langchain.chains.conversational_retrieval.base.ConversationalRetrievalChain

class langchain.chains.conversational_retrieval.base.ConversationalRetrievalChain[source]

Bases: BaseConversationalRetrievalChain

Chain for having a conversation based on retrieved documents.

This chain takes in chat history (a list of messages) and new questions, and then returns an answer to that question. The algorithm for this chain consists of three parts:

1. Use the chat history and the new question to create a “standalone question”. This is done so that this question can be passed into the retrieval step to fetch relevant documents. If only the new question was passed in, then relevant context may be lacking. If the whole conversation was passed into retrieval, there may be unnecessary information there that would distract from retrieval.

2. This new question is passed to the retriever and relevant documents are returned.

3. The retrieved documents are passed to an LLM along with either the new question (default behavior) or the original question and chat history to generate a final response.

Example

from langchain.chains import (
    StuffDocumentsChain, LLMChain, ConversationalRetrievalChain
)
from langchain_core.prompts import PromptTemplate
from langchain_community.llms import OpenAI

combine_docs_chain = StuffDocumentsChain(...)
vectorstore = ...
retriever = vectorstore.as_retriever()

# This controls how the standalone question is generated.
# Should take `chat_history` and `question` as input variables.
template = (
    "Combine the chat history and follow up question into "
    "a standalone question. Chat History: {chat_history}"
    "Follow up question: {question}"
)
prompt = PromptTemplate.from_template(template)
llm = OpenAI()
question_generator_chain = LLMChain(llm=llm, prompt=prompt)
chain = ConversationalRetrievalChain(
    combine_docs_chain=combine_docs_chain,
    retriever=retriever,
    question_generator=question_generator_chain,
)

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

param callback_manager: Optional[BaseCallbackManager] = None

[DEPRECATED] Use callbacks instead.

param callbacks: Callbacks = None

Optional list of callback handlers (or callback manager). Defaults to None. Callback handlers are called throughout the lifecycle of a call to a chain, starting with on_chain_start, ending with on_chain_end or on_chain_error. Each custom chain can optionally call additional callback methods, see Callback docs for full details.

param combine_docs_chain: BaseCombineDocumentsChain [Required]

The chain used to combine any retrieved documents.

param get_chat_history: Optional[Callable[[List[CHAT_TURN_TYPE]], str]] = None

An optional function to get a string of the chat history. If None is provided, will use a default.

param max_tokens_limit: Optional[int] = None

If set, enforces that the documents returned are less than this limit. This is only enforced if combine_docs_chain is of type StuffDocumentsChain.

param memory: Optional[BaseMemory] = None

Optional memory object. Defaults to None. Memory is a class that gets called at the start and at the end of every chain. At the start, memory loads variables and passes them along in the chain. At the end, it saves any returned variables. There are many different types of memory - please see memory docs for the full catalog.

param metadata: Optional[Dict[str, Any]] = None

Optional metadata associated with the chain. Defaults to None. This metadata will be associated with each call to this chain, and passed as arguments to the handlers defined in callbacks. You can use these to eg identify a specific instance of a chain with its use case.

param output_key: str = 'answer'

The output key to return the final answer of this chain in.

param question_generator: LLMChain [Required]

The chain used to generate a new question for the sake of retrieval. This chain will take in the current question (with variable question) and any chat history (with variable chat_history) and will produce a new standalone question to be used later on.

param rephrase_question: bool = True

Whether or not to pass the new generated question to the combine_docs_chain. If True, will pass the new generated question along. If False, will only use the new generated question for retrieval and pass the original question along to the combine_docs_chain.

param response_if_no_docs_found: Optional[str] = None

If specified, the chain will return a fixed response if no docs are found for the question.

param retriever: BaseRetriever [Required]

Retriever to use to fetch documents.

param return_generated_question: bool = False

Return the generated question as part of the final result.

param return_source_documents: bool = False

Return the retrieved source documents as part of the final result.

param tags: Optional[List[str]] = None

Optional list of tags associated with the chain. Defaults to None. These tags will be associated with each call to this chain, and passed as arguments to the handlers defined in callbacks. You can use these to eg identify a specific instance of a chain with its use case.

param verbose: bool [Optional]

Whether or not run in verbose mode. In verbose mode, some intermediate logs will be printed to the console. Defaults to the global verbose value, accessible via langchain.globals.get_verbose().

__call__(inputs: Union[Dict[str, Any], Any], return_only_outputs: bool = False, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, *, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, run_name: Optional[str] = None, include_run_info: bool = False) Dict[str, Any]

[Deprecated] Execute the chain.

