Gemini

Gemini Embedder embeds documents using Google’s Gemini embedding models through the Gemini API or Vertex AI.

Parameter	Type	Description	Default
`id`	`str`	The model ID to use for embeddings	`"gemini-embedding-001"`
`task_type`	`str`	Type of task for embedding generation	`"RETRIEVAL_QUERY"`
`title`	`Optional[str]`	Optional title for the content being embedded	`None`
`dimensions`	`Optional[int]`	Output dimensions of the embedding	`1536`
`api_key`	`Optional[str]`	Google API key	Environment variable `GOOGLE_API_KEY`
`request_params`	`Optional[Dict[str, Any]]`	Additional parameters for embedding requests	`None`
`client_params`	`Optional[Dict[str, Any]]`	Additional parameters for client initialization	`None`
`gemini_client`	`Optional[Client]`	Pre-configured `google.genai` client	`None`
`vertexai`	`bool`	Use the Vertex AI API. Also enabled by setting `GOOGLE_GENAI_USE_VERTEXAI=true`	`False`
`project_id`	`Optional[str]`	Google Cloud project ID for Vertex AI. Falls back to `GOOGLE_CLOUD_PROJECT`	`None`
`location`	`Optional[str]`	Google Cloud region for Vertex AI. Falls back to `GOOGLE_CLOUD_LOCATION`	`None`
`enable_batch`	`bool`	Embed multiple texts per API call when adding content to vector databases	`False`
`batch_size`	`int`	Number of texts per batch when `enable_batch` is `True`	`100`