`langchain_core.prompts.prompt`.PromptTemplate¶

Note

PromptTemplate implements the standard Runnable Interface. 🏃

The Runnable Interface has additional methods that are available on runnables, such as with_types, with_retry, assign, bind, get_graph, and more.

class langchain_core.prompts.prompt.PromptTemplate[source]¶

Bases: StringPromptTemplate

Prompt template for a language model.

A prompt template consists of a string template. It accepts a set of parameters from the user that can be used to generate a prompt for a language model.

The template can be formatted using either f-strings (default) or jinja2 syntax.

Security warning:

Prefer using template_format=”f-string” instead of template_format=”jinja2”, or make sure to NEVER accept jinja2 templates from untrusted sources as they may lead to arbitrary Python code execution.

As of LangChain 0.0.329, Jinja2 templates will be rendered using Jinja2’s SandboxedEnvironment by default. This sand-boxing should be treated as a best-effort approach rather than a guarantee of security, as it is an opt-out rather than opt-in approach.

Despite the sand-boxing, we recommend to never use jinja2 templates from untrusted sources.

Example

from langchain_core.prompts import PromptTemplate

# Instantiation using from_template (recommended)
prompt = PromptTemplate.from_template("Say {foo}")
prompt.format(foo="bar")

# Instantiation using initializer
prompt = PromptTemplate(template="Say {foo}")

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] [Required]¶: A list of the names of the variables whose values are required as inputs to the prompt.

param metadata: Optional[Dict[str, Any]] = None¶: Metadata to be used for tracing.

param optional_variables: List[str] = []¶: optional_variables: A list of the names of the variables for placeholder or MessagePlaceholder that are optional. These variables are auto inferred from the prompt and user need not provide them.

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

param partial_variables: Mapping[str, Any] [Optional]¶

A dictionary of the partial variables the prompt template carries.

Partial variables populate the template so that you don’t need to pass them in every time you call the prompt.

param tags: Optional[List[str]] = None¶: Tags to be used for tracing.

param template: str [Required]¶: The prompt template.

param template_format: Literal['f-string', 'mustache', 'jinja2'] = 'f-string'¶: The format of the prompt template. Options are: ‘f-string’, ‘mustache’, ‘jinja2’.

param validate_template: bool = False¶: Whether or not to try validating the template.

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]) – A list of inputs to the Runnable.
config (Optional[Union[RunnableConfig, List[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. Defaults to None.
return_exceptions (bool) – Whether to return exceptions instead of raising them. Defaults to False.
kwargs (Optional[Any]) – Additional keyword arguments to pass to the Runnable.

Returns

A list of outputs from the Runnable.

Return type

List[Output]

async abatch_as_completed(inputs: Sequence[Input], config: Optional[Union[RunnableConfig, Sequence[RunnableConfig]]] = None, *, return_exceptions: bool = False, **kwargs: Optional[Any]) → AsyncIterator[Tuple[int, Union[Output, Exception]]]¶

Run ainvoke in parallel on a list of inputs, yielding results as they complete.

Parameters

inputs (Sequence[Input]) – A list of inputs to the Runnable.
config (Optional[Union[RunnableConfig, Sequence[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. Defaults to None. Defaults to None.
return_exceptions (bool) – Whether to return exceptions instead of raising them. Defaults to False.
kwargs (Optional[Any]) – Additional keyword arguments to pass to the Runnable.

Yields

A tuple of the index of the input and the output from the Runnable.

Return type

AsyncIterator[Tuple[int, Union[Output, Exception]]]

async aformat(**kwargs: Any) → FormatOutputType¶

Async format the prompt with the inputs.

Parameters: kwargs (Any) – Any arguments to be passed to the prompt template.
Returns: A formatted string.
Return type: FormatOutputType

Example:

await prompt.aformat(variable1="foo")

async aformat_prompt(**kwargs: Any) → PromptValue¶

Async format the prompt with the inputs.

Parameters: kwargs (Any) – Any arguments to be passed to the prompt template.
Returns: A formatted string.
Return type: PromptValue

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

Async invoke the prompt.

Parameters

input (Dict) – Dict, input to the prompt.
config (Optional[RunnableConfig]) – RunnableConfig, configuration for the prompt.
kwargs (Any) –

Returns

The output of the prompt.

Return type

PromptValue

as_tool(args_schema: Optional[Type[BaseModel]] = None, *, name: Optional[str] = None, description: Optional[str] = None, arg_types: Optional[Dict[str, Type]] = None) → BaseTool¶

Beta

This API is in beta and may change in the future.