Parameters
  • inputs (Union[Dict[str, Any], Any]) – Dictionary of inputs, or single input if chain expects only one param. Should contain all inputs specified in Chain.input_keys except for inputs that will be set by the chain’s memory.

  • return_only_outputs (bool) – Whether to return only outputs in the response. If True, only new keys generated by this chain will be returned. If False, both input keys and new keys generated by this chain will be returned. Defaults to False.

  • callbacks (Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]) – Callbacks to use for this chain run. These will be called in addition to callbacks passed to the chain during construction, but only these runtime callbacks will propagate to calls to other objects.

  • tags (Optional[List[str]]) – List of string tags to pass to all callbacks. These will be passed in addition to tags passed to the chain during construction, but only these runtime tags will propagate to calls to other objects.

  • metadata (Optional[Dict[str, Any]]) – Optional metadata associated with the chain. Defaults to None

  • include_run_info (bool) – Whether to include run info in the response. Defaults to False.

  • run_name (Optional[str]) –

Returns

A dict of named outputs. Should contain all outputs specified in

Chain.output_keys.

Return type

Dict[str, Any]

Notes

Deprecated since version 0.1.0: Use invoke instead.

async abatch(inputs: List[Input], config: Optional[Union[RunnableConfig, List[RunnableConfig]]] = None, *, return_exceptions: bool = False, **kwargs: Optional[Any]) List[Output]

Default implementation runs ainvoke in parallel using asyncio.gather.

The default implementation of batch works well for IO bound runnables.

Subclasses should override this method if they can batch more efficiently; e.g., if the underlying runnable uses an API which supports a batch mode.

Parameters
  • inputs (List[Input]) –

  • config (Optional[Union[RunnableConfig, List[RunnableConfig]]]) –

  • return_exceptions (bool) –

  • kwargs (Optional[Any]) –

Return type

List[Output]

async acall(inputs: Union[Dict[str, Any], Any], return_only_outputs: bool = False, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, *, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, run_name: Optional[str] = None, include_run_info: bool = False) Dict[str, Any]

[Deprecated] Asynchronously execute the chain.

Parameters
  • inputs (Union[Dict[str, Any], Any]) – Dictionary of inputs, or single input if chain expects only one param. Should contain all inputs specified in Chain.input_keys except for inputs that will be set by the chain’s memory.

  • return_only_outputs (bool) – Whether to return only outputs in the response. If True, only new keys generated by this chain will be returned. If False, both input keys and new keys generated by this chain will be returned. Defaults to False.

  • callbacks (Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]) – Callbacks to use for this chain run. These will be called in addition to callbacks passed to the chain during construction, but only these runtime callbacks will propagate to calls to other objects.

  • tags (Optional[List[str]]) – List of string tags to pass to all callbacks. These will be passed in addition to tags passed to the chain during construction, but only these runtime tags will propagate to calls to other objects.

  • metadata (Optional[Dict[str, Any]]) – Optional metadata associated with the chain. Defaults to None

  • include_run_info (bool) – Whether to include run info in the response. Defaults to False.

  • run_name (Optional[str]) –

Returns

A dict of named outputs. Should contain all outputs specified in

Chain.output_keys.

Return type

Dict[str, Any]

Notes

Deprecated since version 0.1.0: Use ainvoke instead.

async ainvoke(input: Dict[str, Any], config: Optional[RunnableConfig] = None, **kwargs: Any) Dict[str, Any]

Default implementation of ainvoke, calls invoke from a thread.

The default implementation allows usage of async code even if the runnable did not implement a native async version of invoke.

Subclasses should override this method if they can run asynchronously.

Parameters
  • input (Dict[str, Any]) –

  • config (Optional[RunnableConfig]) –

  • kwargs (Any) –

Return type

Dict[str, Any]

apply(input_list: List[Dict[str, Any]], callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None) List[Dict[str, str]]

[Deprecated] Call the chain on all inputs in the list.

Notes

Deprecated since version 0.1.0: Use batch instead.

Parameters
Return type

List[Dict[str, str]]

async arun(*args: Any, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, **kwargs: Any) Any

[Deprecated] Convenience method for executing chain.

The main difference between this method and Chain.__call__ is that this method expects inputs to be passed directly in as positional arguments or keyword arguments, whereas Chain.__call__ expects a single input dictionary with all the inputs

Parameters
  • *args (Any) – If the chain expects a single input, it can be passed in as the sole positional argument.

  • callbacks (Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]) – Callbacks to use for this chain run. These will be called in addition to callbacks passed to the chain during construction, but only these runtime callbacks will propagate to calls to other objects.

