ChatPromptTemplate class final

A prompt template for chat models.

Whereas LLMs take a string as prompt, Chat models take a list of messages. ChatPromptTemplate uses a list of template messages to generate the final prompt.

Each template message can be:

Example:

final promptTemplate = ChatPromptTemplate.fromPromptMessages([
  ChatMessagePromptTemplate.system("Here's some context: {context}"),
  ChatMessagePromptTemplate.human("Hello {foo}, I'm {bar}. Thanks for the {context}"),
  ChatMessagePromptTemplate.ai("I'm an AI. I'm {foo}. I'm {bar}."),
]);
final prompt = promptTemplate.formatPrompt({
    'foo': 'GPT-4',
    'bar': 'Gemini',
    'context': 'competition',
});
final res = await chatModel.invoke(prompt);

If you prompt template only contains one message, you can use the convenient factory constructor ChatPromptTemplate.fromTemplate.

final promptTemplate = ChatPromptTemplate.fromTemplate("Hello {foo}, I'm {bar}. Thanks for the {context}");

If your prompt template contains multiple messages, you can use the convenient factory constructor ChatPromptTemplate.fromTemplates.

final promptTemplate = ChatPromptTemplate.fromTemplates([
  (ChatMessageType.system, 'You are a helpful assistant that translates {input_language} to {output_language}.'),
  (ChatMessageType.human, '{text}'),
]);

If you need a placeholder for a single message or a list of messages, you can use MessagePlaceholder or MessagesPlaceholder.

final promptTemplate = ChatPromptTemplate.fromTemplates([
  (ChatMessageType.system, "You are a helpful AI assistant."),
  (ChatMessageType.messagesPlaceholder, 'history'),
  (ChatMessageType.messagePlaceholder, 'input'),
]);

In general, prefer using ChatPromptTemplate.fromTemplate and ChatPromptTemplate.fromTemplates to create a ChatPromptTemplate as the resulting code is more readable. Use the main ChatPromptTemplate constructor or ChatPromptTemplate.fromPromptMessages for advanced use cases.

Inheritance
Available Extensions
Annotations
  • @immutable

Constructors

ChatPromptTemplate({required Set<String> inputVariables, PartialValues? partialVariables, required List<ChatMessagePromptTemplate> promptMessages})
A prompt template for chat models.
const
ChatPromptTemplate.fromPromptMessages(List<ChatMessagePromptTemplate> promptMessages, {bool validateTemplate = true})
Creates a ChatPromptTemplate with a list of template messages.
factory
ChatPromptTemplate.fromTemplate(String template, {ChatMessageType type = ChatMessageType.human, String? customRole, PartialValues? partialVariables, bool validateTemplate = true})
Creates a chat prompt template with a single message from a string template.
factory
ChatPromptTemplate.fromTemplates(List<(ChatMessageType, String)> messages, {String? customRole, PartialValues? partialVariables, bool validateTemplate = true})
Creates a ChatPromptTemplate from a list of pairs of chat message prompt template type and template.
factory

Properties

defaultOptions → BaseLangChainOptions
The default options to use when invoking the Runnable.
finalinherited
hashCode → int
The hash code for this object.
no setteroverride
inputVariables → Set<String>
A set of the names of the variables the prompt template expects.
finalinherited
partialVariables → PartialValues?
Partial variables.
finalinherited
promptMessages → List<ChatMessagePromptTemplate>
The list of messages that make up the prompt template.
final
runtimeType → Type
A representation of the runtime type of the object.
no setterinherited
type → String
The type of the prompt template.
no setteroverride

Methods

batch(List<InputValues> inputs, {List<BaseLangChainOptions>? options}) → Future<List<PromptValue>>
Batches the invocation of the Runnable on the given inputs.
inherited
bind(BaseLangChainOptions options) → RunnableBinding<InputValues, BaseLangChainOptions, PromptValue>
Binds the Runnable to the given options.
inherited
close() → void
Cleans up any resources associated with it the Runnable.
inherited
copyWith({Set<String>? inputVariables, PartialValues? partialVariables, List<ChatMessagePromptTemplate>? promptMessages}) → ChatPromptTemplate
Creates a copy of this ChatPromptTemplate with the given fields.
override
format(InputValues values) → String
Format the prompt given the input values and return a formatted string.
inherited
formatMessages([InputValues values = const {}]) → List<ChatMessage>
Format input values into a list of messages.
override
formatPrompt(InputValues values) → PromptValue
Format the prompt given the input values and return a formatted prompt value.
inherited
getCompatibleOptions(RunnableOptions? options) → BaseLangChainOptions?
Returns the given options if they are compatible with the Runnable, otherwise returns null.
inherited
invoke(InputValues input, {BaseLangChainOptions? options}) → Future<PromptValue>
Format the prompt given the input values and return a formatted prompt value.
inherited
mergePartialAndUserVariables(Map<String, dynamic> userVariables) → Map<String, Object>
Merge the partial variables with the user variables.
inherited
noSuchMethod(Invocation invocation) → dynamic
Invoked when a nonexistent method or property is accessed.
inherited
partial(PartialValues values) → BasePromptTemplate
Return a partial of the prompt template.
override
pipe<NewRunOutput extends Object?, NewCallOptions extends RunnableOptions>(Runnable<PromptValue, NewCallOptions, NewRunOutput> next) → RunnableSequence<InputValues, NewRunOutput>
Pipes the output of this Runnable into another Runnable using a RunnableSequence.
inherited
stream(InputValues input, {BaseLangChainOptions? options}) → Stream<PromptValue>
Streams the output of invoking the Runnable on the given input.
inherited
streamFromInputStream(Stream<InputValues> inputStream, {BaseLangChainOptions? options}) → Stream<PromptValue>
Streams the output of invoking the Runnable on the given inputStream.
inherited
toString() → String
A string representation of this object.
override
validateTemplate() → void
Validate the integrity of the prompt template, checking that all the variables are present and that the right format is used.
override

Operators

operator ==(covariant ChatPromptTemplate other) → bool
The equality operator.
override

Static Methods

fromTemplateFile(String templateFile, {ChatMessageType type = ChatMessageType.human, String? customRole, PartialValues? partialVariables, bool validateTemplate = true}) → Future<ChatPromptTemplate>
Creates a ChatPromptTemplate with a single message from a file.