Voyage AI reposted this
SPONSORED: Building GenAI is complicated. DataStax unveiled new integrations and solutions that make it easier for developers to get their GenAI apps to production.
Voyage is a team of leading AI researchers and engineers, dedicated to building embeddings models, customized for domains and companies, for better retrieval accuracy and RAG applications.
External link for Voyage AI
Palo Alto, CA, US
Voyage AI reposted this
SPONSORED: Building GenAI is complicated. DataStax unveiled new integrations and solutions that make it easier for developers to get their GenAI apps to production.
🌍📢 Launching our multilingual embeddings, voyage-multilingual-2! 👑 Average 5.6% gain on evaluated languages, including French, German, Japanese, Spanish, and Korean 📚 32K context length 🛒 On AWS Marketplace Check us out! 👉🏼 The first 50M tokens are on us. More details in our blog post: https://lnkd.in/gVviqtF9 We support academic retrieval research and benchmarking! Please email us at contact@voyageai.com for more 🆓 tokens. #RAG #LLM
🆕 📢 Launching Voyage AI’s new embedding model for finance retrieval and RAG: voyage-finance-2! 1. ✨ Superior finance retrieval quality with an average of 7% gain over OpenAI and 12% over Cohere 2. 📚 32K context length 3. 🛒 On AWS Marketplace #RAG #LLM More detail in the blog post: https://lnkd.in/gwN4V_pR Check us out 👉🏼 The first 50M tokens are on us! We’d also love to support academic retrieval research and benchmarking. Please write us at contact@voyageai.com for more free tokens.
🆕📢 We are thrilled to launch rerank-1, our best general-purpose and multilingual reranker! It refines the ranking of your search results with cross-encoder transformers. 🔹 Outperforms Cohere’s english-v3 on the English dataset. 🔹 Outperforms multilingual-v3 on multilingual datasets. 🔹 8K context-length. More in blog post 📖: https://lnkd.in/gGQJGgaQ
Voyage AI reposted this
I had a blast working with Vivek Gangasani getting Voyage AI models on Amazon #SageMaker #JumpStart! All of the current Voyage #embedding models and #rerankers are available on the #AWS #Marketplace, including the MTEB ranked #1 voyage-large-2-instruct and MTEB legal retrieval ranked #1 voyage-law-2.
Embedding models are the backbone of RAG architecture, enabling nuanced understanding and contextualization of text data for superior performance. VoyageAI embedding models have been topping the MTEB Leaderboard and are the recommended embedding models by Anthropic. Excited to share that we have onboarded VoyageAI embedding models to Amazon SageMaker Jumpstart and co-authored a blog and a notebook with Tengyu Ma and Wen Phan on implementing RAG solution with VoyageAI models deployed on SageMaker and Anthropic Claude3 Sonnet model on Amazon Bedrock . Read to learn more and try out the notebook: https://lnkd.in/gbCcjgnn Hadrien Almela Raj Dhingra Michael Tindal
🆕📢 The new voyage-large-2-instruct embedding model tops the MTEB leaderboard! https://lnkd.in/dRJ9s4mz — embedding dimension = 1024 (4x smaller than any other non-Voyage model in top-5) — 16K context length (2x of OpenAI v3 large) blog: https://lnkd.in/gdsSRRNg
Voyage AI reposted this
🆕📢 Voyage AI's new embedding model for legal and long-context retrieval and RAG: voyage-law-2! 1. 🥇 #1 on MTEB legal retrieval benchmark with a large margin (https://lnkd.in/g3_wXHqH ) 2. 📜 Best quality for long-context (16K) 3. ✨ Improved quality across all domains 4. 🛒 On AWS Marketplace More detail in blog post 📖: https://lnkd.in/gKhh7ftD Please check it out! The first 50M tokens are on us. We’d also love to support academic retrieval research and benchmarking. Please write to us at contact@voyageai.com for more free tokens.
