DocumentationAPI Reference📓 Tutorials🧑‍🍳 Cookbook🤝 Integrations💜 Discord🎨 Studio
API Reference

Together AI

Together AI integration for Haystack

Module haystack_integrations.components.generators.together_ai.generator

TogetherAIGenerator

Provides an interface to generate text using an LLM running on Together AI.

Usage example:

from haystack_integrations.components.generators.together_ai import TogetherAIGenerator

generator = TogetherAIGenerator(model="deepseek-ai/DeepSeek-R1",
                            generation_kwargs={
                            "temperature": 0.9,
                            })

print(generator.run("Who is the best Italian actor?"))

TogetherAIGenerator.__init__

def __init__(api_key: Secret = Secret.from_env_var("TOGETHER_API_KEY"),
             model: str = "meta-llama/Llama-3.3-70B-Instruct-Turbo",
             api_base_url: Optional[str] = "https://api.together.xyz/v1",
             streaming_callback: Optional[StreamingCallbackT] = None,
             system_prompt: Optional[str] = None,
             generation_kwargs: Optional[Dict[str, Any]] = None,
             timeout: Optional[float] = None,
             max_retries: Optional[int] = None)

Initialize the TogetherAIGenerator.

Arguments:

  • api_key: The Together API key.
  • model: The name of the model to use.
  • api_base_url: The base URL of the Together AI API.
  • streaming_callback: A callback function that is called when a new token is received from the stream. The callback function accepts StreamingChunk as an argument.
  • system_prompt: The system prompt to use for text generation. If not provided, the system prompt is omitted, and the default system prompt of the model is used.
  • generation_kwargs: Other parameters to use for the model. These parameters are all sent directly to the Together AI endpoint. See Together AI documentation for more details. Some of the supported parameters:
  • max_tokens: The maximum number of tokens the output text can have.
  • temperature: What sampling temperature to use. Higher values mean the model will take more risks. Try 0.9 for more creative applications and 0 (argmax sampling) for ones with a well-defined answer.
  • top_p: An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So, 0.1 means only the tokens comprising the top 10% probability mass are considered.
  • n: How many completions to generate for each prompt. For example, if the LLM gets 3 prompts and n is 2, it will generate two completions for each of the three prompts, ending up with 6 completions in total.
  • stop: One or more sequences after which the LLM should stop generating tokens.
  • presence_penalty: What penalty to apply if a token is already present at all. Bigger values mean the model will be less likely to repeat the same token in the text.
  • frequency_penalty: What penalty to apply if a token has already been generated in the text. Bigger values mean the model will be less likely to repeat the same token in the text.
  • logit_bias: Add a logit bias to specific tokens. The keys of the dictionary are tokens, and the values are the bias to add to that token.
  • timeout: Timeout for together.ai Client calls, if not set it is inferred from the OPENAI_TIMEOUT environment variable or set to 30.
  • max_retries: Maximum retries to establish contact with Together AI if it returns an internal error, if not set it is inferred from the OPENAI_MAX_RETRIES environment variable or set to 5.

TogetherAIGenerator.to_dict

def to_dict() -> Dict[str, Any]

Serialize this component to a dictionary.

Returns:

The serialized component as a dictionary.

TogetherAIGenerator.from_dict

@classmethod
def from_dict(cls, data: dict[str, Any]) -> "TogetherAIGenerator"

Deserialize this component from a dictionary.

Arguments:

  • data: The dictionary representation of this component.

Returns:

The deserialized component instance.

TogetherAIGenerator.run

@component.output_types(replies=list[str], meta=list[dict[str, Any]])
def run(*,
        prompt: str,
        system_prompt: str | None = None,
        streaming_callback: StreamingCallbackT | None = None,
        generation_kwargs: dict[str, Any] | None = None) -> dict[str, Any]

Generate text completions synchronously.

Arguments:

  • prompt: The input prompt string for text generation.
  • system_prompt: An optional system prompt to provide context or instructions for the generation. If not provided, the system prompt set in the __init__ method will be used.
  • streaming_callback: A callback function that is called when a new token is received from the stream. If provided, this will override the streaming_callback set in the __init__ method.
  • generation_kwargs: Additional keyword arguments for text generation. These parameters will potentially override the parameters passed in the __init__ method. Supported parameters include temperature, max_new_tokens, top_p, etc.

Returns:

A dictionary with the following keys:

  • replies: A list of generated text completions as strings.
  • meta: A list of metadata dictionaries containing information about each generation, including model name, finish reason, and token usage statistics.

TogetherAIGenerator.run_async

@component.output_types(replies=list[str], meta=list[dict[str, Any]])
async def run_async(
        *,
        prompt: str,
        system_prompt: str | None = None,
        streaming_callback: StreamingCallbackT | None = None,
        generation_kwargs: dict[str, Any] | None = None) -> dict[str, Any]

Generate text completions asynchronously.

