbackManagerForChainGroup

Async callback manager for the chain group.

method

libs.core.langchain_core.callbacks.manager.AsyncCallbackManagerForChainGroup.on_chain_end(outputs:dict[str, Any] | Any, **kwargs:Any) -> None

Run when traced chain group ends.

method

libs.core.langchain_core.callbacks.manager.AsyncCallbackManagerForChainGroup.on_chain_error(error:BaseException, **kwargs:Any) -> None

Run when chain errors.

classlibs.core.langchain_core.callbacks.manager.AsyncCallbackManagerForChainRun

Async callback manager for chain run.

method

libs.core.langchain_core.callbacks.manager.AsyncCallbackManagerForChainRun.on_agent_action(action:AgentAction, **kwargs:Any) -> None

Run when agent action is received.

method

libs.core.langchain_core.callbacks.manager.AsyncCallbackManagerForChainRun.on_agent_finish(finish:AgentFinish, **kwargs:Any) -> None

Run when agent finish is received.

method

libs.core.langchain_core.callbacks.manager.AsyncCallbackManagerForChainRun.on_chain_end(outputs:dict[str, Any] | Any, **kwargs:Any) -> None

Run when a chain ends running.

method

libs.core.langchain_core.callbacks.manager.AsyncCallbackManagerForChainRun.on_chain_error(error:BaseException, **kwargs:Any) -> None

Run when chain errors.

classlibs.core.langchain_core.callbacks.manager.AsyncCallbackManagerForLLMRun

Async callback manager for LLM run.

method

libs.core.langchain_core.callbacks.manager.AsyncCallbackManagerForLLMRun.on_llm_end(response:LLMResult, **kwargs:Any) -> None

Run when LLM ends running.

method

libs.core.langchain_core.callbacks.manager.AsyncCallbackManagerForLLMRun.on_llm_error(error:BaseException, **kwargs:Any) -> None

Run when LLM errors.

classlibs.core.langchain_core.callbacks.manager.AsyncCallbackManagerForRetrieverRun

Async callback manager for retriever run.

method

libs.core.langchain_core.callbacks.manager.AsyncCallbackManagerForRetrieverRun.on_retriever_end(documents:Sequence[Document], **kwargs:Any) -> None

Run when the retriever ends running.

method

libs.core.langchain_core.callbacks.manager.AsyncCallbackManagerForRetrieverRun.on_retriever_error(error:BaseException, **kwargs:Any) -> None

Run when retriever errors.

classlibs.core.langchain_core.callbacks.manager.AsyncCallbackManagerForToolRun

Async callback manager for tool run.

methodlibs.core.langchain_core.callbacks.manager.AsyncCallbackManagerForToolRun.on_tool_end(output:Any, **kwargs:Any) -> None

Async run when the tool ends running.

method

libs.core.langchain_core.callbacks.manager.AsyncCallbackManagerForToolRun.on_tool_error(error:BaseException, **kwargs:Any) -> None

Run when tool errors.

classlibs.core.langchain_core.callbacks.manager.AsyncParentRunManager

Async parent run manager.

methodlibs.core.langchain_core.callbacks.manager.AsyncParentRunManager.get_child(tag:str | None=None) -> AsyncCallbackManager

Get a child callback manager.

classlibs.core.langchain_core.callbacks.manager.AsyncRunManager

Async run manager.

methodlibs.core.langchain_core.callbacks.manager.AsyncRunManager.get_sync() -> RunManager

Get the equivalent sync `RunManager`.

methodlibs.core.langchain_core.callbacks.manager.AsyncRunManager.on_retry(retry_state:RetryCallState, **kwargs:Any) -> None

Async run when a retry is received.

methodlibs.core.langchain_core.callbacks.manager.AsyncRunManager.on_text(text:str, **kwargs:Any) -> None

Run when a text is received.

classlibs.core.langchain_core.callbacks.manager.BaseRunManager

Base class for run manager (a bound callback manager).

classlibs.core.langchain_core.callbacks.manager.CallbackManager

Callback manager for LangChain.

method

libs.core.langchain_core.callbacks.manager.CallbackManager.on_llm_start(serialized:dict[str, Any], prompts:list[str], run_id:UUID | None=None, **kwargs:Any) -> list[CallbackManagerForLLMRun]

Run when LLM starts running.

classlibs.core.langchain_core.callbacks.manager.CallbackManagerForChainGroup

Callback manager for the chain group.

method

libs.core.langchain_core.callbacks.manager.CallbackManagerForChainGroup.on_chain_end(outputs:dict[str, Any] | Any, **kwargs:Any) -> None

Run when traced chain group ends.

method

libs.core.langchain_core.callbacks.manager.CallbackManagerForChainGroup.on_chain_error(error:BaseException, **kwargs:Any) -> None

Run when chain errors.

classlibs.core.langchain_core.callbacks.manager.CallbackManagerForChainRun

Callback manager for chain run.

method

libs.core.langchain_core.callbacks.manager.CallbackManagerForChainRun.on_agent_action(action:AgentAction, **kwargs:Any) -> None

Run when agent action is received.

method

libs.core.langchain_core.callbacks.manager.CallbackManagerForChainRun.on_agent_finish(finish:AgentFinish, **kwargs:Any) -> None

Run when agent finish is received.

method

libs.core.langchain_core.callbacks.manager.CallbackManagerForChainRun.on_chain_end(outputs:dict[str, Any] | Any, **kwargs:Any) -> None

Run when chain ends running.

method

libs.core.langchain_core.callbacks.manager.CallbackManagerForChainRun.on_chain_error(error:BaseException, **kwargs:Any) -> None

Run when chain errors.

classlibs.core.langchain_core.callbacks.manager.CallbackManagerForLLMRun

Callback manager for LLM run.

