GeminiEmbeddingFunction

Model2VecEmbeddingFunction is a class in pymilvus that handles encoding text into embeddings using the GeminiEmbeddingFunction module to support embedding retrieval in Milvus.

pymilvus.model.dense.GeminiEmbeddingFunction

Constructor

Constructs an GeminiEmbeddingFunction for common use cases.

GeminiEmbeddingFunction(
    model_name: str = "gemini-embedding-exp-03-07",
    api_key: Optional[str] = None,
    config: Optional['types.EmbedContentConfig']=None,
    **kwargs,
)

PARAMETERS:

• model_name (string) -

  The name of the Gemini model to use for encoding. Valid options are gemini-embedding-exp-03-07(default), models/embedding-001, and models/text-embedding-004.

• api_key (string)-**

The API key for accessing the Gemini API.

• config (types.EmbedContentConfig) -**

  Optional configuration for the embedding model.

  • The output_dimensionality can be specified to the number of resulting output embeddings.

    Model Name	Dimensions
    emini-embedding-exp-03-07	3072(default),1536,768
    models/embedding-001	768
    models/text-embedding-004	768

  • The task_type can be specified to generate optimized embeddings for specific tasks, saving you time and cost and improving performance. Only supported in the gemini-embedding-exp-03-07 model.

    Task Type	Description
    SEMANTIC_SIMILARITY	Used to generate embeddings that are optimized to assess text similarity.
    CLASSIFICATION	Used to generate embeddings that are optimized to classify texts according to preset labels.
    CLUSTERING	Used to generate embeddings that are optimized to cluster texts based on their similarities.
    RETRIEVAL_DOCUMENT, RETRIEVAL_QUERY, QUESTION_ANSWERING, and FACT_VERIFICATION	Used to generate embeddings that are optimized for document search or information retrieval.
    CODE_RETRIEVAL_QUERY	Used to retrieve a code block based on a natural language query, such as sort an array or reverse a linked list. Embeddings of the code blocks are computed using RETRIEVAL_DOCUMENT.

Examples

from pymilvus import model

gemini_ef = model.dense.GeminiEmbeddingFunction(
    model_name="gemini-embedding-exp-03-07",
    api_key="YOUR_API_KEY",
)