Arguments:

  • prompt: The input prompt string for text generation.
  • system_prompt: An optional system prompt to provide context or instructions for the generation.
  • streaming_callback: A callback function that is called when a new token is received from the stream. If provided, this will override the streaming_callback set in the __init__ method.
  • generation_kwargs: Additional keyword arguments for text generation. These parameters will potentially override the parameters passed in the __init__ method. Supported parameters include temperature, max_new_tokens, top_p, etc.

Returns:

A dictionary with the following keys:

  • replies: A list of generated text completions as strings.
  • meta: A list of metadata dictionaries containing information about each generation, including model name, finish reason, and token usage statistics.

Module haystack_integrations.components.generators.together_ai.chat.chat_generator

TogetherAIChatGenerator

Enables text generation using Together AI generative models. For supported models, see Together AI docs.

Users can pass any text generation parameters valid for the Together AI chat completion API directly to this component using the generation_kwargs parameter in __init__ or the generation_kwargs parameter in run method.

Key Features and Compatibility:

  • Primary Compatibility: Designed to work seamlessly with the Together AI chat completion endpoint.
  • Streaming Support: Supports streaming responses from the Together AI chat completion endpoint.
  • Customizability: Supports all parameters supported by the Together AI chat completion endpoint.

This component uses the ChatMessage format for structuring both input and output, ensuring coherent and contextually relevant responses in chat-based text generation scenarios. Details on the ChatMessage format can be found in the Haystack docs

For more details on the parameters supported by the Together AI API, refer to the Together AI API Docs.

Usage example:

from haystack_integrations.components.generators.together_ai import TogetherAIChatGenerator
from haystack.dataclasses import ChatMessage

messages = [ChatMessage.from_user("What's Natural Language Processing?")]

client = TogetherAIChatGenerator()
response = client.run(messages)
print(response)

>>{'replies': [ChatMessage(_content='Natural Language Processing (NLP) is a branch of artificial intelligence
>>that focuses on enabling computers to understand, interpret, and generate human language in a way that is
>>meaningful and useful.', _role=<ChatRole.ASSISTANT: 'assistant'>, _name=None,
>>_meta={'model': 'meta-llama/Llama-3.3-70B-Instruct-Turbo', 'index': 0, 'finish_reason': 'stop',
>>'usage': {'prompt_tokens': 15, 'completion_tokens': 36, 'total_tokens': 51}})]}

TogetherAIChatGenerator.__init__

def __init__(*,
             api_key: Secret = Secret.from_env_var("TOGETHER_API_KEY"),
             model: str = "meta-llama/Llama-3.3-70B-Instruct-Turbo",
             streaming_callback: Optional[StreamingCallbackT] = None,
             api_base_url: Optional[str] = "https://api.together.xyz/v1",
             generation_kwargs: Optional[Dict[str, Any]] = None,
             tools: Optional[Union[List[Tool], Toolset]] = None,
             timeout: Optional[float] = None,
             max_retries: Optional[int] = None,
             http_client_kwargs: Optional[Dict[str, Any]] = None)

Creates an instance of TogetherAIChatGenerator. Unless specified otherwise,

the default model is meta-llama/Llama-3.3-70B-Instruct-Turbo.

Arguments:

  • api_key: The Together API key.
  • model: The name of the Together AI chat completion model to use.
  • streaming_callback: A callback function that is called when a new token is received from the stream. The callback function accepts StreamingChunk as an argument.
  • api_base_url: The Together AI API Base url. For more details, see Together AI docs.
  • generation_kwargs: Other parameters to use for the model. These parameters are all sent directly to the Together AI endpoint. See Together AI API docs for more details. Some of the supported parameters:
  • max_tokens: The maximum number of tokens the output text can have.
  • temperature: What sampling temperature to use. Higher values mean the model will take more risks. Try 0.9 for more creative applications and 0 (argmax sampling) for ones with a well-defined answer.
  • top_p: An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
  • stream: Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.
  • safe_prompt: Whether to inject a safety prompt before all conversations.
  • random_seed: The seed to use for random sampling.
  • tools: A list of tools or a Toolset for which the model can prepare calls. This parameter can accept either a list of Tool objects or a Toolset instance.
  • timeout: The timeout for the Together AI API call.
  • max_retries: Maximum number of retries to contact Together AI after an internal error. If not set, it defaults to either the OPENAI_MAX_RETRIES environment variable, or set to 5.
  • http_client_kwargs: A dictionary of keyword arguments to configure a custom httpx.Clientor httpx.AsyncClient. For more information, see the HTTPX documentation.

TogetherAIChatGenerator.to_dict

def to_dict() -> Dict[str, Any]

Serialize this component to a dictionary.

Returns:

The serialized component as a dictionary.