Voyage AI by MongoDB Profile
Voyage AI by MongoDB

@VoyageAI

Followers
3K
Following
194
Media
40
Statuses
147

Building embedding/vectorization models, customized for your domain and company, for better retrieval quality https://t.co/MEAhTpBQqd

Palo Alto
Joined October 2023
Don't wanna be here? Send us removal request.
@VoyageAI
Voyage AI by MongoDB
5 months
We are excited to announce that Voyage AI is officially joining @MongoDB !. Joining @MongoDB enables us to bring our cutting-edge AI retrieval technology to a broader audience and seamlessly integrate it into mission-critical applications. Learn more:.
Tweet media one
4
11
87
@VoyageAI
Voyage AI by MongoDB
5 days
Try voyage-context-3 today! It’s great for long, unstructured documents, cross-chunk reasoning, and high-sensitivity retrieval tasks. The first 200 million tokens are free as always. Read our blog for more details.
Tweet card summary image
blog.voyageai.com
TL;DR – We’re excited to introduce voyage-context-3, a contextualized chunk embedding model that produces vectors for chunks that capture the full document context without any manual metadata…
1
1
4
@VoyageAI
Voyage AI by MongoDB
5 days
For document-level retrieval, voyage-context-3 outperforms OpenAI-v3-large, Cohere-v4, Jina-v3 late chunking, and Anthropic contextual retrieval by 12.56%, 5.64%, 6.76%, and 2.40%, respectively.
Tweet media one
1
0
2
@VoyageAI
Voyage AI by MongoDB
5 days
For chunk-level retrieval, voyage-context-3 outperforms on average OpenAI-v3-large, Cohere-v4, Jina-v3 late chunking, and contextual retrieval on all domains by 14.24%, 7.89%, 23.66%, and 20.54%, respectively.
Tweet media one
1
1
5
@VoyageAI
Voyage AI by MongoDB
5 days
Before: chunk overlaps, context summaries, metadata augmentation. Now: voyage-context-3 processes the full doc in one pass and generates a distinct embedding for each chunk. Each embedding encodes the chunk-level details AND full doc context, for more semantically aware
Tweet media one
2
4
28
@VoyageAI
Voyage AI by MongoDB
5 days
📢 voyage-context-3: contextualized chunk embeddings. - Auto captures of chunk level detail & global doc context, w/o metadata augmentation.- Beats OpenAI-v3-large by 14.24% & Cohere-v4 by 7.89%.- Binary 512-dim matches OpenAI (float, 3072-dim) in accuracy, but 192x cheaper in
Tweet media one
4
23
78
@VoyageAI
Voyage AI by MongoDB
14 days
🆕 Now in @MongoDB Atlas Search Playground: Chatbot Demo Builder. Explore Atlas Vector Search by building your own Q&A chatbot—no coding required. Use uploaded or sample datasets, and let the Builder handle index definitions, queries, and embeddings (powered by Voyage AI).
Tweet media one
0
2
4
@VoyageAI
Voyage AI by MongoDB
26 days
RT @ElevateHQ_: Huge thanks to @TengyuMa for coming on the Elevate Podcast! Check out the podcast episode here: htt….
0
1
0
@VoyageAI
Voyage AI by MongoDB
2 months
voyage-3.5 and voyage-3.5-lite are available today! The first 200 million tokens are free. Get all the details in our latest blog:
Tweet card summary image
blog.voyageai.com
TL;DR – We’re excited to introduce voyage-3.5 and voyage-3.5-lite, the latest generation of our embedding models. These models offer improved retrieval quality over voyage-3 and voyage-3-lite at th…
1
0
0
@VoyageAI
Voyage AI by MongoDB
2 months
Across evaluated domains & multilingual tasks, voyage-3.5 outperforms OpenAI-v3-large, voyage-3, and Cohere-v4 by an average of 8.26%, 2.66%, and 1.63%, respectively; and voyage-3.5-lite outperforms OpenAI-v3-large and voyage-3-lite by an average of 6.34% and 4.28%, respectively.
Tweet media one
1
0
0
@VoyageAI
Voyage AI by MongoDB
2 months
voyage-3.5 improves retrieval quality over voyage-3 by 2.66%, and voyage-3.5-lite improves over voyage-3-lite by 4.28%—both maintaining a 32K context length and their respective price points of $0.06 and $0.02 per 1M tokens.
Tweet media one
1
0
0
@VoyageAI
Voyage AI by MongoDB
2 months
📢 Meet voyage-3.5 and voyage-3.5-lite!.• flexible dim. and quantizations.• voyage-3.5 & 3.5-lite (int8, 2048 dim.) are 8% & 6% more accurate than OpenAI-v3-large, and 2.2x & 6.5x cheaper, resp. Also 83% less vectorDB cost! .• 3.5-lite ~ Cohere-v4 in quality, but 83% cheaper.
Tweet media one
2
13
42
@VoyageAI
Voyage AI by MongoDB
3 months
RT @llama_index: Learn how to do multi-modal retrieval using @VoyageAI's multi-modal embeddings and @MongoDB's multi-modal indexes!. In thi….
0
7
0
@VoyageAI
Voyage AI by MongoDB
3 months
Voyage AI joined @MongoDB just 2 months ago, and we’re accelerating our mission of building the best embedding models for all developers!. Here’s what’s already in motion:.• 100x API scaling.• New, advanced models.• Built-in embeddings in Atlas Vector Search.• Direct API
Tweet media one
0
2
15
@VoyageAI
Voyage AI by MongoDB
4 months
🧑‍💻Better code search means a better developer experience. Our partner @continuedev builds the leading open-source AI code assistant and voyage-code-3 and rerank-2 are two models helping them do it! . Learn more in their blog:
Tweet card summary image
blog.continue.dev
As your codebase grows, finding the right information at the right time becomes increasingly difficult. Everyone who's spent hours hunting for a function they wrote months ago or searching for...
@continuedev
Continue
4 months
@metcalfc wrote a deep dive on why your custom AI code assistant should include embeddings and a reranker from @VoyageAI🥇
Tweet media one
0
1
11
@VoyageAI
Voyage AI by MongoDB
5 months
RT @MongoDB: The performance of AI-driven apps hinges on vector efficiency. Join us tomorrow to learn how MongoDB Atlas Vector Search + @Vo….
0
3
0
@VoyageAI
Voyage AI by MongoDB
6 months
@pinecone With the Pinecone Model Gallery, you can create an index tailored for the latest Voyage models in just a few clicks. Simply search for the model, hit “Create Index”, and Pinecone auto-fills key settings like dimensionality & similarity metric.
Tweet media one
1
1
1
@VoyageAI
Voyage AI by MongoDB
6 months
We just realized that many people don’t realize how easy it is to use @VoyageAI embeddings with @pinecone !.
3
3
9