Create a BaseTool from a Runnable.

as_tool will instantiate a BaseTool with a name, description, and args_schema from a Runnable. Where possible, schemas are inferred from runnable.get_input_schema. Alternatively (e.g., if the Runnable takes a dict as input and the specific dict keys are not typed), the schema can be specified directly with args_schema. You can also pass arg_types to just specify the required arguments and their types.

Parameters

args_schema (Optional[Type[BaseModel]]) – The schema for the tool. Defaults to None.
name (Optional[str]) – The name of the tool. Defaults to None.
description (Optional[str]) – The description of the tool. Defaults to None.
arg_types (Optional[Dict[str, Type]]) – A dictionary of argument names to types. Defaults to None.

Returns

A BaseTool instance.

Return type

BaseTool

Typed dict input:

from typing import List
from typing_extensions import TypedDict
from langchain_core.runnables import RunnableLambda

class Args(TypedDict):
    a: int
    b: List[int]

def f(x: Args) -> str:
    return str(x["a"] * max(x["b"]))

runnable = RunnableLambda(f)
as_tool = runnable.as_tool()
as_tool.invoke({"a": 3, "b": [1, 2]})

dict input, specifying schema via args_schema:

from typing import Any, Dict, List
from langchain_core.pydantic_v1 import BaseModel, Field
from langchain_core.runnables import RunnableLambda

def f(x: Dict[str, Any]) -> str:
    return str(x["a"] * max(x["b"]))

class FSchema(BaseModel):
    """Apply a function to an integer and list of integers."""

    a: int = Field(..., description="Integer")
    b: List[int] = Field(..., description="List of ints")

runnable = RunnableLambda(f)
as_tool = runnable.as_tool(FSchema)
as_tool.invoke({"a": 3, "b": [1, 2]})

dict input, specifying schema via arg_types:

from typing import Any, Dict, List
from langchain_core.runnables import RunnableLambda

def f(x: Dict[str, Any]) -> str:
    return str(x["a"] * max(x["b"]))

runnable = RunnableLambda(f)
as_tool = runnable.as_tool(arg_types={"a": int, "b": List[int]})
as_tool.invoke({"a": 3, "b": [1, 2]})

String input:

from langchain_core.runnables import RunnableLambda

def f(x: str) -> str:
    return x + "a"

def g(x: str) -> str:
    return x + "z"

runnable = RunnableLambda(f) | g
as_tool = runnable.as_tool()
as_tool.invoke("b")

New in version 0.2.14.

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) – The input to the Runnable.
config (Optional[RunnableConfig]) – The config to use for the Runnable. Defaults to None.
kwargs (Optional[Any]) – Additional keyword arguments to pass to the Runnable.

Yields

The output of the Runnable.

Return type

AsyncIterator[Output]

astream_events(input: Any, config: Optional[RunnableConfig] = None, *, version: Literal['v1', 'v2'], 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[Union[StandardStreamEvent, CustomStreamEvent]]¶

Beta

This API is in beta and may change in the future.

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.
parent_ids: List[str] - The IDs of the parent runnables that
generated the event. The root Runnable will have an empty list. The order of the parent IDs is from the root to the immediate parent. Only available for v2 version of the API. The v1 version of the API will return an empty list.
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.

ATTENTION This reference table is for the V2 version of the schema.

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]]}	AIMessageChunk(content=”hello world”)
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_end	some_tool			{“x”: 1, “y”: “2”}
on_retriever_start	[retriever name]		{“query”: “hello”}
on_retriever_end	[retriever name]		{“query”: “hello”}	[Document(…), ..]
on_prompt_start	[template_name]		{“question”: “hello”}
on_prompt_end	[template_name]		{“question”: “hello”}	ChatPromptValue(messages: [SystemMessage, …])

In addition to the standard events, users can also dispatch custom events (see example below).

Custom events will be only be surfaced with in the v2 version of the API!

A custom event has following format:

Attribute	Type	Description
name	str	A user defined name for the event.
data	Any	The data associated with the event. This can be anything, though we suggest making it JSON serializable.

