Skip to main content

Embedding Model Configuration

Embedding settings control how your documents are converted to vectors.

Embedding Settings

Available Providers​

ProviderModelsNotes
OpenAItext-embedding-3-small, text-embedding-3-large, text-embedding-ada-002Most popular, high quality
Cohereembed-english-v3.0, embed-multilingual-v3.0Good multilingual support
Geminitext-embedding-004, gemini-embedding-001, gemini-embedding-2-previewMultimodal support (gemini-embedding-2-preview)
Ollamanomic-embed-text, mxbai-embed-largeSelf-hosted, privacy-focused

Configuration Options​

  1. Provider: Select your embedding service
  2. API Key: Enter your provider's API key
  3. Model: Choose the specific embedding model
  4. Dimensions: For supported models, select output dimensions (768, 1536, or 3072)
Dimension Selection

The dimensions option appears when you select a model that supports configurable output dimensionality. Currently, this includes Gemini gemini-embedding-001 and gemini-embedding-2-preview.

Choosing an Embedding Model​

text-embedding-3-small (OpenAI)​

  • Dimensions: 1536
  • Best for: General purpose, cost-effective
  • Quality: High

text-embedding-3-large (OpenAI)​

  • Dimensions: 3072
  • Best for: Maximum accuracy needs
  • Quality: Highest

embed-multilingual-v3.0 (Cohere)​

  • Best for: Multi-language documents
  • Supports: 100+ languages

Ollama Models​

  • Best for: Privacy-conscious deployments
  • Requires: Self-hosted Ollama server

Gemini Embedding Models​

gemini-embedding-001​

  • Dimensions: 768 / 1536 / 3072 (configurable)
  • Best for: Production text embedding with flexible dimensions
  • Supports: output_dimensionality parameter

gemini-embedding-2-preview (Multimodal)​

  • Dimensions: 768 / 1536 / 3072 (configurable, default 3072)
  • Best for: Visual document intelligence — images embedded alongside text
  • Max tokens: 8,192
  • Supports: Multimodal embedding (images + text), output_dimensionality parameter

See Multimodal Embeddings for details on image extraction and visual search.

Multimodal Badge

When selecting an embedding model, look for the purple Multimodal badge in the model dropdown. This badge indicates models that support true multimodal embedding with images alongside text.