  • tags (Optional[List[str]]) – List of string tags to pass to all callbacks. These will be passed in addition to tags passed to the chain during construction, but only these runtime tags will propagate to calls to other objects.

  • **kwargs (Any) – If the chain expects multiple inputs, they can be passed in directly as keyword arguments.

  • metadata (Optional[Dict[str, Any]]) –

  • **kwargs

Returns

The chain output.

Return type

Any

Example

# Suppose we have a single-input chain that takes a 'question' string:
await chain.arun("What's the temperature in Boise, Idaho?")
# -> "The temperature in Boise is..."

# Suppose we have a multi-input chain that takes a 'question' string
# and 'context' string:
question = "What's the temperature in Boise, Idaho?"
context = "Weather report for Boise, Idaho on 07/03/23..."
await chain.arun(question=question, context=context)
# -> "The temperature in Boise is..."

Notes

Deprecated since version 0.1.0: Use ainvoke instead.

assign(**kwargs: Union[Runnable[Dict[str, Any], Any], Callable[[Dict[str, Any]], Any], Mapping[str, Union[Runnable[Dict[str, Any], Any], Callable[[Dict[str, Any]], Any]]]]) RunnableSerializable[Any, Any]

Assigns new fields to the dict output of this runnable. Returns a new runnable.

Parameters

kwargs (Union[Runnable[Dict[str, Any], Any], Callable[[Dict[str, Any]], Any], Mapping[str, Union[Runnable[Dict[str, Any], Any], Callable[[Dict[str, Any]], Any]]]]) –

Return type

RunnableSerializable[Any, Any]

async astream(input: Input, config: Optional[RunnableConfig] = None, **kwargs: Optional[Any]) AsyncIterator[Output]

Default implementation of astream, which calls ainvoke. Subclasses should override this method if they support streaming output.

Parameters
  • input (Input) –

  • config (Optional[RunnableConfig]) –

  • kwargs (Optional[Any]) –

Return type

AsyncIterator[Output]

astream_events(input: Any, config: Optional[RunnableConfig] = None, *, version: Literal['v1'], include_names: Optional[Sequence[str]] = None, include_types: Optional[Sequence[str]] = None, include_tags: Optional[Sequence[str]] = None, exclude_names: Optional[Sequence[str]] = None, exclude_types: Optional[Sequence[str]] = None, exclude_tags: Optional[Sequence[str]] = None, **kwargs: Any) AsyncIterator[StreamEvent]

[Beta] Generate a stream of events.

Use to create an iterator over StreamEvents that provide real-time information about the progress of the runnable, including StreamEvents from intermediate results.

A StreamEvent is a dictionary with the following schema:

  • event: str - Event names are of the

    format: on_[runnable_type]_(start|stream|end).

  • name: str - The name of the runnable that generated the event.

  • run_id: str - randomly generated ID associated with the given execution of

    the runnable that emitted the event. A child runnable that gets invoked as part of the execution of a parent runnable is assigned its own unique ID.

  • tags: Optional[List[str]] - The tags of the runnable that generated

    the event.

  • metadata: Optional[Dict[str, Any]] - The metadata of the runnable

    that generated the event.

  • data: Dict[str, Any]

Below is a table that illustrates some evens that might be emitted by various chains. Metadata fields have been omitted from the table for brevity. Chain definitions have been included after the table.

event

name

chunk

input

output

on_chat_model_start

[model name]

{“messages”: [[SystemMessage, HumanMessage]]}

on_chat_model_stream

[model name]

AIMessageChunk(content=”hello”)

on_chat_model_end

[model name]

{“messages”: [[SystemMessage, HumanMessage]]}

{“generations”: […], “llm_output”: None, …}

on_llm_start

[model name]

{‘input’: ‘hello’}

on_llm_stream

[model name]

‘Hello’

on_llm_end

[model name]

‘Hello human!’

on_chain_start

format_docs

on_chain_stream

format_docs

“hello world!, goodbye world!”

on_chain_end

format_docs

[Document(…)]

“hello world!, goodbye world!”

on_tool_start

some_tool

{“x”: 1, “y”: “2”}

on_tool_stream

some_tool

{“x”: 1, “y”: “2”}

on_tool_end

some_tool

{“x”: 1, “y”: “2”}

on_retriever_start

[retriever name]

{“query”: “hello”}

on_retriever_chunk

[retriever name]

{documents: […]}

on_retriever_end

[retriever name]

{“query”: “hello”}

{documents: […]}

on_prompt_start

[template_name]

