About Pinecone
Pinecone is a Vector Database that’s revolutionizing how developers build Search systems. Our managed vector database provides customers with easy-to-use capabilities that until now have only been in the hands of a few tech giants.
Highlights
- The Pinecone serverless vector database is the developer-favorite vector database that is easy to use at any scale, with a large user community. Fully managed vector database with intuitive API, console, and SDKs.
- The Pinecone serverless vector database provides best-in-class performance with 50x lower cost at any scale. Pinecone delivers fast vector search with filtering, live index updates, and keyword boosting (hybrid search).
- Pinecone is the most popular vector database for AI search, recommenders, and Retrieval Augmented Generation (RAG) applications. <br><br> Enterprise-grade security and compliance: SOC 2 Type II and HIPAA certified and built to keep data from your Vector Database secure
Pinecone serverless is the most popular vector database, used by engineering teams to solve two of the biggest challenges in deploying GenAI solutions – data security and hallucinations – by allowing them to store, search, and find the most relevant information from company data and send only that context to Large Language Models (LLMs) with every query.
This workflow is called Retrieval Augmented Generation (RAG), and with the Pinecone vector database, it aids in providing relevant, accurate, and fast responses from search or GenAI applications to end users.
Vector databases are purpose-built for storing and searching through vector embeddings, AI representations of data. This method of information retrieval (IR) is called vector search. Vector search is the new standard for finding the most relevant data for GenAI applications or any kind of search application.
Pinecone Vector Database Usage-based Billing: Charges are calculated by pod price multiplied by pod count. Invoices reflect total index runtime, rounded to 15-minute increments.
Pinecone
The vector database for machine learning applications. Build vector-based personalization, ranking, and search systems that are accurate, fast, and scalable.
PinnedLoading
- pinecone-python-client Public
The Pinecone Python client
- examples Public
Jupyter Notebooks to help you get hands-on with Pinecone vector databases
- pinecone-ts-client Public
The official TypeScript/Node client for the Pinecone vector database
- pinecone-vercel-starter Public template
Pinecone + Vercel AI SDK Starter
Repositories
LoadingType Language Sort
Showing 10 of 78 repositories
- pulumi-pinecone Public
Pinecone Pulumi Provider
Python 7 Apache-2.0 2 4 12 Updated 9 hours ago
- embeddings-demo Public
TypeScript 0 0 0 2 Updated 11 hours ago
- tokenization-demo Public
TypeScript 1 0 0 2 Updated 11 hours ago
Pinecone AWS Reference Architecture
TypeScript 104 Apache-2.0 11 7 4 Updated yesterday
- sample-apps Public
Official Pinecone sample apps
TypeScript 26 10 6 6 Updated yesterday
- pinecone-rag-demo-azd Public
TypeScript 1 MIT 1 0 5 Updated yesterday
- spark-pinecone Public
The Apache Spark connector for Pinecone
Scala 18 Apache-2.0 4 0 1 Updated 2 days ago
- pinecone-ts-client Public
The official TypeScript/Node client for the Pinecone vector database
TypeScript 192 Apache-2.0 38 8 2 Updated 2 days ago
- pinecone-python-client Public
The Pinecone Python client
Python 314 Apache-2.0 83 20 7 Updated 2 days ago
- semantic-search-postgres Public