Here are declarations associated with the standard 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="v2")
]

# will produce the following events (run_id, and parent_ids
# 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": [],
    },
]

Example: Dispatch Custom Event

from langchain_core.callbacks.manager import (
    adispatch_custom_event,
)
from langchain_core.runnables import RunnableLambda, RunnableConfig
import asyncio


async def slow_thing(some_input: str, config: RunnableConfig) -> str:
    """Do something that takes a long time."""
    await asyncio.sleep(1) # Placeholder for some slow operation
    await adispatch_custom_event(
        "progress_event",
        {"message": "Finished step 1 of 3"},
        config=config # Must be included for python < 3.10
    )
    await asyncio.sleep(1) # Placeholder for some slow operation
    await adispatch_custom_event(
        "progress_event",
        {"message": "Finished step 2 of 3"},
        config=config # Must be included for python < 3.10
    )
    await asyncio.sleep(1) # Placeholder for some slow operation
    return "Done"

slow_thing = RunnableLambda(slow_thing)

async for event in slow_thing.astream_events("some_input", version="v2"):
    print(event)

Parameters

input (Any) – The input to the Runnable.
config (Optional[RunnableConfig]) – The config to use for the Runnable.
version (Literal['v1', 'v2']) – The version of the schema to use either v2 or v1. Users should use v2. v1 is for backwards compatibility and will be deprecated in 0.4.0. No default will be assigned until the API is stabilized. custom events will only be surfaced in v2.
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.

Yields

An async stream of StreamEvents.

Raises

NotImplementedError – If the version is not v1 or v2.

Return type

AsyncIterator[Union[StandardStreamEvent, CustomStreamEvent]]

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]

batch_as_completed(inputs: Sequence[Input], config: Optional[Union[RunnableConfig, Sequence[RunnableConfig]]] = None, *, return_exceptions: bool = False, **kwargs: Optional[Any]) → Iterator[Tuple[int, Union[Output, Exception]]]¶

Run invoke in parallel on a list of inputs, yielding results as they complete.

Parameters

inputs (Sequence[Input]) –
config (Optional[Union[RunnableConfig, Sequence[RunnableConfig]]]) –
return_exceptions (bool) –
kwargs (Optional[Any]) –

Return type

Iterator[Tuple[int, Union[Output, Exception]]]

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

Configure alternatives for Runnables that can be set at runtime.

Parameters

which (ConfigurableField) – The ConfigurableField instance that will be used to select the alternative.
default_key (str) – The default key to use if no alternative is selected. Defaults to “default”.
prefix_keys (bool) – Whether to prefix the keys with the ConfigurableField id. Defaults to False.
**kwargs (Union[Runnable[Input, Output], Callable[[], Runnable[Input, Output]]]) – A dictionary of keys to Runnable instances or callables that return Runnable instances.

Returns

A new Runnable with the alternatives configured.

Return type

RunnableSerializable[Input, Output]

from langchain_anthropic import ChatAnthropic
from langchain_core.runnables.utils import ConfigurableField
from langchain_openai import ChatOpenAI

model = ChatAnthropic(
    model_name="claude-3-sonnet-20240229"
).configurable_alternatives(
    ConfigurableField(id="llm"),
    default_key="anthropic",
    openai=ChatOpenAI()
)

# uses the default model ChatAnthropic
print(model.invoke("which organization created you?").content)

# uses ChatOpenAI
print(
    model.with_config(
        configurable={"llm": "openai"}
    ).invoke("which organization created you?").content
)

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

Configure particular Runnable fields at runtime.

Parameters: **kwargs (Union[ConfigurableField, ConfigurableFieldSingleOption, ConfigurableFieldMultiOption]) – A dictionary of ConfigurableField instances to configure.
Returns: A new Runnable with the fields configured.
Return type: RunnableSerializable[Input, Output]

from langchain_core.runnables import ConfigurableField
from langchain_openai import ChatOpenAI

model = ChatOpenAI(max_tokens=20).configurable_fields(
    max_tokens=ConfigurableField(
        id="output_token_number",
        name="Max tokens in the output",
        description="The maximum number of tokens in the output",
    )
)

# max_tokens = 20
print(
    "max_tokens_20: ",
    model.invoke("tell me something about chess").content
)

# max_tokens = 200
print("max_tokens_200: ", model.with_config(
    configurable={"output_token_number": 200}
    ).invoke("tell me something about chess").content
)

format(**kwargs: Any) → str[source]¶

Format the prompt with the inputs.

Parameters: kwargs (Any) – Any arguments to be passed to the prompt template.
Returns: A formatted string.
Return type: str

format_prompt(**kwargs: Any) → PromptValue¶

Format the prompt with the inputs.

Parameters: kwargs (Any) – Any arguments to be passed to the prompt template.
Returns: A formatted string.
Return type: PromptValue

classmethod from_examples(examples: List[str], suffix: str, input_variables: List[str], example_separator: str = '\n\n', prefix: str = '', **kwargs: Any) → PromptTemplate[source]¶

Take examples in list format with prefix and suffix to create a prompt.