{“question”: “hello”}

on_prompt_end

[template_name]

{“question”: “hello”}

ChatPromptValue(messages: [SystemMessage, …])

Here are declarations associated with the events shown above:

format_docs:

def format_docs(docs: List[Document]) -> str:
    '''Format the docs.'''
    return ", ".join([doc.page_content for doc in docs])

format_docs = RunnableLambda(format_docs)

some_tool:

@tool
def some_tool(x: int, y: str) -> dict:
    '''Some_tool.'''
    return {"x": x, "y": y}

prompt:

template = ChatPromptTemplate.from_messages(
    [("system", "You are Cat Agent 007"), ("human", "{question}")]
).with_config({"run_name": "my_template", "tags": ["my_template"]})

Example:

from langchain_core.runnables import RunnableLambda

async def reverse(s: str) -> str:
    return s[::-1]

chain = RunnableLambda(func=reverse)

events = [
    event async for event in chain.astream_events("hello", version="v1")
]

# will produce the following events (run_id has been omitted for brevity):
[
    {
        "data": {"input": "hello"},
        "event": "on_chain_start",
        "metadata": {},
        "name": "reverse",
        "tags": [],
    },
    {
        "data": {"chunk": "olleh"},
        "event": "on_chain_stream",
        "metadata": {},
        "name": "reverse",
        "tags": [],
    },
    {
        "data": {"output": "olleh"},
        "event": "on_chain_end",
        "metadata": {},
        "name": "reverse",
        "tags": [],
    },
]
Parameters
  • input (Any) – The input to the runnable.

  • config (Optional[RunnableConfig]) – The config to use for the runnable.

  • version (Literal['v1']) – The version of the schema to use. Currently only version 1 is available. No default will be assigned until the API is stabilized.

  • include_names (Optional[Sequence[str]]) – Only include events from runnables with matching names.

  • include_types (Optional[Sequence[str]]) – Only include events from runnables with matching types.

  • include_tags (Optional[Sequence[str]]) – Only include events from runnables with matching tags.

  • exclude_names (Optional[Sequence[str]]) – Exclude events from runnables with matching names.

  • exclude_types (Optional[Sequence[str]]) – Exclude events from runnables with matching types.

  • exclude_tags (Optional[Sequence[str]]) – Exclude events from runnables with matching tags.

  • kwargs (Any) – Additional keyword arguments to pass to the runnable. These will be passed to astream_log as this implementation of astream_events is built on top of astream_log.

Returns

An async stream of StreamEvents.

Return type

AsyncIterator[StreamEvent]

Notes

async astream_log(input: Any, config: Optional[RunnableConfig] = None, *, diff: bool = True, with_streamed_output_list: bool = True, include_names: Optional[Sequence[str]] = None, include_types: Optional[Sequence[str]] = None, include_tags: Optional[Sequence[str]] = None, exclude_names: Optional[Sequence[str]] = None, exclude_types: Optional[Sequence[str]] = None, exclude_tags: Optional[Sequence[str]] = None, **kwargs: Any) Union[AsyncIterator[RunLogPatch], AsyncIterator[RunLog]]

Stream all output from a runnable, as reported to the callback system. This includes all inner runs of LLMs, Retrievers, Tools, etc.

Output is streamed as Log objects, which include a list of jsonpatch ops that describe how the state of the run has changed in each step, and the final state of the run.

The jsonpatch ops can be applied in order to construct state.

Parameters
  • input (Any) – The input to the runnable.

  • config (Optional[RunnableConfig]) – The config to use for the runnable.

  • diff (bool) – Whether to yield diffs between each step, or the current state.

  • with_streamed_output_list (bool) – Whether to yield the streamed_output list.

  • include_names (Optional[Sequence[str]]) – Only include logs with these names.

  • include_types (Optional[Sequence[str]]) – Only include logs with these types.

  • include_tags (Optional[Sequence[str]]) – Only include logs with these tags.

  • exclude_names (Optional[Sequence[str]]) – Exclude logs with these names.

  • exclude_types (Optional[Sequence[str]]) – Exclude logs with these types.

  • exclude_tags (Optional[Sequence[str]]) – Exclude logs with these tags.

  • kwargs (Any) –

Return type

Union[AsyncIterator[RunLogPatch], AsyncIterator[RunLog]]

async atransform(input: AsyncIterator[Input], config: Optional[RunnableConfig] = None, **kwargs: Optional[Any]) AsyncIterator[Output]

Default implementation of atransform, which buffers input and calls astream. Subclasses should override this method if they can start producing output while input is still being generated.

