embedding • AI Agent SDK

embedding: Generate embeddings for text using LiteLLM.

embedding

Function

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

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

input · Union · required

Text or list of texts to embed

model · str · default: "'text-embedding-3-small'"

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

dimensions · Optional

Optional output dimensions (for models that support it)

encoding_format · str · default: "'float'"

“float” or “base64”

timeout · float · default: "600.0"

Request timeout in seconds

api_key · Optional

Optional API key override

api_base · Optional

Optional API base URL override

metadata · Optional

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

Returns

Returns · EmbeddingResult

EmbeddingResult with embeddings list, model, usage, and metadata

Usage

>>> 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

• EmbeddingAgent.embed
• EmbeddingAgent.embed_batch
• embedding
• Memory.search_short_term

Source

View on GitHub

praisonaiagents/embedding/embed.py at line 13