Embedding models, much like generative models, rely on powerful neural network (and often transformer-based) architecture to capture and compress semantic context. And, much like generative models, they’re incredibly hard to train. We are a team of leading AI researchers who had experience in training embedding models for 5+ years. We make all the components right, from model architecture and data collection to selecting suitable loss functions and optimizers. Please see our blog post for more details.
Currently, we offer
voyage-2, powerful generalist embedding models, and
voyage-code-2, our most advanced embedding model optimized for code retrieval.
voyage-large-2is recommended for generalist tasks which have complicated documents or high quality requirements.
voyage-2is recommended for other generalist tasks, especially those with higher demand of throughput.
voyage-code-2is recommended for code-related tasks.
Other domain-optimized embedding models such as
voyage-law-02 will come Q1 2024.
We recommend cosine similarity.
Voyage AI embeddings are normalized to length 1, which means that:
- Cosine similarity can be computed slightly faster using just a dot product.
- Cosine similarity and Euclidean distance will result in the identical rankings.
Please see this page.
Upon creating an account, we instantly generate an API key for you. Once signed in, access your API key by clicking the "Create new API key" button in the dashboard.
Please see the rate limit guide.
To efficiently retrieve the nearest texts from a sizable corpus, you can use a vector database. Here are some common choices:
- Pinecone, a fully managed vector database
- Zilliz, a vector database for enterprise
- Chroma, an open-source embeddings store
- Elasticsearch, a popular search/analytics engine and vector database
- Milvus, a vector database built for scalable similarity search
- Qdrant, a vector search engine
API requests before 2/20/2024 will be free. After 2/20/2024, the first 50 million tokens are free for every account, and subsequent usage is priced on a per-token basis.
You can add payment methods to your account in the dashboard. We will bill monthly. You can expect a credit card charge around the 5th of each month for the usage of the past month.
Currently we offer fine-tuned embeddings through subscription. Please email Tengyu Ma (CEO) at [email protected] if you are interested.
Please email us at [email protected] for inquiries and customer support.
To subscribe to our newsletter, feel free to send us an email at [email protected].
Updated 12 days ago