methodlibs.core.langchain_core.callbacks.manager.CallbackManagerForLLMRun.on_llm_end(response:LLMResult, **kwargs:Any) -> None

Run when LLM ends running.

method

libs.core.langchain_core.callbacks.manager.CallbackManagerForLLMRun.on_llm_error(error:BaseException, **kwargs:Any) -> None

Run when LLM errors.

classlibs.core.langchain_core.callbacks.manager.CallbackManagerForRetrieverRun

Callback manager for retriever run.

method

libs.core.langchain_core.callbacks.manager.CallbackManagerForRetrieverRun.on_retriever_end(documents:Sequence[Document], **kwargs:Any) -> None

Run when retriever ends running.

method

libs.core.langchain_core.callbacks.manager.CallbackManagerForRetrieverRun.on_retriever_error(error:BaseException, **kwargs:Any) -> None

Run when retriever errors.

classlibs.core.langchain_core.callbacks.manager.CallbackManagerForToolRun

Callback manager for tool run.

methodlibs.core.langchain_core.callbacks.manager.CallbackManagerForToolRun.on_tool_end(output:Any, **kwargs:Any) -> None

Run when the tool ends running.

method

libs.core.langchain_core.callbacks.manager.CallbackManagerForToolRun.on_tool_error(error:BaseException, **kwargs:Any) -> None

Run when tool errors.

classlibs.core.langchain_core.callbacks.manager.ParentRunManager

Synchronous parent run manager.

methodlibs.core.langchain_core.callbacks.manager.ParentRunManager.get_child(tag:str | None=None) -> CallbackManager

Get a child callback manager.

classlibs.core.langchain_core.callbacks.manager.RunManager

Synchronous run manager.

methodlibs.core.langchain_core.callbacks.manager.RunManager.on_retry(retry_state:RetryCallState, **kwargs:Any) -> None

Run when a retry is received.

methodlibs.core.langchain_core.callbacks.manager.RunManager.on_text(text:str, **kwargs:Any) -> None

Run when a text is received.

func

libs.core.langchain_core.callbacks.manager.adispatch_custom_event(name:str, data:Any, *config:RunnableConfig | None=None) -> None

Dispatch an adhoc event to the handlers.

func

libs.core.langchain_core.callbacks.manager.ahandle_event(handlers:list[BaseCallbackHandler], event_name:str, ignore_condition_name:str | None, *args:Any, **kwargs:Any) -> None

Async generic event handler for `AsyncCallbackManager`.

func

libs.core.langchain_core.callbacks.manager.dispatch_custom_event(name:str, data:Any, *config:RunnableConfig | None=None) -> None

Dispatch an adhoc event.

func

libs.core.langchain_core.callbacks.manager.handle_event(handlers:list[BaseCallbackHandler], event_name:str, ignore_condition_name:str | None, *args:Any, **kwargs:Any) -> None

Generic event handler for `CallbackManager`.

classlibs.core.langchain_core.callbacks.stdout.StdOutCallbackHandler

Callback handler that prints to std out.

method

libs.core.langchain_core.callbacks.stdout.StdOutCallbackHandler.on_agent_action(action:AgentAction, color:str | None=None, **kwargs:Any) -> Any

Run on agent action.

method

libs.core.langchain_core.callbacks.stdout.StdOutCallbackHandler.on_agent_finish(finish:AgentFinish, color:str | None=None, **kwargs:Any) -> None

Run on the agent end.

method

libs.core.langchain_core.callbacks.stdout.StdOutCallbackHandler.on_chain_end(outputs:dict[str, Any], **kwargs:Any) -> None

Print out that we finished a chain.

method

libs.core.langchain_core.callbacks.stdout.StdOutCallbackHandler.on_chain_start(serialized:dict[str, Any], inputs:dict[str, Any], **kwargs:Any) -> None

Print out that we are entering a chain.

method

libs.core.langchain_core.callbacks.stdout.StdOutCallbackHandler.on_text(text:str, color:str | None=None, end:str='', **kwargs:Any) -> None

Run when the agent ends.

classlibs.core.langchain_core.callbacks.streaming_stdout.StreamingStdOutCallbackHandler

Callback handler for streaming.

method

libs.core.langchain_core.callbacks.streaming_stdout.StreamingStdOutCallbackHandler.on_agent_action(action:AgentAction, **kwargs:Any) -> Any

Run on agent action.

method

libs.core.langchain_core.callbacks.streaming_stdout.StreamingStdOutCallbackHandler.on_agent_finish(finish:AgentFinish, **kwargs:Any) -> None

Run on the agent end.

method

libs.core.langchain_core.callbacks.streaming_stdout.StreamingStdOutCallbackHandler.on_chain_end(outputs:dict[str, Any], **kwargs:Any) -> None

Run when a chain ends running.

method

libs.core.langchain_core.callbacks.streaming_stdout.StreamingStdOutCallbackHandler.on_chain_error(error:BaseException, **kwargs:Any) -> None

Run when chain errors.

method

libs.core.langchain_core.callbacks.streaming_stdout.StreamingStdOutCallbackHandler.on_chain_start(serialized:dict[str, Any], inputs:dict[str, Any], **kwargs:Any) -> None

Run when a chain starts running.

method

libs.core.langchain_core.callbacks.streaming_stdout.StreamingStdOutCallbackHandler.on_chat_model_start(serialized:dict[str, Any], messages:list[list[BaseMessage]], **kwargs:Any) -> None

Run when LLM starts running.

method

libs.core.langchain_core.callbacks.streaming_stdout.StreamingStdOutCallbackHandler.on_llm_end(response:LLMResult, **kwargs:Any) -> None

Run when LLM ends running.

method

libs.core.langchain_core.callbacks.streaming_stdout.StreamingStdOutCallbackHandler.on_llm_error(error:BaseException, **kwargs:Any) -> None