Voyage AI reposted this
While we are seeing more general-purpose vector embedding models evolving in the ecosystem, it is not a surprise that there is a need for specialized models. Voyage AI, founded by Tengyu Ma and a team of leading researchers, is taking care of this. "𝘞𝘦 𝘵𝘩𝘪𝘯𝘬 𝘦𝘮𝘣𝘦𝘥𝘥𝘪𝘯𝘨𝘴 𝘢𝘳𝘦 𝘢𝘯 𝘶𝘯𝘥𝘦𝘳-𝘭𝘰𝘷𝘦𝘥 𝘣𝘶𝘵 𝘪𝘯𝘤𝘳𝘦𝘥𝘪𝘣𝘭𝘺 𝘪𝘮𝘱𝘰𝘳𝘵𝘢𝘯𝘵 𝘱𝘢𝘳𝘵 𝘰𝘧 𝘦𝘷𝘦𝘳𝘺𝘰𝘯𝘦’𝘴 𝘳𝘦𝘵𝘳𝘪𝘦𝘷𝘢𝘭 𝘴𝘵𝘢𝘤𝘬. 𝘚𝘰 𝘸𝘦 𝘴𝘦𝘵 𝘰𝘶𝘵 𝘵𝘰 𝘣𝘶𝘪𝘭𝘥 𝘫𝘶𝘴𝘵 𝘣𝘦𝘵𝘵𝘦𝘳 𝘦𝘮𝘣𝘦𝘥𝘥𝘪𝘯𝘨𝘴." 👍 Besides the general-purpose models, there are also two domain-specific embeddings available with a focus on legal domain and source code. "𝒗𝒐𝒚𝒂𝒈𝒆-2 𝘢𝘯𝘥 𝒗𝒐𝒚𝒂𝒈𝒆-𝒍𝒂𝒓𝒈𝒆-2 𝘢𝘳𝘦 𝘨𝘦𝘯𝘦𝘳𝘢𝘭𝘪𝘴𝘵 𝘦𝘮𝘣𝘦𝘥𝘥𝘪𝘯𝘨 𝘮𝘰𝘥𝘦𝘭𝘴 𝘵𝘩𝘢𝘵 𝘢𝘤𝘩𝘪𝘦𝘷𝘦 𝘴𝘵𝘢𝘵𝘦-𝘰𝘧-𝘵𝘩𝘦-𝘢𝘳𝘵 𝘱𝘦𝘳𝘧𝘰𝘳𝘮𝘢𝘯𝘤𝘦 𝘢𝘤𝘳𝘰𝘴𝘴 𝘥𝘰𝘮𝘢𝘪𝘯𝘴 𝘢𝘯𝘥 𝘳𝘦𝘵𝘢𝘪𝘯 𝘩𝘪𝘨𝘩 𝘦𝘧𝘧𝘪𝘤𝘪𝘦𝘯𝘤𝘺. 𝒗𝒐𝒚𝒂𝒈𝒆-𝒍𝒂𝒘-2 𝘪𝘴 𝘰𝘱𝘵𝘪𝘮𝘪𝘻𝘦𝘥 𝘧𝘰𝘳 𝘵𝘩𝘦 𝘭𝘦𝘨𝘢𝘭 𝘥𝘰𝘮𝘢𝘪𝘯, 𝘥𝘦𝘮𝘰𝘯𝘴𝘵𝘳𝘢𝘵𝘪𝘯𝘨 𝘴𝘶𝘱𝘦𝘳𝘪𝘰𝘳 𝘢𝘤𝘤𝘶𝘳𝘢𝘤𝘺 𝘪𝘯 𝘳𝘦𝘵𝘳𝘪𝘦𝘷𝘪𝘯𝘨 𝘭𝘦𝘨𝘢𝘭 𝘥𝘰𝘤𝘶𝘮𝘦𝘯𝘵𝘴. 𝒗𝒐𝒚𝒂𝒈𝒆-𝒄𝒐𝒅𝒆-2 𝘪𝘴 𝘰𝘱𝘵𝘪𝘮𝘪𝘻𝘦𝘥 𝘧𝘰𝘳 𝘵𝘩𝘦 𝘤𝘰𝘥𝘦 𝘧𝘪𝘦𝘭𝘥, 𝘰𝘧𝘧𝘦𝘳𝘪𝘯𝘨 4𝘹 𝘵𝘩𝘦 𝘤𝘰𝘯𝘵𝘦𝘹𝘵 𝘭𝘦𝘯𝘨𝘵𝘩 𝘧𝘰𝘳 𝘮𝘰𝘳𝘦 𝘧𝘭𝘦𝘹𝘪𝘣𝘭𝘦 𝘶𝘴𝘢𝘨𝘦, 𝘢𝘭𝘣𝘦𝘪𝘵 𝘢𝘵 𝘢 𝘳𝘦𝘭𝘢𝘵𝘪𝘷𝘦𝘭𝘺 𝘩𝘪𝘨𝘩𝘦𝘳 𝘭𝘢𝘵𝘦𝘯𝘤𝘺." https://lnkd.in/dzzw6EFg Voyager Embeddings with Qdrant ➡ supalink.me/Dajce25D 🙌 #vectorembeddings #vectorsearch #vectordatabase #ai #ml
Voyage AI reposted this
Rerankers refine the retrieval in RAG. 🆕📢 Excited to announce our first reranker, rerank-lite-1: state-of-the-art in retrieval accuracy on 27 datasets across domains (law, finance, tech, long docs, etc.), enhancing various search methods, vector-based or lexical. Besides superior quality, we offer 4K context length, flexible pricing based on tokens instead of searches, and 50M free tokens! 📄 API references: https://lnkd.in/gQnu7zf5 📖 Blog post: https://lnkd.in/gdN8TTxJ
Rerankers refine the retrieval in RAG. 🆕📢 Excited to announce our first reranker, rerank-lite-1: state-of-the-art in retrieval accuracy on 27 datasets across domains (law, finance, tech, long docs, etc.), enhancing various search methods, vector-based or lexical. Besides superior quality, we offer 4K context length, flexible pricing based on tokens instead of searches, and 50M free tokens! 📄 API references: https://lnkd.in/gQnu7zf5 📖 Blog post: https://lnkd.in/gdN8TTxJ