Parameters
  • input (AsyncIterator[Input]) –

  • config (Optional[RunnableConfig]) –

  • kwargs (Optional[Any]) –

Return type

AsyncIterator[Output]

batch(inputs: List[Input], config: Optional[Union[RunnableConfig, List[RunnableConfig]]] = None, *, return_exceptions: bool = False, **kwargs: Optional[Any]) List[Output]

Default implementation runs invoke in parallel using a thread pool executor.

The default implementation of batch works well for IO bound runnables.

Subclasses should override this method if they can batch more efficiently; e.g., if the underlying runnable uses an API which supports a batch mode.

Parameters
  • inputs (List[Input]) –

  • config (Optional[Union[RunnableConfig, List[RunnableConfig]]]) –

  • return_exceptions (bool) –

  • kwargs (Optional[Any]) –

Return type

List[Output]

bind(**kwargs: Any) Runnable[Input, Output]

Bind arguments to a Runnable, returning a new Runnable.

Parameters

kwargs (Any) –

Return type

Runnable[Input, Output]

config_schema(*, include: Optional[Sequence[str]] = None) Type[BaseModel]

The type of config this runnable accepts specified as a pydantic model.

To mark a field as configurable, see the configurable_fields and configurable_alternatives methods.

Parameters

include (Optional[Sequence[str]]) – A list of fields to include in the config schema.

Returns

A pydantic model that can be used to validate config.

Return type

Type[BaseModel]

configurable_alternatives(which: ConfigurableField, *, default_key: str = 'default', prefix_keys: bool = False, **kwargs: Union[Runnable[Input, Output], Callable[[], Runnable[Input, Output]]]) RunnableSerializable[Input, Output]
Parameters
Return type

RunnableSerializable[Input, Output]

configurable_fields(**kwargs: Union[ConfigurableField, ConfigurableFieldSingleOption, ConfigurableFieldMultiOption]) RunnableSerializable[Input, Output]
Parameters

kwargs (Union[ConfigurableField, ConfigurableFieldSingleOption, ConfigurableFieldMultiOption]) –

Return type

RunnableSerializable[Input, Output]

classmethod construct(_fields_set: Optional[SetStr] = None, **values: Any) Model

Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data. Default values are respected, but no other validation is performed. Behaves as if Config.extra = ‘allow’ was set since it adds all passed values

Parameters
  • _fields_set (Optional[SetStr]) –

  • values (Any) –

Return type

Model

copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny] = None, deep: bool = False) Model

Duplicate a model, optionally choose which fields to include, exclude and change.

Parameters
  • include (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) – fields to include in new model

  • exclude (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) – fields to exclude from new model, as with values this takes precedence over include

  • update (Optional[DictStrAny]) – values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data

  • deep (bool) – set to True to make a deep copy of the model

  • self (Model) –

Returns

new model instance

Return type

Model

dict(**kwargs: Any) Dict

Dictionary representation of chain.

Expects Chain._chain_type property to be implemented and for memory to be

null.

Parameters

**kwargs (Any) – Keyword arguments passed to default pydantic.BaseModel.dict method.

Returns

A dictionary representation of the chain.

Return type

Dict

Example

chain.dict(exclude_unset=True)
# -> {"_type": "foo", "verbose": False, ...}
classmethod from_llm(llm: BaseLanguageModel, retriever: BaseRetriever, condense_question_prompt: BasePromptTemplate = PromptTemplate(input_variables=['chat_history', 'question'], template='Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question, in its original language.\n\nChat History:\n{chat_history}\nFollow Up Input: {question}\nStandalone question:'), chain_type: str = 'stuff', verbose: bool = False, condense_question_llm: Optional[BaseLanguageModel] = None, combine_docs_chain_kwargs: Optional[Dict] = None, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, **kwargs: Any) BaseConversationalRetrievalChain[source]

Convenience method to load chain from LLM and retriever.

This provides some logic to create the question_generator chain as well as the combine_docs_chain.

Parameters
  • llm (BaseLanguageModel) – The default language model to use at every part of this chain (eg in both the question generation and the answering)

  • retriever (BaseRetriever) – The retriever to use to fetch relevant documents from.

  • condense_question_prompt (BasePromptTemplate) – The prompt to use to condense the chat history and new question into a standalone question.

  • chain_type (str) – The chain type to use to create the combine_docs_chain, will be sent to load_qa_chain.

  • verbose (bool) – Verbosity flag for logging to stdout.

  • condense_question_llm (Optional[BaseLanguageModel]) – The language model to use for condensing the chat history and new question into a standalone question. If none is provided, will default to llm.