Run when LLM errors.

method

libs.core.langchain_core.callbacks.streaming_stdout.StreamingStdOutCallbackHandler.on_llm_new_token(token:str | list[str | dict[str, Any]], **kwargs:Any) -> None

Run on new LLM token.

method

libs.core.langchain_core.callbacks.streaming_stdout.StreamingStdOutCallbackHandler.on_llm_start(serialized:dict[str, Any], prompts:list[str], **kwargs:Any) -> None

Run when LLM starts running.

method

libs.core.langchain_core.callbacks.streaming_stdout.StreamingStdOutCallbackHandler.on_text(text:str, **kwargs:Any) -> None

Run on an arbitrary text.

method

libs.core.langchain_core.callbacks.streaming_stdout.StreamingStdOutCallbackHandler.on_tool_end(output:Any, **kwargs:Any) -> None

Run when tool ends running.

method

libs.core.langchain_core.callbacks.streaming_stdout.StreamingStdOutCallbackHandler.on_tool_error(error:BaseException, **kwargs:Any) -> None

Run when tool errors.

method

libs.core.langchain_core.callbacks.streaming_stdout.StreamingStdOutCallbackHandler.on_tool_start(serialized:dict[str, Any], input_str:str, **kwargs:Any) -> None

Run when the tool starts running.

func

libs.core.langchain_core.callbacks.usage.get_usage_metadata_callback(name:str='usage_metadata_callback') -> Generator[UsageMetadataCallbackHandler, None, None]

Get usage metadata callback.

methodlibs.core.langchain_core.chat_history.InMemoryChatMessageHistory.aadd_messages(messages:Sequence[BaseMessage]) -> None

Async add messages to the store.

methodlibs.core.langchain_core.chat_history.InMemoryChatMessageHistory.aclear() -> None

Async clear all messages from the store.

methodlibs.core.langchain_core.chat_history.InMemoryChatMessageHistory.add_message(message:BaseMessage) -> None

Add a self-created message to the store.

methodlibs.core.langchain_core.chat_history.InMemoryChatMessageHistory.aget_messages() -> list[BaseMessage]

Async version of getting messages.

methodlibs.core.langchain_core.chat_history.InMemoryChatMessageHistory.clear() -> None

Clear all messages from the store.

classlibs.core.langchain_core.chat_loaders.BaseChatLoader

Base class for chat loaders.

methodlibs.core.langchain_core.chat_loaders.BaseChatLoader.lazy_load() -> Iterator[ChatSession]

Lazy load the chat sessions.

methodlibs.core.langchain_core.chat_loaders.BaseChatLoader.load() -> list[ChatSession]

Eagerly load the chat sessions into memory.

classlibs.core.langchain_core.chat_sessions.ChatSession

Chat Session.

classlibs.core.langchain_core.cross_encoders.BaseCrossEncoder

Interface for cross encoder models.

methodlibs.core.langchain_core.cross_encoders.BaseCrossEncoder.score(text_pairs:list[tuple[str, str]]) -> list[float]

Score pairs' similarity.

classlibs.core.langchain_core.document_loaders.base.BaseBlobParser

Abstract interface for blob parsers.

methodlibs.core.langchain_core.document_loaders.base.BaseBlobParser.lazy_parse(blob:Blob) -> Iterator[Document]

Lazy parsing interface.

classlibs.core.langchain_core.document_loaders.base.BaseLoader

Interface for document loader.

methodlibs.core.langchain_core.document_loaders.base.BaseLoader.alazy_load() -> AsyncIterator[Document]

A lazy loader for `Document`.

methodlibs.core.langchain_core.document_loaders.base.BaseLoader.aload() -> list[Document]

Load data into `Document` objects.

methodlibs.core.langchain_core.document_loaders.base.BaseLoader.lazy_load() -> Iterator[Document]

A lazy loader for `Document`.

methodlibs.core.langchain_core.document_loaders.base.BaseLoader.load() -> list[Document]

Load data into `Document` objects.

method

libs.core.langchain_core.document_loaders.base.BaseLoader.load_and_split(text_splitter:TextSplitter | None=None) -> list[Document]

Load `Document` and split into chunks.

methodlibs.core.langchain_core.documents.base.Blob.as_bytes() -> bytes

Read data as bytes.

methodlibs.core.langchain_core.documents.base.Blob.as_bytes_io() -> Generator[BytesIO | BufferedReader, None, None]

Read data as a byte stream.

methodlibs.core.langchain_core.documents.base.Blob.as_string() -> str

Read data as a string.

methodlibs.core.langchain_core.documents.base.Blob.check_blob_is_valid(values:dict[str, Any]) -> Any

Verify that either data or path is provided.

classlibs.core.langchain_core.documents.base.Document

Class for storing a piece of text and associated metadata.

methodlibs.core.langchain_core.documents.base.Document.get_lc_namespace() -> list[str]

Get the namespace of the LangChain object.

methodlibs.core.langchain_core.documents.base.Document.is_lc_serializable() -> bool

Return `True` as this class is serializable.

classlibs.core.langchain_core.documents.compressor.BaseDocumentCompressor

Base class for document compressors.

method

libs.core.langchain_core.documents.transformers.BaseDocumentTransformer.transform_documents(documents:Sequence[Document], **kwargs:Any) -> Sequence[Document]

Transform a list of documents.

classlibs.core.langchain_core.embeddings.embeddings.Embeddings

Interface for embedding models.

methodlibs.core.langchain_core.embeddings.embeddings.Embeddings.aembed_documents(texts:list[str]) -> list[list[float]]

Asynchronous Embed search docs.

methodlibs.core.langchain_core.embeddings.embeddings.Embeddings.aembed_query(text:str) -> list[float]

