Model Flexibility
Embedding Models
Select from industry-leading embedding models to optimize semantic understanding for your specific use case.
Supported Models
All major providers supported out of the box
| Model | Dimensions | Quality | Speed | Best For |
|---|---|---|---|---|
| OpenAI text-embedding-3-large | 3072 | Excellent | Fast | Best overall quality, great for most use cases |
| OpenAI text-embedding-3-small | 1536 | Very Good | Very Fast | Great balance of quality and cost |
| Cohere embed-multilingual-v3 | 1024 | Excellent | Fast | Best for multilingual content |
| Voyage AI voyage-large-2 | 1536 | Excellent | Fast | Optimized for code and technical docs |
The Challenge
❌ With Fixed Embeddings:
- • Locked into one provider
- • Full re-index to switch models
- • Can't optimize for your data
- • No way to compare performance
✓ With RAG Engine:
- • Switch providers anytime
- • Automatic re-indexing
- • Choose best model for your data
- • A/B test model performance
How It Works
Flexible embedding management
1
Easy Switching
Change embedding models anytime - we handle the re-indexing automatically.
2
Custom Models
Bring your own fine-tuned embeddings or self-hosted models.
3
Hybrid Embeddings
Combine multiple embedding models for different content types.
4
Auto-Optimize
A/B test models to find the best performer for your data.
Use Cases
Multilingual
Use Cohere for 100+ languages.
Code Search
Voyage AI for technical docs.
Cost Optimization
Smaller models for large datasets.
Data Privacy
Self-hosted models for sensitive data.
Comparison
Most flexible embedding support
| Feature | RAG Engine | LangChain | LlamaIndex | Pinecone |
|---|---|---|---|---|
| Multiple embedding providers | ✓ | ✓ | ✓ | ~ |
| One-click model switching | ✓ | ✗ | ✗ | ✗ |
| Custom model support | ✓ | ✓ | ✓ | ✗ |
| Automatic re-indexing | ✓ | ✗ | ✗ | ✗ |
| Embedding A/B testing | ✓ | ✗ | ✗ | ✗ |
Works Great With
Ready to Get Started?
Choose the perfect embedding model for your use case today.
Get Started Free