`langchain_core.prompts.few_shot`.FewShotChatMessagePromptTemplate¶

class langchain_core.prompts.few_shot.FewShotChatMessagePromptTemplate[source]¶

Bases: BaseChatPromptTemplate, _FewShotPromptTemplateMixin

Chat prompt template that supports few-shot examples.

The high level structure of produced by this prompt template is a list of messages consisting of prefix message(s), example message(s), and suffix message(s).

This structure enables creating a conversation with intermediate examples like:

System: You are a helpful AI Assistant Human: What is 2+2? AI: 4 Human: What is 2+3? AI: 5 Human: What is 4+4?

This prompt template can be used to generate a fixed list of examples or else to dynamically select examples based on the input.

Examples

Prompt template with a fixed list of examples (matching the sample conversation above):

from langchain_core.prompts import (
    FewShotChatMessagePromptTemplate,
    ChatPromptTemplate
)

examples = [
    {"input": "2+2", "output": "4"},
    {"input": "2+3", "output": "5"},
]

example_prompt = ChatPromptTemplate.from_messages(
    [('human', '{input}'), ('ai', '{output}')]
)

few_shot_prompt = FewShotChatMessagePromptTemplate(
    examples=examples,
    # This is a prompt template used to format each individual example.
    example_prompt=example_prompt,
)

final_prompt = ChatPromptTemplate.from_messages(
    [
        ('system', 'You are a helpful AI Assistant'),
        few_shot_prompt,
        ('human', '{input}'),
    ]
)
final_prompt.format(input="What is 4+4?")

Prompt template with dynamically selected examples:

from langchain_core.prompts import SemanticSimilarityExampleSelector
from langchain_core.embeddings import OpenAIEmbeddings
from langchain_core.vectorstores import Chroma

examples = [
    {"input": "2+2", "output": "4"},
    {"input": "2+3", "output": "5"},
    {"input": "2+4", "output": "6"},
    # ...
]

to_vectorize = [
    " ".join(example.values())
    for example in examples
]
embeddings = OpenAIEmbeddings()
vectorstore = Chroma.from_texts(
    to_vectorize, embeddings, metadatas=examples
)
example_selector = SemanticSimilarityExampleSelector(
    vectorstore=vectorstore
)

from langchain_core import SystemMessage
from langchain_core.prompts import HumanMessagePromptTemplate
from langchain_core.prompts.few_shot import FewShotChatMessagePromptTemplate

few_shot_prompt = FewShotChatMessagePromptTemplate(
    # Which variable(s) will be passed to the example selector.
    input_variables=["input"],
    example_selector=example_selector,
    # Define how each example will be formatted.
    # In this case, each example will become 2 messages:
    # 1 human, and 1 AI
    example_prompt=(
        HumanMessagePromptTemplate.from_template("{input}")
        + AIMessagePromptTemplate.from_template("{output}")
    ),
)
# Define the overall prompt.
final_prompt = (
    SystemMessagePromptTemplate.from_template(
        "You are a helpful AI Assistant"
    )
    + few_shot_prompt
    + HumanMessagePromptTemplate.from_template("{input}")
)
# Show the prompt
print(final_prompt.format_messages(input="What's 3+3?"))

# Use within an LLM
from langchain_core.chat_models import ChatAnthropic
chain = final_prompt | ChatAnthropic()
chain.invoke({"input": "What's 3+3?"})

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 example_prompt: Union[BaseMessagePromptTemplate, BaseChatPromptTemplate] [Required]¶: The class to format each example.

param example_selector: Any = None¶: ExampleSelector to choose the examples to format into the prompt. Either this or examples should be provided.

param examples: Optional[List[dict]] = None¶: Examples to format into the prompt. Either this or example_selector should be provided.

param input_types: Dict[str, Any] [Optional]¶: A dictionary of the types of the variables the prompt template expects. If not provided, all variables are assumed to be strings.

param input_variables: List[str] [Optional]¶: A list of the names of the variables the prompt template will use to pass to the example_selector, if provided.

param output_parser: Optional[BaseOutputParser] = None¶: How to parse the output of calling an LLM on this formatted prompt.

param partial_variables: Mapping[str, Union[str, Callable[[], str]]] [Optional]¶

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.

async ainvoke(input: Input, config: Optional[RunnableConfig] = None, **kwargs: Any) → Output¶

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.

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.

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.

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: Optional[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 – The input to the runnable.
config – The config to use for the runnable.
diff – Whether to yield diffs between each step, or the current state.
with_streamed_output_list – Whether to yield the streamed_output list.
include_names – Only include logs with these names.
include_types – Only include logs with these types.
include_tags – Only include logs with these tags.
exclude_names – Exclude logs with these names.
exclude_types – Exclude logs with these types.
exclude_tags – Exclude logs with these tags.

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.

