Praison AI

embedding • AI Agent SDK

embedding: Generate embeddings for text using LiteLLM.

embedding

Function

</div>

This function is defined in the embed module.

Generate embeddings for text using LiteLLM.

This is the primary embedding function that supports all LiteLLM embedding providers (OpenAI, Azure, Cohere, Voyage, etc.).

Signature

python
def embedding(input: Union[str, List[str]], model: str, dimensions: Optional[int], encoding_format: str, timeout: float, api_key: Optional[str], api_base: Optional[str], metadata: Optional[Dict[str, Any]]) -> EmbeddingResult

Parameters

ParamField Union

Text or list of texts to embed

ParamField str

Model name (e.g., “text-embedding-3-small”, “text-embedding-3-large”)

ParamField Optional[int]

Optional output dimensions (for models that support it)

ParamField str

“float” or “base64”

ParamField float

Request timeout in seconds

ParamField Optional[str]

Optional API key override

ParamField Optional[str]

Optional API base URL override

ParamField Optional

Optional metadata for tracing **kwargs: Additional arguments passed to litellm.embedding()

Returns

ResponseField EmbeddingResult

EmbeddingResult with embeddings list, model, usage, and metadata

Usage

python
>>> from praisonaiagents import embedding
    >>> result = embedding("Hello, world!")
    >>> print(len(result.embeddings[0]))
    1536

    >>> result = embedding(["Hello", "World"], model="text-embedding-3-large")
    >>> print(len(result.embeddings))
    2

Uses

  • litellm.embedding
  • EmbeddingResult

Used By

Source

View on GitHub

praisonaiagents/embedding/embed.py at line 13