All models
OpenAI
Text Embedding 3 Large
Accurate OpenAI embeddings
This model is not in the catalog right now.
See available modelsAbout the model
Text Embedding 3 Large is the flagship embeddings model from OpenAI, focused on retrieval quality. It turns text into vectors and accurately scores the semantic similarity between a query and documents, which matters for semantic search and RAG. The vector dimension is adjustable, so you can trade off accuracy against storage size. The resulting representations work well for clustering, recommendations, deduplication and classification. It handles many languages confidently, including Russian.
Strengths
- Highest retrieval quality in the OpenAI lineup
- Adjustable vector dimension
- Accurate semantic similarity scoring
- Vectors for clustering and recommendations
- Suitable for RAG and semantic search
- Works with many languages, including Russian
Where to use it
- Semantic search across documents
- RAG pipelines and question-answering systems
- Clustering and topic grouping
- Recommendation systems
- Deduplication and similarity search
- Text classification based on vectors