Embedding Model Configuration
Embedding settings control how your documents are converted to vectors.
Available Providers
| Provider | Models | Notes |
|---|---|---|
| OpenAI | text-embedding-3-small, text-embedding-3-large, text-embedding-ada-002 | Most popular, high quality |
| Cohere | embed-english-v3.0, embed-multilingual-v3.0 | Good multilingual support |
| Gemini | text-embedding-004 | Google's latest model |
| Ollama | nomic-embed-text, mxbai-embed-large | Self-hosted, privacy-focused |
Configuration Options
- Provider: Select your embedding service
- API Key: Enter your provider's API key
- Model: Choose the specific embedding model
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