embeddings

See the litellm documention.

embedding

embedding(
   model: str,
   input: list[str],
   *args,
   cache_enabled: bool,
   cache_path: typing.Union[str, pathlib.Path, NoneType],
   cache_key_prefix: typing.Optional[str],
   include_model_in_cache_key: bool,
   return_cache_key: bool,
   return_info: bool,
   enable_retries: bool,
   retry_on_exceptions: typing.Optional[list[Exception]],
   retry_on_all_exceptions: bool,
   max_retries: typing.Optional[int],
   retry_delay: typing.Optional[int],
   **kwargs
)

This function is a wrapper around a corresponding function in the litellm library, see this for a full list of the available arguments.

---

response, cache_hit, call_log = embedding(
    model="text-embedding-3-small",
    input=[
        "First string to embsed",
        "Second string to embed",
    ],
)
response.data[1]['embedding'][:10]

[-0.0012842135038226843,
 -0.013222426176071167,
 -0.008362501859664917,
 -0.04306064546108246,
 -0.004547890741378069,
 0.003748304443433881,
 0.03082892671227455,
 -0.012777778320014477,
 -0.01638176664710045,
 -0.01972052827477455]

async_embedding (async)

async_embedding(
   model: str,
   input: list[str],
   *args,
   cache_enabled: bool,
   cache_path: typing.Union[str, pathlib.Path, NoneType],
   cache_key_prefix: typing.Optional[str],
   include_model_in_cache_key: bool,
   return_cache_key: bool,
   return_info: bool,
   enable_retries: bool,
   retry_on_exceptions: typing.Optional[list[Exception]],
   retry_on_all_exceptions: bool,
   max_retries: typing.Optional[int],
   retry_delay: typing.Optional[int],
   timeout: typing.Optional[int],
   **kwargs
)

This function is a wrapper around a corresponding function in the litellm library, see this for a full list of the available arguments.

---

response, cache_hit, call_log = await async_embedding(
    model="text-embedding-3-small",
    input=[
        "First string to embed",
        "Second string to embed",
    ],
)
response.data[1]['embedding'][:10]

[-0.0012842135038226843,
 -0.013222426176071167,
 -0.008362501859664917,
 -0.04306064546108246,
 -0.004547890741378069,
 0.003748304443433881,
 0.03082892671227455,
 -0.012777778320014477,
 -0.01638176664710045,
 -0.01972052827477455]

batch_embeddings

batch_embeddings(
   model: str,
   input: list[str],
   batch_size: int,
   verbose: bool,
   **kwargs
)

Compute embeddings for a list of input strings in batches synchronously.

Arguments: - model (str): The embedding model to use. - input (list[str]): List of input strings to embed. - batch_size (int): Number of inputs per batch. - verbose (bool): If True, display a progress bar. - **kwargs: Additional keyword arguments passed to embedding.

Returns: list: List of embedding vectors for each input string.

---

embeddings, responses = batch_embeddings(
    model="text-embedding-3-small",
    input=[
        "First string to embed",
        "Second string to embed",
        "Third string to embed",
        "Fourth string to embed",
    ],
    batch_size=2,
    verbose=False,
)

async_batch_embeddings (async)

async_batch_embeddings(
   model: str,
   input: list[str],
   batch_size: int,
   verbose: bool,
   **kwargs
)

Compute embeddings for a list of input strings in batches asynchronously.

Arguments: - model (str): The embedding model to use. - input (list[str]): List of input strings to embed. - batch_size (int): Number of inputs per batch. - verbose (bool): If True, display a progress bar. - **kwargs: Additional keyword arguments passed to async_embedding.

Returns: list: List of embedding vectors for each input string.

---

embeddings, responses = await async_batch_embeddings(
    model="text-embedding-3-small",
    input=[
        "First string to embed",
        "Second string to embed",
        "Third string to embed",
        "Fourth string to embed",
    ],
    batch_size=2,
    verbose=False,
)