  • combine_docs_chain_kwargs (Optional[Dict]) – Parameters to pass as kwargs to load_qa_chain when constructing the combine_docs_chain.

  • callbacks (Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]) – Callbacks to pass to all subchains.

  • **kwargs (Any) – Additional parameters to pass when initializing ConversationalRetrievalChain

Return type

BaseConversationalRetrievalChain

classmethod from_orm(obj: Any) Model
Parameters

obj (Any) –

Return type

Model

get_graph(config: Optional[RunnableConfig] = None) Graph

Return a graph representation of this runnable.

Parameters

config (Optional[RunnableConfig]) –

Return type

Graph

get_input_schema(config: Optional[RunnableConfig] = None) Type[BaseModel]

Get a pydantic model that can be used to validate input to the runnable.

Runnables that leverage the configurable_fields and configurable_alternatives methods will have a dynamic input schema that depends on which configuration the runnable is invoked with.

This method allows to get an input schema for a specific configuration.

Parameters

config (Optional[RunnableConfig]) – A config to use when generating the schema.

Returns

A pydantic model that can be used to validate input.

Return type

Type[BaseModel]

classmethod get_lc_namespace() List[str]

Get the namespace of the langchain object.

For example, if the class is langchain.llms.openai.OpenAI, then the namespace is [“langchain”, “llms”, “openai”]

Return type

List[str]

get_name(suffix: Optional[str] = None, *, name: Optional[str] = None) str

Get the name of the runnable.

Parameters
  • suffix (Optional[str]) –

  • name (Optional[str]) –

Return type

str

get_output_schema(config: Optional[RunnableConfig] = None) Type[BaseModel]

Get a pydantic model that can be used to validate output to the runnable.

Runnables that leverage the configurable_fields and configurable_alternatives methods will have a dynamic output schema that depends on which configuration the runnable is invoked with.

This method allows to get an output schema for a specific configuration.

Parameters

config (Optional[RunnableConfig]) – A config to use when generating the schema.

Returns

A pydantic model that can be used to validate output.

Return type

Type[BaseModel]

get_prompts(config: Optional[RunnableConfig] = None) List[BasePromptTemplate]
Parameters

config (Optional[RunnableConfig]) –

Return type

List[BasePromptTemplate]

invoke(input: Dict[str, Any], config: Optional[RunnableConfig] = None, **kwargs: Any) Dict[str, Any]

Transform a single input into an output. Override to implement.

Parameters
  • input (Dict[str, Any]) – The input to the runnable.

  • config (Optional[RunnableConfig]) – A config to use when invoking the runnable. The config supports standard keys like ‘tags’, ‘metadata’ for tracing purposes, ‘max_concurrency’ for controlling how much work to do in parallel, and other keys. Please refer to the RunnableConfig for more details.

  • kwargs (Any) –

Returns

The output of the runnable.

Return type

Dict[str, Any]

classmethod is_lc_serializable() bool

Is this class serializable?

Return type

bool

json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Optional[Callable[[Any], Any]] = None, models_as_dict: bool = True, **dumps_kwargs: Any) unicode

Generate a JSON representation of the model, include and exclude arguments as per dict().

encoder is an optional function to supply as default to json.dumps(), other arguments as per json.dumps().

Parameters
  • include (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) –

  • exclude (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) –

  • by_alias (bool) –

  • skip_defaults (Optional[bool]) –

  • exclude_unset (bool) –

  • exclude_defaults (bool) –

  • exclude_none (bool) –

  • encoder (Optional[Callable[[Any], Any]]) –

  • models_as_dict (bool) –

  • dumps_kwargs (Any) –

Return type

unicode

classmethod lc_id() List[str]

A unique identifier for this class for serialization purposes.

The unique identifier is a list of strings that describes the path to the object.

Return type

List[str]

map() Runnable[List[Input], List[Output]]

Return a new Runnable that maps a list of inputs to a list of outputs, by calling invoke() with each input.

Return type

Runnable[List[Input], List[Output]]

classmethod parse_file(path: Union[str, Path], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) Model
Parameters
  • path (Union[str, Path]) –

  • content_type (unicode) –

  • encoding (unicode) –

  • proto (Protocol) –

  • allow_pickle (bool) –

Return type

Model

classmethod parse_obj(obj: Any) Model
Parameters

obj (Any) –

Return type

Model

classmethod parse_raw(b: Union[str, bytes], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) Model
Parameters
  • b (Union[str, bytes]) –

  • content_type (unicode) –

  • encoding (unicode) –

  • proto (Protocol) –

  • allow_pickle (bool) –

Return type

Model

pick(keys: Union[str, List[str]]) RunnableSerializable[Any, Any]

Pick keys from the dict output of this runnable. Returns a new runnable.

