Pinecone Nexus is in Public Preview.
A knowledge engine that compiles untapped, distributed enterprise data into a layer agents query directly. Answers get faster, cheaper, and more accurate.
Read more: pinecone.io/blog/pinecone-โฆ
Let's talk chunkingโAn essential technique that helps optimize the relevance of the content we get back from a vector database once we use the LLM to embed content:
Introducing Pinecone serverless, a completely reinvented vector database that lets you easily build fast and accurate GenAI applications at up to 50x lower cost. Available today in public preview, free to try with $100 in usage credits.
pinecone.io/blog/serverlesโฆ
Exciting news! ๐ Pinecone has raised $100M in Series B funding at a $750M valuation, led by @a16z, with participation from @ICONIQGrowth, @MenloVentures, and @Wing_VC. We're on a mission to provide long-term memory for AI.
(1/7)
โจ Introducing our free course on Natural Language Processing (NLP) for Semantic Search!
๐ง Covers everything you need to build state-of-the-art language models, from machine translation to question-answering, and more.
๐ Start here:
Pinecone giveaway! ๐ We're giving away top-quality Marine Layer hoodies to 3 people who:
1. Follow @pinecone
AND
2. Retweet this tweet
Winners will be announced on June 2nd!
The biggest deal about this is the ability to create your own plugins. The Retrieval Plugin is a kind of starter kit, with built-in integrations to the Pinecone vector database:
Data Prep 101 with @jamescalam: Learn how to prepare text using @langchain data loaders, tokenization using the tiktoken tokenizers, chunking with LangChain text splitters, and storing data with @huggingface datasets.
๐๐ค Hold on to your hats, folks! @OpenAI's ChatGPT plugins are REVOLUTIONIZING the AI landscape, and Pinecone is your express ticket ๐๏ธ to harnessing their power in production! ๐ Ready for lift-off? ๐ Let's dive in and explore this game-changing combo! ๐ฅ๐ #AI#NextLevelTech