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

有赞技术团队
有赞技术团队
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
IT之家
IT之家
博客园 - 【当耐特】
罗磊的独立博客
Stack Overflow Blog
Stack Overflow Blog
MyScale Blog
MyScale Blog
WordPress大学
WordPress大学
The GitHub Blog
The GitHub Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
Hugging Face - Blog
Hugging Face - Blog
I
InfoQ
B
Blog RSS Feed
腾讯CDC
云风的 BLOG
云风的 BLOG
N
Netflix TechBlog - Medium
Apple Machine Learning Research
Apple Machine Learning Research
GbyAI
GbyAI
雷峰网
雷峰网
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
D
DataBreaches.Net
The Cloudflare Blog
V
V2EX
S
SegmentFault 最新的问题

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
April Monthly Product Update
Xian Huang · 2024-05-01 · via Pinecone

This month, we continued expanding our serverless service and improving your experience building with Pinecone. Check out some of our product highlights below or read the full release notes.

Try serverless for free with 3x more capacity

You now get 3x more capacity with the new serverless free plan, including 2GB of storage, 2M Write Units (WU) (~300k writes), 1M Read Units (RU) (~100k reads) per month, and up to 5 indexes. Existing free plan users can easily convert ‘gcp-starter’ indexes to serverless.

Build on serverless with Java SDK and expanded regions

Pinecone serverless lets you build AI applications for any size of customer base with better performance and costs. With our Pinecone Java client (v1.0.0) adding serverless support, you can build on serverless with Java, Python, or Node.js. Start building in the new eu-west-1 region in addition to the us-west-2 and us-east-1 regions of AWS.

// Maven
<dependency>
  <groupId>io.pinecone</groupId>
  <artifactId>pinecone-client</artifactId>
  <version>1.0.0</version>
</dependency>

// Gradle
implementation "io.pinecone:pinecone-client:1.0.0"

Global Control Plane API to streamline resource management

Our Global Control Plane API is now generally available (view our new API lifecycle policy to learn more details about the lifecycle of Pinecone APIs, features, and client versions), which enables you to use a global URL for all control plane operations (e.g., list indexes, create indexes, list collections) regardless of the cloud environment.

The Global API is currently supported within our Python, Node, and Java clients. If you want to manage your Pinecone resources via infrastructure as code, we support Terraform and Pulumi. View the quickstart to start building today, or check out the migration guide to upgrade to the new API.

Simplified process to build and search what you need

Our new sample apps allow you to interact with a demo before you build your own. Simply run the npx create-pinecone-app command to make the sample app yours. Check out our demo to learn how to build a multi-tenant RAG app with our sample apps.

Looking for something on the Pinecone site? With our new AI chatbot, you can find relevant search results and resources faster from across the Pinecone site — from our docs, blogs, or forums — and even open a support ticket. Check out a quick demo below.

Seamless access to Pinecone from our partner platforms

With the new Pinecone Partner Program, our partners can create a seamless signup and login process for joint users to access Pinecone using our Connect widget and monitor usage.

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