Parameters

keys (Union[str, List[str]]) –

Return type

RunnableSerializable[Any, Any]

pipe(*others: Union[Runnable[Any, Other], Callable[[Any], Other]], name: Optional[str] = None) RunnableSerializable[Input, Other]

Compose this runnable with another object to create a RunnableSequence.

Parameters
  • others (Union[Runnable[Any, Other], Callable[[Any], Other]]) –

  • name (Optional[str]) –

Return type

RunnableSerializable[Input, Other]

prep_inputs(inputs: Union[Dict[str, Any], Any]) Dict[str, str]

Prepare chain inputs, including adding inputs from memory.

Parameters

inputs (Union[Dict[str, Any], Any]) – Dictionary of raw inputs, or single input if chain expects only one param. Should contain all inputs specified in Chain.input_keys except for inputs that will be set by the chain’s memory.

Returns

A dictionary of all inputs, including those added by the chain’s memory.

Return type

Dict[str, str]

prep_outputs(inputs: Dict[str, str], outputs: Dict[str, str], return_only_outputs: bool = False) Dict[str, str]

Validate and prepare chain outputs, and save info about this run to memory.

Parameters
  • inputs (Dict[str, str]) – Dictionary of chain inputs, including any inputs added by chain memory.

  • outputs (Dict[str, str]) – Dictionary of initial chain outputs.

  • return_only_outputs (bool) – Whether to only return the chain outputs. If False, inputs are also added to the final outputs.

Returns

A dict of the final chain outputs.

Return type

Dict[str, str]

run(*args: Any, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, **kwargs: Any) Any

[Deprecated] Convenience method for executing chain.

The main difference between this method and Chain.__call__ is that this method expects inputs to be passed directly in as positional arguments or keyword arguments, whereas Chain.__call__ expects a single input dictionary with all the inputs

Parameters
  • *args (Any) – If the chain expects a single input, it can be passed in as the sole positional argument.

  • callbacks (Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]) – Callbacks to use for this chain run. These will be called in addition to callbacks passed to the chain during construction, but only these runtime callbacks will propagate to calls to other objects.

  • tags (Optional[List[str]]) – List of string tags to pass to all callbacks. These will be passed in addition to tags passed to the chain during construction, but only these runtime tags will propagate to calls to other objects.

  • **kwargs (Any) – If the chain expects multiple inputs, they can be passed in directly as keyword arguments.

  • metadata (Optional[Dict[str, Any]]) –

  • **kwargs

Returns

The chain output.

Return type

Any

Example

# Suppose we have a single-input chain that takes a 'question' string:
chain.run("What's the temperature in Boise, Idaho?")
# -> "The temperature in Boise is..."

# Suppose we have a multi-input chain that takes a 'question' string
# and 'context' string:
question = "What's the temperature in Boise, Idaho?"
context = "Weather report for Boise, Idaho on 07/03/23..."
chain.run(question=question, context=context)
# -> "The temperature in Boise is..."

Notes

Deprecated since version 0.1.0: Use invoke instead.

save(file_path: Union[Path, str]) None

Save the chain.

Expects Chain._chain_type property to be implemented and for memory to be

null.

Parameters

file_path (Union[Path, str]) – Path to file to save the chain to.

Return type

None

Example

chain.save(file_path="path/chain.yaml")
classmethod schema(by_alias: bool = True, ref_template: unicode = '#/definitions/{model}') DictStrAny
Parameters
  • by_alias (bool) –

  • ref_template (unicode) –

Return type

DictStrAny

classmethod schema_json(*, by_alias: bool = True, ref_template: unicode = '#/definitions/{model}', **dumps_kwargs: Any) unicode
Parameters
  • by_alias (bool) –

  • ref_template (unicode) –

  • dumps_kwargs (Any) –

Return type

unicode

stream(input: Input, config: Optional[RunnableConfig] = None, **kwargs: Optional[Any]) Iterator[Output]

Default implementation of stream, which calls invoke. Subclasses should override this method if they support streaming output.

Parameters
  • input (Input) –

  • config (Optional[RunnableConfig]) –

  • kwargs (Optional[Any]) –

Return type

Iterator[Output]

to_json() Union[SerializedConstructor, SerializedNotImplemented]

Serialize the runnable to JSON.

