GeminiEmbedder
class is used to embed text data into vectors using Google’s Gemini API. You can use it through Google AI Studio or Google Cloud Vertex AI.
Parameter | Type | Default | Description |
---|---|---|---|
id | str | gemini-embedding-exp-03-07 | The Gemini embedding model ID to use |
task_type | str | RETRIEVAL_QUERY | The type of task for which embeddings are being generated |
title | Optional[str] | None | Optional title for the embedding task |
dimensions | Optional[int] | 1536 | The dimensionality of the generated embeddings |
api_key | Optional[str] | None | The API key used for authenticating requests |
request_params | Optional[Dict[str, Any]] | None | Optional dictionary of parameters for the embedding request |
client_params | Optional[Dict[str, Any]] | None | Optional dictionary of parameters for the Gemini client |
gemini_client | Optional[GeminiClient] | None | Optional pre-configured Gemini client instance |
vertexai | bool | False | Whether to use Vertex AI instead of Google AI Studio |
project_id | Optional[str] | None | Google Cloud project ID for Vertex AI |
location | Optional[str] | None | Google Cloud region for Vertex AI |