VoyagerRecursion Software
|
voyage-code-3MongoDB
|
|||||
Related Products
|
||||||
About
Voyager™ is a best-in-class middleware platform enabling the development of state-of-the-art mobile applications for the enterprise – applications that facilitate communication and collaboration through reliable, real-time, and secure sharing and distribution of information and content. Voyager™ provides simpler and better Service Oriented Architecture, allowing developers to solve problems without wasting time learning overly complex SOA code and configurations, and thereby carving out a distinct position for itself among all middleware tools and SOA products.
The driving purpose of Voyager™ is to increase design flexibility, reduce complexity, and accelerate the development of collaborative mobile applications across the enterprise, leveraging all connected device assets and facilitating M2M communications.
|
About
Voyage AI introduces voyage-code-3, a next-generation embedding model optimized for code retrieval. It outperforms OpenAI-v3-large and CodeSage-large by an average of 13.80% and 16.81% on a suite of 32 code retrieval datasets, respectively. It supports embeddings of 2048, 1024, 512, and 256 dimensions and offers multiple embedding quantization options, including float (32-bit), int8 (8-bit signed integer), uint8 (8-bit unsigned integer), binary (bit-packed int8), and ubinary (bit-packed uint8). With a 32 K-token context length, it surpasses OpenAI's 8K and CodeSage Large's 1K context lengths. Voyage-code-3 employs Matryoshka learning to create embeddings with a nested family of various lengths within a single vector. This allows users to vectorize documents into a 2048-dimensional vector and later use shorter versions (e.g., 256, 512, or 1024 dimensions) without re-invoking the embedding model.
|
|||||
Platforms Supported
Windows
Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Not Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
|||||
Audience
Application developers
|
Audience
AI researchers and developers in search of a solution providing an embedding model for code retrieval
|
|||||
Support
Phone Support
Supported
24/7 Live Support
Not Supported
Online
Not Supported
|
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
|||||
API
Offers API
Not Supported
|
API
Offers API
Not Supported
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
No information available.
Free Version
Not Supported
Free Trial
Not Supported
|
Pricing
No information available.
Free Version
Not Supported
Free Trial
Not Supported
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Not Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Supported
In Person
Not Supported
|
|||||
Company InformationRecursion Software
Founded: 2001
United States
www.recursionsw.com
|
Company InformationMongoDB
Founded: 2007
United States
blog.voyageai.com/2024/12/04/voyage-code-3/
|
|||||
Alternatives |
Alternatives |
|||||
|
|
|
|||||
|
|
|
|||||
|
|
||||||
|
|
|
|||||
Categories |
Categories |
|||||
Mobility Features
App Management
Not Supported
Barcode Scanning
Not Supported
Compliance Management
Not Supported
Content Management
Not Supported
Data Collection
Not Supported
Data Management
Not Supported
File Management
Not Supported
Forms Automation
Not Supported
Mobile Messaging
Not Supported
Remote Access
Supported
Remote Systems Monitoring
Not Supported
|
||||||
Integrations
Birdeye
Supported
Elasticsearch
Not Supported
Milvus
Not Supported
PackageLog
Supported
Qdrant
Not Supported
Vespa
Not Supported
|
Integrations
Birdeye
Not Supported
Elasticsearch
Supported
Milvus
Supported
PackageLog
Not Supported
Qdrant
Supported
Vespa
Supported
|
|||||
|
|
|