Return type

Union[SerializedConstructor, SerializedNotImplemented]

to_json_not_implemented() SerializedNotImplemented
Return type

SerializedNotImplemented

transform(input: Iterator[Input], config: Optional[RunnableConfig] = None, **kwargs: Optional[Any]) Iterator[Output]

Default implementation of transform, which buffers input and then calls stream. Subclasses should override this method if they can start producing output while input is still being generated.

Parameters
  • input (Iterator[Input]) –

  • config (Optional[RunnableConfig]) –

  • kwargs (Optional[Any]) –

Return type

Iterator[Output]

classmethod update_forward_refs(**localns: Any) None

Try to update ForwardRefs on fields based on this Model, globalns and localns.

Parameters

localns (Any) –

Return type

None

classmethod validate(value: Any) Model
Parameters

value (Any) –

Return type

Model

with_config(config: Optional[RunnableConfig] = None, **kwargs: Any) Runnable[Input, Output]

Bind config to a Runnable, returning a new Runnable.

Parameters
Return type

Runnable[Input, Output]

with_fallbacks(fallbacks: Sequence[Runnable[Input, Output]], *, exceptions_to_handle: Tuple[Type[BaseException], ...] = (<class 'Exception'>,), exception_key: Optional[str] = None) RunnableWithFallbacksT[Input, Output]

Add fallbacks to a runnable, returning a new Runnable.

Parameters
  • fallbacks (Sequence[Runnable[Input, Output]]) – A sequence of runnables to try if the original runnable fails.

  • exceptions_to_handle (Tuple[Type[BaseException], ...]) – A tuple of exception types to handle.

  • exception_key (Optional[str]) – If string is specified then handled exceptions will be passed to fallbacks as part of the input under the specified key. If None, exceptions will not be passed to fallbacks. If used, the base runnable and its fallbacks must accept a dictionary as input.

Returns

A new Runnable that will try the original runnable, and then each fallback in order, upon failures.

Return type

RunnableWithFallbacksT[Input, Output]

with_listeners(*, on_start: Optional[Listener] = None, on_end: Optional[Listener] = None, on_error: Optional[Listener] = None) Runnable[Input, Output]

Bind lifecycle listeners to a Runnable, returning a new Runnable.

on_start: Called before the runnable starts running, with the Run object. on_end: Called after the runnable finishes running, with the Run object. on_error: Called if the runnable throws an error, with the Run object.

The Run object contains information about the run, including its id, type, input, output, error, start_time, end_time, and any tags or metadata added to the run.

Parameters
  • on_start (Optional[Listener]) –

  • on_end (Optional[Listener]) –

  • on_error (Optional[Listener]) –

Return type

Runnable[Input, Output]

with_retry(*, retry_if_exception_type: ~typing.Tuple[~typing.Type[BaseException], ...] = (<class 'Exception'>,), wait_exponential_jitter: bool = True, stop_after_attempt: int = 3) Runnable[Input, Output]

Create a new Runnable that retries the original runnable on exceptions.

Parameters
  • retry_if_exception_type (Tuple[Type[BaseException], ...]) – A tuple of exception types to retry on

  • wait_exponential_jitter (bool) – Whether to add jitter to the wait time between retries

  • stop_after_attempt (int) – The maximum number of attempts to make before giving up

Returns

A new Runnable that retries the original runnable on exceptions.

Return type

Runnable[Input, Output]

with_types(*, input_type: Optional[Type[Input]] = None, output_type: Optional[Type[Output]] = None) Runnable[Input, Output]

Bind input and output types to a Runnable, returning a new Runnable.

Parameters
  • input_type (Optional[Type[Input]]) –

  • output_type (Optional[Type[Output]]) –

Return type

Runnable[Input, Output]

property InputType: Type[Input]

The type of input this runnable accepts specified as a type annotation.

property OutputType: Type[Output]

The type of output this runnable produces specified as a type annotation.

property config_specs: List[ConfigurableFieldSpec]

List configurable fields for this runnable.

property input_keys: List[str]

Input keys.

property input_schema: Type[BaseModel]

The type of input this runnable accepts specified as a pydantic model.

property lc_attributes: Dict

List of attribute names that should be included in the serialized kwargs.

These attributes must be accepted by the constructor.

property lc_secrets: Dict[str, str]

A map of constructor argument names to secret ids.

For example,

{“openai_api_key”: “OPENAI_API_KEY”}

name: Optional[str] = None

The name of the runnable. Used for debugging and tracing.

property output_schema: Type[BaseModel]

The type of output this runnable produces specified as a pydantic model.

Examples using ConversationalRetrievalChain