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.

bind(**kwargs: Any) → Runnable[Input, Output]¶: Bind arguments to a Runnable, returning a new Runnable.

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 – A list of fields to include in the config schema.
Returns: A pydantic model that can be used to validate config.

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

configurable_fields(**kwargs: Union[ConfigurableField, ConfigurableFieldSingleOption, ConfigurableFieldMultiOption]) → 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

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 – fields to include in new model
exclude – fields to exclude from new model, as with values this takes precedence over include
update – 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 – set to True to make a deep copy of the model

Returns

new model instance

dict(**kwargs: Any) → Dict¶: Return dictionary representation of prompt.

format(**kwargs: Any) → str[source]¶

Format the prompt with inputs generating a string.

Use this method to generate a string representation of a prompt consisting of chat messages.

Useful for feeding into a string based completion language model or debugging.

Parameters: **kwargs – keyword arguments to use for formatting.
Returns: A string representation of the prompt

format_messages(**kwargs: Any) → List[BaseMessage][source]¶

Format kwargs into a list of messages.

Parameters: **kwargs – keyword arguments to use for filling in templates in messages.
Returns: A list of formatted messages with all template variables filled in.

format_prompt(**kwargs: Any) → PromptValue¶

Format prompt. Should return a PromptValue. :param **kwargs: Keyword arguments to use for formatting.

Returns: PromptValue.

classmethod from_orm(obj: Any) → Model¶

get_graph(config: Optional[RunnableConfig] = None) → Graph¶: Return a graph representation of this runnable.

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 – A config to use when generating the schema.
Returns: A pydantic model that can be used to validate input.

classmethod get_lc_namespace() → List[str]¶: Get the namespace of the langchain object.

get_name(suffix: Optional[str] = None, *, name: Optional[str] = None) → str¶: Get the name of the runnable.

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 – A config to use when generating the schema.
Returns: A pydantic model that can be used to validate output.

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

invoke(input: Dict, config: Optional[RunnableConfig] = None) → PromptValue¶

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

Parameters

input – The input to the runnable.
config – 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.

Returns

The output of the runnable.

classmethod is_lc_serializable() → bool[source]¶: Return whether or not the class is serializable.

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().

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.

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.

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

classmethod parse_obj(obj: Any) → Model¶

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

partial(**kwargs: Union[str, Callable[[], str]]) → BasePromptTemplate¶: Return a partial of the prompt template.

pick(keys: Union[str, List[str]]) → RunnableSerializable[Any, Any]¶: Pick keys from the dict output of this runnable. Returns a new runnable.

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.

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

Save the prompt.

Parameters: file_path – Path to directory to save prompt to.

Example: .. code-block:: python

prompt.save(file_path=”path/prompt.yaml”)

classmethod schema(by_alias: bool = True, ref_template: unicode = '#/definitions/{model}') → DictStrAny¶

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

to_json() → Union[SerializedConstructor, SerializedNotImplemented]¶

to_json_not_implemented() → 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.

classmethod update_forward_refs(**localns: Any) → None¶: Try to update ForwardRefs on fields based on this Model, globalns and localns.

classmethod validate(value: Any) → Model¶

with_config(config: Optional[RunnableConfig] = None, **kwargs: Any) → Runnable[Input, Output]¶: Bind config to a Runnable, returning a new Runnable.

with_fallbacks(fallbacks: Sequence[Runnable[Input, Output]], *, exceptions_to_handle: Tuple[Type[BaseException], ...] = (<class 'Exception'>,)) → RunnableWithFallbacksT[Input, Output]¶

Add fallbacks to a runnable, returning a new Runnable.

Parameters

fallbacks – A sequence of runnables to try if the original runnable fails.
exceptions_to_handle – A tuple of exception types to handle.

Returns

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

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.

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 – A tuple of exception types to retry on
wait_exponential_jitter – Whether to add jitter to the wait time between retries
stop_after_attempt – The maximum number of attempts to make before giving up

Returns

A new Runnable that retries the original runnable on exceptions.

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.

property InputType: Type[langchain_core.runnables.utils.Input]¶: The type of input this runnable accepts specified as a type annotation.

property OutputType: Any¶: The type of output this runnable produces specified as a type annotation.

property config_specs: List[langchain_core.runnables.utils.ConfigurableFieldSpec]¶: List configurable fields for this runnable.

property input_schema: Type[pydantic.main.BaseModel]¶: The type of input this runnable accepts specified as a pydantic model.

property lc_attributes: Dict¶: Return a 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[pydantic.main.BaseModel]¶: The type of output this runnable produces specified as a pydantic model.

Examples using FewShotChatMessagePromptTemplate¶

Few-shot examples for chat models

langchain_core.prompts.few_shot.FewShotChatMessagePromptTemplate¶

Examples using FewShotChatMessagePromptTemplate¶

`langchain_core.prompts.few_shot`.FewShotChatMessagePromptTemplate¶