Asynchronous Embed query text.

methodlibs.core.langchain_core.embeddings.embeddings.Embeddings.embed_documents(texts:list[str]) -> list[list[float]]

Embed search docs.

methodlibs.core.langchain_core.embeddings.embeddings.Embeddings.embed_query(text:str) -> list[float]

Embed query text.

classlibs.core.langchain_core.embeddings.fake.FakeEmbeddings

Fake embedding model for unit testing purposes.

classlibs.core.langchain_core.example_selectors.length_based.LengthBasedExampleSelector

Select examples based on length.

method

libs.core.langchain_core.example_selectors.length_based.LengthBasedExampleSelector.aadd_example(example:dict[str, str]) -> None

Async add new example to list.

method

libs.core.langchain_core.example_selectors.length_based.LengthBasedExampleSelector.add_example(example:dict[str, str]) -> None

Add new example to list.

funclibs.core.langchain_core.example_selectors.semantic_similarity.sorted_values(values:dict[str, str]) -> list[str]

Return a list of values in dict sorted by key.

classlibs.core.langchain_core.exceptions.ErrorCode

Error codes.

classlibs.core.langchain_core.exceptions.LangChainException

General LangChain exception.

classlibs.core.langchain_core.exceptions.TracerException

Base class for exceptions in tracers module.

funclibs.core.langchain_core.globals.get_debug() -> bool

Get the value of the `debug` global setting.

funclibs.core.langchain_core.globals.get_llm_cache() -> Optional['BaseCache']

Get the value of the `llm_cache` global setting.

funclibs.core.langchain_core.globals.get_verbose() -> bool

Get the value of the `verbose` global setting.

funclibs.core.langchain_core.globals.set_debug(value:bool) -> None

Set a new value for the `debug` global setting.

funclibs.core.langchain_core.globals.set_llm_cache(value:Optional['BaseCache']) -> None

Set a new LLM cache, overwriting the previous value, if any.

funclibs.core.langchain_core.globals.set_verbose(value:bool) -> None

Set a new value for the `verbose` global setting.

classlibs.core.langchain_core.indexing.api.IndexingException

Raised when an indexing operation fails.

classlibs.core.langchain_core.indexing.base.DeleteResponse

A generic response for delete operation.

methodlibs.core.langchain_core.indexing.base.DocumentIndex.adelete(ids:list[str] | None=None, **kwargs:Any) -> DeleteResponse

Delete by IDs or other criteria.

methodlibs.core.langchain_core.indexing.base.DocumentIndex.aget(ids:Sequence[str], **kwargs:Any) -> list[Document]

Get documents by id.

methodlibs.core.langchain_core.indexing.base.DocumentIndex.aupsert(items:Sequence[Document], **kwargs:Any) -> UpsertResponse

Add or update documents in the `VectorStore`.

methodlibs.core.langchain_core.indexing.base.DocumentIndex.delete(ids:list[str] | None=None, **kwargs:Any) -> DeleteResponse

Delete by IDs or other criteria.

methodlibs.core.langchain_core.indexing.base.DocumentIndex.get(ids:Sequence[str], **kwargs:Any) -> list[Document]

Get documents by id.

methodlibs.core.langchain_core.indexing.base.DocumentIndex.upsert(items:Sequence[Document], **kwargs:Any) -> UpsertResponse

Upsert documents into the index.

classlibs.core.langchain_core.indexing.base.InMemoryRecordManager

An in-memory record manager for testing purposes.

methodlibs.core.langchain_core.indexing.base.InMemoryRecordManager.adelete_keys(keys:Sequence[str]) -> None

Async delete specified records from the database.

methodlibs.core.langchain_core.indexing.base.InMemoryRecordManager.delete_keys(keys:Sequence[str]) -> None

Delete specified records from the database.

methodlibs.core.langchain_core.indexing.base.InMemoryRecordManager.exists(keys:Sequence[str]) -> list[bool]

Check if the provided keys exist in the database.

method

libs.core.langchain_core.indexing.base.InMemoryRecordManager.update(keys:Sequence[str], *group_ids:Sequence[str | None] | None=None, *time_at_least:float | None=None) -> None

Upsert records into the database.

methodlibs.core.langchain_core.indexing.base.RecordManager.delete_keys(keys:Sequence[str]) -> None

Delete specified records from the database.

methodlibs.core.langchain_core.indexing.base.RecordManager.exists(keys:Sequence[str]) -> list[bool]

Check if the provided keys exist in the database.

method

libs.core.langchain_core.indexing.base.RecordManager.update(keys:Sequence[str], *group_ids:Sequence[str | None] | None=None, *time_at_least:float | None=None) -> None

Upsert records into the database.

classlibs.core.langchain_core.indexing.base.UpsertResponse

A generic response for upsert operations.

classlibs.core.langchain_core.indexing.in_memory.InMemoryDocumentIndex

In memory document index.

method

libs.core.langchain_core.indexing.in_memory.InMemoryDocumentIndex.delete(ids:list[str] | None=None, **kwargs:Any) -> DeleteResponse

Delete by IDs.

method

libs.core.langchain_core.indexing.in_memory.InMemoryDocumentIndex.upsert(items:Sequence[Document], **kwargs:Any) -> UpsertResponse

Upsert documents into the index.

func

libs.core.langchain_core.language_models._compat_bridge.amessage_to_events(msg:BaseMessage, *message_id:str | None=None) -> AsyncIterator[MessagesData]

Async variant of `message_to_events`.

classlibs.core.langchain_core.language_models.base.LangSmithParams

LangSmith parameters for tracing.

funclibs.core.langchain_core.language_models.base.get_tokenizer() -> Any

Get a GPT-2 tokenizer instance.