Intended to be used as a way to dynamically create a prompt from examples.

Parameters

examples (List[str]) – List of examples to use in the prompt.
suffix (str) – String to go after the list of examples. Should generally set up the user’s input.
input_variables (List[str]) – A list of variable names the final prompt template will expect.
example_separator (str) – The separator to use in between examples. Defaults to two new line characters.
prefix (str) – String that should go before any examples. Generally includes examples. Default to an empty string.
kwargs (Any) –

Returns

The final prompt generated.

Return type

PromptTemplate

classmethod from_file(template_file: Union[str, Path], input_variables: Optional[List[str]] = None, encoding: Optional[str] = None, **kwargs: Any) → PromptTemplate[source]¶

Load a prompt from a file.

Parameters

template_file (Union[str, Path]) – The path to the file containing the prompt template.
input_variables (Optional[List[str]]) – [DEPRECATED] A list of variable names the final prompt template will expect. Defaults to None.
encoding (Optional[str]) – The encoding system for opening the template file. If not provided, will use the OS default.
kwargs (Any) –

Return type

PromptTemplate

input_variables is ignored as from_file now delegates to from_template().

Returns

The prompt loaded from the file.

Parameters

template_file (Union[str, Path]) –
input_variables (Optional[List[str]]) –
encoding (Optional[str]) –
kwargs (Any) –

Return type

PromptTemplate

classmethod from_template(template: str, *, template_format: str = 'f-string', partial_variables: Optional[Dict[str, Any]] = None, **kwargs: Any) → PromptTemplate[source]¶

Load a prompt template from a template.

Security warning:

Prefer using template_format=”f-string” instead of template_format=”jinja2”, or make sure to NEVER accept jinja2 templates from untrusted sources as they may lead to arbitrary Python code execution.

As of LangChain 0.0.329, Jinja2 templates will be rendered using Jinja2’s SandboxedEnvironment by default. This sand-boxing should be treated as a best-effort approach rather than a guarantee of security, as it is an opt-out rather than opt-in approach.

Despite the sand-boxing, we recommend never using jinja2 templates from untrusted sources.

Parameters

template (str) – The template to load.
template_format (str) – The format of the template. Use jinja2 for jinja2, and f-string or None for f-strings. Defaults to f-string.
partial_variables (Optional[Dict[str, Any]]) –

A dictionary of variables that can be used to partially
fill in the template. For example, if the template is

”{variable1} {variable2}”, and partial_variables is {“variable1”: “foo”}, then the final prompt will be “foo {variable2}”. Defaults to None.
kwargs (Any) – Any other arguments to pass to the prompt template.

Returns

The prompt template loaded from the template.

Return type

PromptTemplate

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

Invoke the prompt.

Parameters

input (Dict) – Dict, input to the prompt.
config (Optional[RunnableConfig]) – RunnableConfig, configuration for the prompt.

Returns

The output of the prompt.

Return type

PromptValue

partial(**kwargs: Union[str, Callable[[], str]]) → BasePromptTemplate¶

Return a partial of the prompt template.

Parameters: kwargs (Union[str, Callable[[], str]]) – Union[str, Callable[[], str], partial variables to set.
Returns: A partial of the prompt template.
Return type: BasePromptTemplate

pretty_print() → None¶

Print a pretty representation of the prompt.

Return type: None

pretty_repr(html: bool = False) → str¶

Get a pretty representation of the prompt.

Parameters: html (bool) – Whether to return an HTML-formatted string.
Returns: A pretty representation of the prompt.
Return type: str

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

Save the prompt.

Parameters

file_path (Union[Path, str]) – Path to directory to save prompt to.

Raises

ValueError – If the prompt has partial variables.
ValueError – If the file path is not json or yaml.
NotImplementedError – If the prompt type is not implemented.

Return type

None

Example: .. code-block:: python

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

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) – The input to the Runnable.
config (Optional[RunnableConfig]) – The config to use for the Runnable. Defaults to None.
kwargs (Optional[Any]) – Additional keyword arguments to pass to the Runnable.

Yields

The output of the Runnable.

Return type

Iterator[Output]

to_json() → Union[SerializedConstructor, SerializedNotImplemented]¶

Serialize the Runnable to JSON.

Returns: A JSON-serializable representation of the Runnable.
Return type: Union[SerializedConstructor, SerializedNotImplemented]

Examples using PromptTemplate¶

langchain_core.prompts.prompt.PromptTemplate¶

Examples using PromptTemplate¶

`langchain_core.prompts.prompt`.PromptTemplate¶