TogetherEmbeddings#

class langchain_together.embeddings.TogetherEmbeddings[source]#

Bases: BaseModel, Embeddings

Together embedding model integration.

Setup:

Install langchain_together and set environment variable TOGETHER_API_KEY.

pip install -U langchain_together
export TOGETHER_API_KEY="your-api-key"

Key init args — completion params:

model: str: Name of Together model to use.

Key init args — client params:

api_key: Optional[SecretStr]

See full list of supported init args and their descriptions in the params section.

Instantiate:

from __module_name__ import TogetherEmbeddings

embed = TogetherEmbeddings(
    model="togethercomputer/m2-bert-80M-8k-retrieval",
    # api_key="...",
    # other params...
)

Embed single text:

input_text = "The meaning of life is 42"
vector = embed.embed_query(input_text)
print(vector[:3])

[-0.024603435769677162, -0.007543657906353474, 0.0039630369283258915]

Embed multiple texts:

 input_texts = ["Document 1...", "Document 2..."]
vectors = embed.embed_documents(input_texts)
print(len(vectors))
# The first 3 coordinates for the first vector
print(vectors[0][:3])

2
[-0.024603435769677162, -0.007543657906353474, 0.0039630369283258915]

Async:

 vector = await embed.aembed_query(input_text)
print(vector[:3])

 # multiple:
 # await embed.aembed_documents(input_texts)

[-0.009100092574954033, 0.005071679595857859, -0.0029193938244134188]

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

param allowed_special: Literal['all'] | Set[str] = {}#: Not yet supported.

param chunk_size: int = 1000#

Maximum number of texts to embed in each batch.

Not yet supported.

param default_headers: Mapping[str, str] | None = None#

param default_query: Mapping[str, object] | None = None#

param dimensions: int | None = None#

The number of dimensions the resulting output embeddings should have.

Not yet supported.

param disallowed_special: Literal['all'] | Set[str] | Sequence[str] = 'all'#: Not yet supported.

param embedding_ctx_length: int = 4096#

The maximum number of tokens to embed at once.

Not yet supported.

param http_async_client: Any | None = None#: Optional httpx.AsyncClient. Only used for async invocations. Must specify http_client as well if you’d like a custom client for sync invocations.

param http_client: Any | None = None#: Optional httpx.Client. Only used for sync invocations. Must specify http_async_client as well if you’d like a custom client for async invocations.

param max_retries: int = 2#: Maximum number of retries to make when generating.

param model: str = 'togethercomputer/m2-bert-80M-8k-retrieval'#: Embeddings model name to use. Instead, use ‘togethercomputer/m2-bert-80M-8k-retrieval’ for example.

param model_kwargs: Dict[str, Any] [Optional]#: Holds any model parameters valid for create call not explicitly specified.

param request_timeout: float | Tuple[float, float] | Any | None = None (alias 'timeout')#: Timeout for requests to Together embedding API. Can be float, httpx.Timeout or None.

param show_progress_bar: bool = False#

Whether to show a progress bar when embedding.

Not yet supported.

param skip_empty: bool = False#

Whether to skip empty strings when embedding or raise an error. Defaults to not skipping.

Not yet supported.

param together_api_base: str [Optional] (alias 'base_url')#: Endpoint URL to use.

param together_api_key: SecretStr | None [Optional] (alias 'api_key')#

Together AI API key.

Automatically read from env variable TOGETHER_API_KEY if not provided.

async aembed_documents(texts: List[str]) → List[List[float]][source]#

Embed a list of document texts using passage model asynchronously.

Parameters:: texts (List[str]) – The list of texts to embed.
Returns:: List of embeddings, one for each text.
Return type:: List[List[float]]

async aembed_query(text: str) → List[float][source]#

Asynchronous Embed query text using query model.

Parameters:: text (str) – The text to embed.
Returns:: Embedding for the text.
Return type:: List[float]

embed_documents(texts: List[str]) → List[List[float]][source]#

Embed a list of document texts using passage model.

Parameters:: texts (List[str]) – The list of texts to embed.
Returns:: List of embeddings, one for each text.
Return type:: List[List[float]]

embed_query(text: str) → List[float][source]#

Embed query text using query model.

Parameters:: text (str) – The text to embed.
Returns:: Embedding for the text.
Return type:: List[float]

Examples using TogetherEmbeddings

TogetherEmbeddings