classlibs.core.langchain_core.language_models.chat_model_stream.SyncTextProjection

String-specialized sync projection.

methodlibs.core.langchain_core.language_models.chat_model_stream.SyncTextProjection.push(delta:str) -> None

Append a text delta.

classlibs.core.langchain_core.language_models.chat_models.BaseChatModel

Base class for chat models.

methodlibs.core.langchain_core.language_models.chat_models.BaseChatModel.OutputType() -> Any

Get the output type for this `Runnable`.

methodlibs.core.langchain_core.language_models.chat_models.BaseChatModel.asdict() -> builtins.dict[str, Any]

Return a dictionary representation of the chat model.

methodlibs.core.langchain_core.language_models.chat_models.BaseChatModel.dict(**_kwargs:Any) -> builtins.dict[str, Any]

DEPRECATED - use `asdict()` instead.

func

libs.core.langchain_core.language_models.chat_models.agenerate_from_stream(stream:AsyncIterator[ChatGenerationChunk]) -> ChatResult

Async generate from a stream.

func

libs.core.langchain_core.language_models.chat_models.generate_from_stream(stream:Iterator[ChatGenerationChunk]) -> ChatResult

Generate from a stream.

classlibs.core.langchain_core.language_models.fake.FakeListLLM

Fake LLM for testing purposes.

classlibs.core.langchain_core.language_models.fake.FakeListLLMError

Fake error for testing purposes.

classlibs.core.langchain_core.language_models.fake.FakeStreamingListLLM

Fake streaming list LLM for testing purposes.

classlibs.core.langchain_core.language_models.fake_chat_models.FakeChatModel

Fake Chat Model wrapper for testing purposes.

classlibs.core.langchain_core.language_models.fake_chat_models.FakeListChatModel

Fake chat model for testing purposes.

classlibs.core.langchain_core.language_models.fake_chat_models.FakeListChatModelError

Fake error for testing purposes.

classlibs.core.langchain_core.language_models.fake_chat_models.FakeMessagesListChatModel

Fake chat model for testing purposes.

classlibs.core.langchain_core.language_models.llms.BaseLLM

Base LLM abstract interface.

methodlibs.core.langchain_core.language_models.llms.BaseLLM.OutputType() -> type[str]

Get the output type for this `Runnable`.

methodlibs.core.langchain_core.language_models.llms.BaseLLM.asdict() -> builtins.dict[str, Any]

Return a dictionary representation of the LLM.

methodlibs.core.langchain_core.language_models.llms.BaseLLM.dict(**_kwargs:Any) -> builtins.dict[str, Any]

DEPRECATED - use `asdict()` instead.

methodlibs.core.langchain_core.language_models.llms.BaseLLM.save(file_path:Path | str) -> None

Save the LLM.

classlibs.core.langchain_core.language_models.llms.LLM

Simple interface for implementing a custom LLM.

funclibs.core.langchain_core.load.dump.default(obj:Any) -> Any

Return a default value for an object.

funclibs.core.langchain_core.load.dump.dumpd(obj:Any) -> Any

Return a dict representation of an object.

funclibs.core.langchain_core.load.dump.dumps(obj:Any, *pretty:bool=False, **kwargs:Any) -> str

Return a JSON string representation of an object.

classlibs.core.langchain_core.load.load.Reviver

Reviver for JSON objects.

classlibs.core.langchain_core.load.serializable.BaseSerialized

Base class for serialized objects.

classlibs.core.langchain_core.load.serializable.Serializable

Serializable base class.

methodlibs.core.langchain_core.load.serializable.Serializable.get_lc_namespace() -> list[str]

Get the namespace of the LangChain object.

methodlibs.core.langchain_core.load.serializable.Serializable.is_lc_serializable() -> bool

Is this class serializable?

methodlibs.core.langchain_core.load.serializable.Serializable.to_json() -> SerializedConstructor | SerializedNotImplemented

Serialize the object to JSON.

methodlibs.core.langchain_core.load.serializable.Serializable.to_json_not_implemented() -> SerializedNotImplemented

Serialize a "not implemented" object.

classlibs.core.langchain_core.load.serializable.SerializedConstructor

Serialized constructor.

classlibs.core.langchain_core.load.serializable.SerializedNotImplemented

Serialized not implemented.

classlibs.core.langchain_core.load.serializable.SerializedSecret

Serialized secret.

funclibs.core.langchain_core.load.serializable.to_json_not_implemented(obj:object) -> SerializedNotImplemented

Serialize a "not implemented" object.

funclibs.core.langchain_core.load.serializable.try_neq_default(value:Any, key:str, model:BaseModel) -> bool

Try to determine if a value is different from the default.

classlibs.core.langchain_core.messages.ai.AIMessage

Message from an AI.

methodlibs.core.langchain_core.messages.ai.AIMessage.lc_attributes() -> dict[str, Any]

Attributes to be serialized.

methodlibs.core.langchain_core.messages.ai.AIMessage.pretty_repr(html:bool=False) -> str

Return a pretty representation of the message for display.

classlibs.core.langchain_core.messages.ai.AIMessageChunk

Message chunk from an AI (yielded when streaming).

methodlibs.core.langchain_core.messages.ai.AIMessageChunk.init_server_tool_calls() -> Self

Initialize server tool calls.

methodlibs.core.langchain_core.messages.ai.AIMessageChunk.init_tool_calls() -> Self

Initialize tool calls from tool call chunks.

classlibs.core.langchain_core.messages.ai.InputTokenDetails

Breakdown of input token counts.

classlibs.core.langchain_core.messages.ai.OutputTokenDetails

Breakdown of output token counts.

classlibs.core.langchain_core.messages.ai.UsageMetadata

Usage metadata for a message, such as token counts.

