惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

大猫的无限游戏
大猫的无限游戏
MyScale Blog
MyScale Blog
雷峰网
雷峰网
量子位
小众软件
小众软件
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园 - 叶小钗
T
Tailwind CSS Blog
月光博客
月光博客
博客园 - 【当耐特】
博客园_首页
罗磊的独立博客
博客园 - 三生石上(FineUI控件)
IT之家
IT之家
爱范儿
爱范儿
阮一峰的网络日志
阮一峰的网络日志
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
WordPress大学
WordPress大学
The Cloudflare Blog
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
S
SegmentFault 最新的问题
人人都是产品经理
人人都是产品经理
V
V2EX
酷 壳 – CoolShell
酷 壳 – CoolShell

Pinecone

Pinecone Assistant: A Managed Knowledge Layer for Production AI Applications Multi-domain RAG in n8n: why one knowledge base is not enough Allspice Transforms the Culinary Experience with Semantic Search Powered by Pinecone | Pinecone Building RAG workflows in n8n: choosing the right Pinecone node Knowledge needs a meta-knowledge layer Garbage Day: How Pinecone Safely Deletes Billions of Objects at Scale When "Performance" Means Two Different Things Pinecone BYOC: Pinecone in your AWS, GCP, or Azure account, no vendor access True, Relevant, and Wrong: The Applicability Problem in RAG Use the Pinecone Plugin for Claude Code to develop AI Applications Faster Millions at Stake: How Melange's High-Recall Retrieval Prevents Litigation Collapse Powering High-stakes Patent Search at Scale: How Melange Built a Reliable AI System on Pinecone | Pinecone Pinecone Assistant Node in n8n: Turn Any Data Source Into Knowledge RAG with Access Control Pinecone Dedicated Read Nodes are now in Public Preview Inside Pinecone: Slab Architecture New Bulk Data Operations: Update, Delete, and Fetch by Metadata The Hidden Cost of Building: Lessons from Aquant Simplifying Vector Embeddings with Pinecone Integrated Inference Capabilities Pinecone joins Microsoft Marketplace as a Launch Partner GTM Engineering: Clay + Pinecone for AI-powered Sales Outbound Build an AI knowledge assistant with Google Docs and Pinecone Moving Pinecone forward with Ash Ashutosh as CEO and Edo spearheading our growing AI ambitions as Chief Scientist Pinecone Founder Edo Liberty to Spearhead Pinecone’s Growing AI Ambitions; Appoints Ash Ashutosh as CEO to Expand Vector Database Market Leadership Fast, Accurate Retrieval for Creators at Scale: Delphi’s Path Toward a Million Conversational Agents with Pinecone | Pinecone Announcing Pinecone Pioneers: A Program for Builders, Organizers, and Community Leaders What is Context Engineering? Chunking Strategies for LLM Applications Beyond the hype: Why RAG remains essential for modern AI Obviant Makes 30% More Accurate Defense Acquisition Recommendations Combining Sparse and Dense Retrieval with Pinecone | Pinecone
March Monthly Product Update
Xian Huang · 2024-04-01 · via Pinecone

We had a productive March, including updated SDKs, new features, and improvements to our console. Check out some of the highlights below.

Broader availability with a new serverless region

We welcomed 2024 with Pinecone serverless, introducing a breakthrough architecture allowing you to build better AI applications while saving up to 50x. You can now deploy Pinecone serverless in the us-east-1 region in addition to the us-west-2 region of AWS. Support for serverless in GCP and Azure is coming soon.

Build better RAG applications with updated Node.js and Canopy SDK

The Pinecone Node.js client v2.1.0 adds functionality to list record IDs or just those with a common ID prefix. ID prefixes enable you to query segments of content, which is especially useful for managing RAG applications where you often need to chunk large documents into smaller segments. This feature is also supported in the Python client (v3.1.0 and later).

import { Pinecone } from '@pinecone-database/pinecone';
const pc = new Pinecone();

const index = pc.index('my-index').namespace('my-namespace');

const results = await index.listPaginated({ prefix: 'doc1#' });
console.log(results);
// {
//   vectors: [
//     { id: 'doc1#01' }, { id: 'doc1#02' }, { id: 'doc1#03' },
//     { id: 'doc1#04' }, { id: 'doc1#05' },  { id: 'doc1#06' },
//     { id: 'doc1#07' }, { id: 'doc1#08' }, { id: 'doc1#09' },
//     ...
//   ],
//   pagination: {
//     next: 'eyJza2lwX3Bhc3QiOiJwcmVUZXN0LS04MCIsInByZWZpeCI6InByZVRlc3QifQ=='
//   },
//   namespace: 'my-namespace',
//   usage: { readUnits: 1 }
// }

Canopy is an open-source RAG framework and context engine that enables you to quickly and easily experiment with and build applications using RAG. The latest version of Canopy (v0.8.1) includes better guidance for you to create a knowledge base when using the core library, bug fixes, and more.

Better access control with self-serve SSO and Python proxy support

Enterprise customers can now configure single single-on to manage their teams' access to Pinecone through any identity management solution with SAML 2.0 support, such as Okta.

The latest version of our Python SDK adds four optional configuration properties that enable the use of Pinecone via proxy. This allows users working in environments with proxy servers, network restrictions, or specific security requirements to configure the Python SDK to work seamlessly within those constraints. We’re committed to helping you build secure applications and stay tuned for more security features.

Easier navigation with a refreshed console

You can now find what you need more efficiently. Pick up where you left off with a new index shortcut, and locate indexes faster with the index browser that allows you to search indexes by name. You can also sort indexes alphabetically, by how recently they were viewed or created, or by status, and filter indexes by index type (serverless, pod-based, or starter).

Refreshed console

Refreshed console

Last but not least, we’ve added a Troubleshooting section in the docs where you can find best practices, and how to address common errors.

Check the release notes for a running list of all product and feature releases. If you’re new to Pinecone, try it out today.