ChatAnthropic class

Wrapper around Anthropic Messages API (aka Claude API).

Example:

final chatModel = ChatAnthropic(apiKey: '...');
final messages = [
  ChatMessage.system('You are a helpful assistant that translates English to French.'),
  ChatMessage.humanText('I love programming.'),
];
final prompt = PromptValue.chat(messages);
final res = await llm.invoke(prompt);

Docs: https://docs.anthropic.com

Authentication

The Anthropic API uses API keys for authentication. Visit your API Keys page to retrieve the API key you'll use in your requests.

Available models

The following models are available:

claude-3-5-sonnet-20240620
claude-3-haiku-20240307
claude-3-opus-20240229
claude-3-sonnet-20240229
claude-2.0
claude-2.1

Mind that the list may not be up-to-date. See https://docs.anthropic.com/en/docs/about-claude/models for the updated list.

Call options

You can configure the parameters that will be used when calling the chat completions API in several ways:

Default options:

Use the defaultOptions parameter to set the default options. These options will be used unless you override them when generating completions.

final chatModel = ChatAnthropic(
  apiKey: anthropicApiKey,
  defaultOptions: const ChatAnthropicOptions(
    temperature: 0.9,
    maxTokens: 100,
  ),
);

Call options:

You can override the default options when invoking the model:

final res = await chatModel.invoke(
  prompt,
  options: const ChatAnthropicOptions(temperature: 0.5),
);

Bind:

You can also change the options in a Runnable pipeline using the bind method.

In this example, we are using two totally different models for each question:

final chatModel = ChatAnthropic(apiKey: anthropicApiKey);
const outputParser = StringOutputParser();
final prompt1 = PromptTemplate.fromTemplate('How are you {name}?');
final prompt2 = PromptTemplate.fromTemplate('How old are you {name}?');
final chain = Runnable.fromMap({
  'q1': prompt1 | chatModel.bind(const ChatAnthropicOptions(model: 'claude-3-5-sonnet-20241022)) | outputParser,
  'q2': prompt2 | chatModel.bind(const ChatAnthropicOptions(model: 'claude-3-sonnet-20240229)) | outputParser,
});
final res = await chain.invoke({'name': 'David'});

Advance

Custom HTTP client

You can always provide your own implementation of http.Client for further customization:

final client = ChatAnthropic(
  apiKey: 'ANTHROPIC_API_KEY',
  client: MyHttpClient(),
);

Using a proxy

HTTP proxy

You can use your own HTTP proxy by overriding the baseUrl and providing your required headers:

final client = ChatAnthropic(
  baseUrl: 'https://my-proxy.com',
  headers: {'x-my-proxy-header': 'value'},
);

If you need further customization, you can always provide your own http.Client.

SOCKS5 proxy

To use a SOCKS5 proxy, you can use the socks5_proxy package and a custom http.Client.

Constructors

ChatAnthropic.new({String? apiKey, String baseUrl = 'https://api.anthropic.com/v1', Map<String, String>? headers, Map<String, dynamic>? queryParams, Client? client, ChatAnthropicOptions defaultOptions = const ChatAnthropicOptions(model: defaultModel, maxTokens: defaultMaxTokens), String encoding = 'cl100k_base'}): Create a new ChatAnthropic instance.

Properties

defaultOptions → ChatAnthropicOptions: The default options to use when invoking the Runnable.
finalinherited
encoding ↔ String: The encoding to use by tiktoken when tokenize is called.
getter/setter pair
hashCode → int: The hash code for this object.
no setterinherited
modelType → String: Return type of language model.
no setter
runtimeType → Type: A representation of the runtime type of the object.
no setterinherited

Methods

batch(List<PromptValue> inputs, {List<ChatAnthropicOptions>? options}) → Future<List<ChatResult>>: Batches the invocation of the Runnable on the given inputs.
inherited
bind(ChatAnthropicOptions options) → RunnableBinding<PromptValue, ChatAnthropicOptions, ChatResult>: Binds the Runnable to the given options.
inherited
call(List<ChatMessage> messages, {ChatAnthropicOptions? options}) → Future<AIChatMessage>: Runs the chat model on the given messages and returns a chat message.
inherited
close() → void: Cleans up any resources associated with it the Runnable.
countTokens(PromptValue promptValue, {ChatAnthropicOptions? options}) → Future<int>: Returns the number of tokens resulting from tokenize the given prompt.
inherited
getCompatibleOptions(RunnableOptions? options) → ChatAnthropicOptions?: Returns the given options if they are compatible with the Runnable, otherwise returns null.
inherited
invoke(PromptValue input, {ChatAnthropicOptions? options}) → Future<ChatResult>: Invokes the Runnable on the given input.
noSuchMethod(Invocation invocation) → dynamic: Invoked when a nonexistent method or property is accessed.
inherited
pipe<NewRunOutput extends Object?, NewCallOptions extends RunnableOptions>(Runnable<ChatResult, NewCallOptions, NewRunOutput> next) → RunnableSequence<PromptValue, NewRunOutput>: Pipes the output of this Runnable into another Runnable using a RunnableSequence.
inherited
stream(PromptValue input, {ChatAnthropicOptions? options}) → Stream<ChatResult>: Streams the output of invoking the Runnable on the given input.
streamFromInputStream(Stream<PromptValue> inputStream, {ChatAnthropicOptions? options}) → Stream<ChatResult>: Streams the output of invoking the Runnable on the given inputStream.
inherited
tokenize(PromptValue promptValue, {ChatAnthropicOptions? options}) → Future<List<int>>: Tokenizes the given prompt using tiktoken.
toString() → String: A string representation of this object.
inherited
withFallbacks(List<Runnable<PromptValue, RunnableOptions, ChatResult>> fallbacks) → RunnableWithFallback<PromptValue, ChatResult>: Adds fallback runnables to be invoked if the primary runnable fails.
inherited
withRetry({int maxRetries = 3, FutureOr<bool> retryIf(Object e)?, List<Duration?>? delayDurations, bool addJitter = false}) → RunnableRetry<PromptValue, ChatResult>: Adds retry logic to an existing runnable.
inherited

Operators

operator ==(Object other) → bool: The equality operator.
inherited

Constants

defaultMaxTokens → const int: The default max tokens to use unless another is specified.
defaultModel → const String: The default model to use unless another is specified.