func

libs.core.langchain_core.messages.ai.add_ai_message_chunks(left:AIMessageChunk, *others:AIMessageChunk) -> AIMessageChunk

Add multiple `AIMessageChunk`s together.

funclibs.core.langchain_core.messages.ai.add_usage(left:UsageMetadata | None, right:UsageMetadata | None) -> UsageMetadata

Recursively add two UsageMetadata objects.

func

libs.core.langchain_core.messages.ai.subtract_usage(left:UsageMetadata | None, right:UsageMetadata | None) -> UsageMetadata

Recursively subtract two `UsageMetadata` objects.

classlibs.core.langchain_core.messages.base.BaseMessage

Base abstract message class.

methodlibs.core.langchain_core.messages.base.BaseMessage.get_lc_namespace() -> list[str]

Get the namespace of the LangChain object.

methodlibs.core.langchain_core.messages.base.BaseMessage.is_lc_serializable() -> bool

`BaseMessage` is serializable.

methodlibs.core.langchain_core.messages.base.BaseMessage.pretty_print() -> None

Print a pretty representation of the message.

methodlibs.core.langchain_core.messages.base.BaseMessage.pretty_repr(html:bool=False) -> str

Get a pretty representation of the message.

funclibs.core.langchain_core.messages.base.get_msg_title_repr(title:str, *bold:bool=False) -> str

Get a title representation for a message.

func

libs.core.langchain_core.messages.base.merge_content(first_content:str | list[str | dict[Any, Any]], *contents:str | list[str | dict[Any, Any]]) -> str | list[str | dict[Any, Any]]

Merge multiple message contents.

funclibs.core.langchain_core.messages.base.message_to_dict(message:BaseMessage) -> dict[str, Any]

Convert a Message to a dictionary.

classlibs.core.langchain_core.messages.chat.ChatMessage

Message that can be assigned an arbitrary speaker (i.e.

classlibs.core.langchain_core.messages.chat.ChatMessageChunk

Chat Message chunk.

classlibs.core.langchain_core.messages.content.AudioContentBlock

Audio data.

classlibs.core.langchain_core.messages.content.Citation

Annotation for citing data from a document.

classlibs.core.langchain_core.messages.content.ImageContentBlock

Image data.

classlibs.core.langchain_core.messages.content.InvalidToolCall

Allowance for errors made by LLM.

classlibs.core.langchain_core.messages.content.NonStandardAnnotation

Provider-specific annotation format.

classlibs.core.langchain_core.messages.content.NonStandardContentBlock

Provider-specific content data.

classlibs.core.langchain_core.messages.content.ReasoningContentBlock

Reasoning output from a LLM.

classlibs.core.langchain_core.messages.content.ServerToolCall

Tool call that is executed server-side.

classlibs.core.langchain_core.messages.content.ServerToolResult

Result of a server-side tool call.

classlibs.core.langchain_core.messages.content.TextContentBlock

Text output from a LLM.

classlibs.core.langchain_core.messages.content.ToolCall

Represents an AI's request to call a tool.

classlibs.core.langchain_core.messages.content.ToolCallChunk

A chunk of a tool call (yielded when streaming).

classlibs.core.langchain_core.messages.content.VideoContentBlock

Video data.

func

libs.core.langchain_core.messages.content.create_citation(*url:str | None=None, *title:str | None=None, *start_index:int | None=None, *end_index:int | None=None, *cited_text:str | None=None, *id:str | None=None, **kwargs:Any) -> Citation

Create a `Citation`.

func

libs.core.langchain_core.messages.content.create_non_standard_block(value:dict[str, Any], *id:str | None=None, *index:int | str | None=None) -> NonStandardContentBlock

Create a `NonStandardContentBlock`.

func

libs.core.langchain_core.messages.content.create_reasoning_block(reasoning:str | None=None, id:str | None=None, index:int | str | None=None, **kwargs:Any) -> ReasoningContentBlock

Create a `ReasoningContentBlock`.

func

libs.core.langchain_core.messages.content.create_text_block(text:str, *id:str | None=None, *annotations:list[Annotation] | None=None, *index:int | str | None=None, **kwargs:Any) -> TextContentBlock

Create a `TextContentBlock`.

func

libs.core.langchain_core.messages.content.create_tool_call(name:str, args:dict[str, Any], *id:str | None=None, *index:int | str | None=None, **kwargs:Any) -> ToolCall

Create a `ToolCall`.

classlibs.core.langchain_core.messages.function.FunctionMessageChunk

Function Message chunk.

classlibs.core.langchain_core.messages.human.HumanMessage

Message from the user.

classlibs.core.langchain_core.messages.human.HumanMessageChunk

Human Message chunk.

classlibs.core.langchain_core.messages.modifier.RemoveMessage

Message responsible for deleting other messages.

classlibs.core.langchain_core.messages.system.SystemMessage

Message for priming AI behavior.

classlibs.core.langchain_core.messages.system.SystemMessageChunk

System Message chunk.

classlibs.core.langchain_core.messages.tool.ToolCall

Represents an AI's request to call a tool.

classlibs.core.langchain_core.messages.tool.ToolCallChunk

A chunk of a tool call (yielded when streaming).

classlibs.core.langchain_core.messages.tool.ToolMessageChunk

Tool Message chunk.

classlibs.core.langchain_core.messages.tool.ToolOutputMixin

Mixin for objects that tools can return directly.

func

libs.core.langchain_core.messages.tool.default_tool_chunk_parser(raw_tool_calls:list[dict[str, Any]]) -> list[ToolCallChunk]

Best-effort parsing of tool chunks.

func

libs.core.langchain_core.messages.tool.default_tool_parser(raw_tool_calls:list[dict[str, Any]]) -> tuple[list[ToolCall], list[InvalidToolCall]]

Best-effort parsing of tools.

