Voyageai models

This model takes in written text only and gives back the same candidates reordered, most relevant first. Its work is the second pass of a search, where the first results are sorted again so the best matches sit on top, and it reads about 32 pages of text at once. It is tuned for quick turnaround on busy pages and is a little more accurate than the earlier lite version. It cannot write new text or read pictures, so a job that needs a written answer calls for a different kind of model.

Reorders search candidates by relevance as the quality-tuned reranker that upgrades rerank-2.5, gaining most on long documents and code, scoring each query and document pair up to 32K tokens and following instructions on what counts as relevant

Voyage-code-4 turns computer code into a fingerprint of its meaning, so a search finds the code that does what you describe, not just code with the same words. Voyage built it for coding assistants and code search, and it reads about 30 pages at a time. Pick it to search through a code base. For ordinary writing, voyage-4 is the general-purpose model.

Rerank 2.5 Lite takes a question and a list of candidate documents and puts them in order of how well they answer it, which sharpens the results of a search. You can add written instructions to steer it, and a question and one document together can run to about 30 pages. It is tuned for speed.

Rerank 2.5 takes a question and a list of candidate documents and puts them in order of how well they answer it, which sharpens the results of a search. You can add written instructions to steer it, such as which kind of document to favour. A question and one document together can run to about 30 pages.

Voyage-multimodal-3.5 turns text and pictures into a fingerprint of their meaning, including pages where the two are mixed, such as screenshots of PDFs, figures and tables. One search can then cover both the words and the visuals. Pick it when your material is more than plain text.

Voyage-4-lite turns text into a fingerprint of its meaning, so search finds writing that means the same thing, in many languages. It is the lightest of the three Voyage-4 models, tuned for speed, and it reads about 30 pages at a time. The three share one meaning space, so questions asked with this one can search documents stored by voyage-4-large.

Voyage-4 turns text into a fingerprint of its meaning, so search finds writing that means the same thing, in many languages. It is the middle size of the three Voyage-4 models, with quality close to the older voyage-3-large, and it reads about 30 pages at a time. The three share one meaning space, so you can mix them.

Voyage-4-large turns text into a fingerprint of its meaning, so search finds writing that means the same thing, in many languages. It is the largest of the three Voyage-4 models and gives the best accuracy of them, reading about 30 pages at a time. The three share one meaning space, so documents stored with this one can be searched with voyage-4-lite.