func

libs.core.langchain_core.messages.tool.invalid_tool_call(*name:str | None=None, *args:str | None=None, *id:str | None=None, *error:str | None=None) -> InvalidToolCall

Create an invalid tool call.

funclibs.core.langchain_core.messages.tool.tool_call(*name:str, *args:dict[str, Any], *id:str | None) -> ToolCall

Create a tool call.

func

libs.core.langchain_core.messages.tool.tool_call_chunk(*name:str | None=None, *args:str | None=None, *id:str | None=None, *index:int | None=None) -> ToolCallChunk

Create a tool call chunk.

funclibs.core.langchain_core.messages.utils.message_chunk_to_message(chunk:BaseMessage) -> BaseMessage

Convert a message chunk to a `Message`.

classlibs.core.langchain_core.output_parsers.base.BaseGenerationOutputParser

Base class to parse the output of an LLM call.

methodlibs.core.langchain_core.output_parsers.base.BaseGenerationOutputParser.InputType() -> Any

Return the input type for the parser.

methodlibs.core.langchain_core.output_parsers.base.BaseGenerationOutputParser.OutputType() -> type[T]

Return the output type for the parser.

classlibs.core.langchain_core.output_parsers.base.BaseOutputParser

Base class to parse the output of an LLM call.

methodlibs.core.langchain_core.output_parsers.base.BaseOutputParser.InputType() -> Any

Return the input type for the parser.

methodlibs.core.langchain_core.output_parsers.base.BaseOutputParser.OutputType() -> type[T]

Return the output type for the parser.

methodlibs.core.langchain_core.output_parsers.base.BaseOutputParser.asdict(**kwargs:Any) -> builtins.dict[str, Any]

Return a dictionary representation of the output parser.

methodlibs.core.langchain_core.output_parsers.base.BaseOutputParser.dict(**kwargs:Any) -> builtins.dict[str, Any]

DEPRECATED - use `asdict()` instead.

methodlibs.core.langchain_core.output_parsers.base.BaseOutputParser.parse(text:str) -> T

Parse a single string model output into some structure.

classlibs.core.langchain_core.output_parsers.json.JsonOutputParser

Parse the output of an LLM call to a JSON object.

methodlibs.core.langchain_core.output_parsers.json.JsonOutputParser.parse(text:str) -> Any

Parse the output of an LLM call to a JSON object.

classlibs.core.langchain_core.output_parsers.list.ListOutputParser

Parse the output of a model to a list.

methodlibs.core.langchain_core.output_parsers.list.ListOutputParser.parse(text:str) -> list[str]

Parse the output of an LLM call.

methodlibs.core.langchain_core.output_parsers.list.ListOutputParser.parse_iter(text:str) -> Iterator[re.Match[str]]

Parse the output of an LLM call.

classlibs.core.langchain_core.output_parsers.list.MarkdownListOutputParser

Parse a Markdown list.

methodlibs.core.langchain_core.output_parsers.list.MarkdownListOutputParser.parse(text:str) -> list[str]

Parse the output of an LLM call.

classlibs.core.langchain_core.output_parsers.list.NumberedListOutputParser

Parse a numbered list.

methodlibs.core.langchain_core.output_parsers.list.NumberedListOutputParser.parse(text:str) -> list[str]

Parse the output of an LLM call.

funclibs.core.langchain_core.output_parsers.list.droplastn(iter:Iterator[T], n:int) -> Iterator[T]

Drop the last `n` elements of an iterator.

classlibs.core.langchain_core.output_parsers.openai_functions.JsonOutputFunctionsParser

Parse an output as the JSON object.

methodlibs.core.langchain_core.output_parsers.openai_functions.JsonOutputFunctionsParser.parse(text:str) -> Any

Parse the output of an LLM call to a JSON object.

classlibs.core.langchain_core.output_parsers.openai_functions.OutputFunctionsParser

Parse an output that is one of sets of values.

classlibs.core.langchain_core.output_parsers.openai_functions.PydanticOutputFunctionsParser

Parse an output as a Pydantic object.

method

libs.core.langchain_core.output_parsers.openai_functions.PydanticOutputFunctionsParser.validate_schema(values:dict[str, Any]) -> Any

Validate the Pydantic schema.

classlibs.core.langchain_core.output_parsers.openai_tools.JsonOutputKeyToolsParser

Parse tools from OpenAI response.

classlibs.core.langchain_core.output_parsers.openai_tools.JsonOutputToolsParser

Parse tools from OpenAI response.

classlibs.core.langchain_core.output_parsers.openai_tools.PydanticToolsParser

Parse tools from OpenAI response.

func

libs.core.langchain_core.output_parsers.openai_tools.parse_tool_call(raw_tool_call:dict[str, Any], *partial:bool=False, *strict:bool=False, *return_id:bool=True) -> dict[str, Any] | None

Parse a single tool call.

func

libs.core.langchain_core.output_parsers.openai_tools.parse_tool_calls(raw_tool_calls:list[dict[str, Any]], *partial:bool=False, *strict:bool=False, *return_id:bool=True) -> list[dict[str, Any]]

Parse a list of tool calls.

classlibs.core.langchain_core.output_parsers.pydantic.PydanticOutputParser

Parse an output using a Pydantic model.

methodlibs.core.langchain_core.output_parsers.pydantic.PydanticOutputParser.OutputType() -> type[TBaseModel]

Return the Pydantic model.

methodlibs.core.langchain_core.output_parsers.pydantic.PydanticOutputParser.parse(text:str) -> TBaseModel

Parse the output of an LLM call to a Pydantic object.

classlibs.core.langchain_core.output_parsers.string.StrOutputParser

Extract text content from model outputs as a string.

methodlibs.core.langchain_core.output_parsers.string.StrOutputParser.is_lc_serializable() -> bool

`StrOutputParser` is serializable.

methodlibs.core.langchain_core.output_parsers.string.StrOutputParser.parse(text:str) -> str

Returns the input text with no changes.

classlibs.core.langchain_core.output_parsers.xml.XMLOutputParser

Parse an output using xml format.

methodlibs.core.langchain_core.output_parsers.xml.XMLOutputParser.parse(text:str) -> dict[str, str | list[Any]]

Parse the output of an LLM call.

funclibs.core.langchain_core.output_parsers.xml.nested_element(path:list[str], elem:ET.Element) -> Any

Get nested element from path.

classlibs.core.langchain_core.outputs.chat_generation.ChatGeneration

A single chat generation output.

classlibs.core.langchain_core.outputs.chat_generation.ChatGenerationChunk

`ChatGeneration` chunk.

classlibs.core.langchain_core.outputs.generation.Generation

A single text generation output.

methodlibs.core.langchain_core.outputs.generation.Generation.get_lc_namespace() -> list[str]

Get the namespace of the LangChain object.

methodlibs.core.langchain_core.outputs.generation.Generation.is_lc_serializable() -> bool

Return `True` as this class is serializable.

classlibs.core.langchain_core.outputs.llm_result.LLMResult

A container for results of an LLM call.

methodlibs.core.langchain_core.outputs.llm_result.LLMResult.flatten() -> list[LLMResult]

Flatten generations into a single list.

classlibs.core.langchain_core.prompt_values.ChatPromptValue

Chat prompt value.

methodlibs.core.langchain_core.prompt_values.ChatPromptValue.get_lc_namespace() -> list[str]

Get the namespace of the LangChain object.

methodlibs.core.langchain_core.prompt_values.ChatPromptValue.to_messages() -> list[BaseMessage]

Return prompt as a list of messages.

methodlibs.core.langchain_core.prompt_values.ChatPromptValue.to_string() -> str

Return prompt as string.

classlibs.core.langchain_core.prompt_values.ImagePromptValue

Image prompt value.

methodlibs.core.langchain_core.prompt_values.ImagePromptValue.to_messages() -> list[BaseMessage]

Return prompt (image URL) as messages.

methodlibs.core.langchain_core.prompt_values.ImagePromptValue.to_string() -> str

Return prompt (image URL) as string.

classlibs.core.langchain_core.prompt_values.ImageURL

Image URL for multimodal model inputs (OpenAI format).

classlibs.core.langchain_core.prompt_values.PromptValue

Base abstract class for inputs to any language model.

methodlibs.core.langchain_core.prompt_values.PromptValue.get_lc_namespace() -> list[str]

Get the namespace of the LangChain object.

methodlibs.core.langchain_core.prompt_values.PromptValue.is_lc_serializable() -> bool

Return `True` as this class is serializable.

methodlibs.core.langchain_core.prompt_values.PromptValue.to_messages() -> list[BaseMessage]

Return prompt as a list of messages.

methodlibs.core.langchain_core.prompt_values.PromptValue.to_string() -> str

Return prompt value as string.

classlibs.core.langchain_core.prompt_values.StringPromptValue

String prompt value.

methodlibs.core.langchain_core.prompt_values.StringPromptValue.get_lc_namespace() -> list[str]

Get the namespace of the LangChain object.

methodlibs.core.langchain_core.prompt_values.StringPromptValue.to_messages() -> list[BaseMessage]

Return prompt as messages.

methodlibs.core.langchain_core.prompt_values.StringPromptValue.to_string() -> str

Return prompt as string.

classlibs.core.langchain_core.prompts.chat.AIMessagePromptTemplate

AI message prompt template.

classlibs.core.langchain_core.prompts.chat.BaseChatPromptTemplate

Base class for chat prompt templates.

methodlibs.core.langchain_core.prompts.chat.BaseChatPromptTemplate.aformat(**kwargs:Any) -> str

Async format the chat template into a string.

methodlibs.core.langchain_core.prompts.chat.BaseChatPromptTemplate.aformat_messages(**kwargs:Any) -> list[BaseMessage]

Async format kwargs into a list of messages.

methodlibs.core.langchain_core.prompts.chat.BaseChatPromptTemplate.aformat_prompt(**kwargs:Any) -> ChatPromptValue

Async format prompt.

methodlibs.core.langchain_core.prompts.chat.BaseChatPromptTemplate.format(**kwargs:Any) -> str

Format the chat template into a string.

methodlibs.core.langchain_core.prompts.chat.BaseChatPromptTemplate.format_messages(**kwargs:Any) -> list[BaseMessage]

Format kwargs into a list of messages.

methodlibs.core.langchain_core.prompts.chat.BaseChatPromptTemplate.format_prompt(**kwargs:Any) -> ChatPromptValue

Format prompt.

methodlibs.core.langchain_core.prompts.chat.BaseChatPromptTemplate.pretty_print() -> None

Print a human-readable representation.

methodlibs.core.langchain_core.prompts.chat.BaseChatPromptTemplate.pretty_repr(html:bool=False) -> str

Human-readable representation.

classlibs.core.langchain_core.prompts.chat.ChatMessagePromptTemplate

Chat message prompt template.

methodlibs.core.langchain_core.prompts.chat.ChatMessagePromptTemplate.aformat(**kwargs:Any) -> BaseMessage

Async format the prompt template.

methodlibs.core.langchain_core.prompts.chat.ChatMessagePromptTemplate.format(**kwargs:Any) -> BaseMessage

Format the prompt template.

About this data

These signatures were extracted from the public source of langchain-ai/langchain using Python's ast module. Argument names, default values, type annotations and return types are taken verbatim from the code. Implementation bodies are never stored. See how it works for details.

Back to all 805 libraries