Curious about contextual retrieval? Learn live how to build it into your RAG applications with Pinecone and Anthropic on Tuesday, November 12. Register here: https://lnkd.in/eyw5vyPd Contextual retrieval is a new technique that can dramatically improve the quality of results with RAG. In this webinar, we’ll show you how it can work to improve results on a common, tricky dataset– recorded technical talks that combine images (slides), video (speakers) and text. Join Alex Albert (Anthropic) and Arjun Patel (Pinecone), as they demonstrate building a Retreival Augmented Generation system over company videos to enable effective search that understands the spoken content of the videos and also what appears on screen. You'll learn: - How to build a RAG solution with Pinecone, Claude, and Bedrock, leveraging Claude's AI capabilities through Amazon Bedrock for visual question answering - Practical implementation steps using a demo Amazon SageMaker notebook - Best practices for integrating Pinecone, Claude, and AWS services
Pinecone
Software Development
New York, NY 61,316 followers
The Pinecone vector database: Long-term memory for AI.
About us
Pinecone is a fully managed vector database that makes it easy to add vector search to production applications. It combines state-of-the-art vector search libraries, advanced features such as filtering, and distributed infrastructure to provide high performance and reliability at any scale. No more hassles of benchmarking and tuning algorithms or building and maintaining infrastructure for vector search. We are engineers who built large machine learning platforms, databases, and search engines at AWS, Yahoo, Splunk, Databricks, and more. We are scientists who transformed businesses with ML applications such as shopping recommendations, online advertising, semantic search, anomaly detection, and more. We are researchers who collectively published more than 100 academic papers and patents on machine learning, systems, and algorithms.
- Website
-
https://www.pinecone.io/
External link for Pinecone
- Industry
- Software Development
- Company size
- 51-200 employees
- Headquarters
- New York, NY
- Type
- Privately Held
- Founded
- 2019
Locations
-
Primary
Get directions
New York, NY 10001, US
-
Get directions
San Francisco, California, US
-
Get directions
Tel Aviv, IL
Employees at Pinecone
Updates
-
📈 Exciting news for Pinecone and Datadog users! Our integration now fully supports Pinecone Serverless indexes, making it easier than ever to gain insights into your vector database’s health and improve performance. With this integration, you’ll have access to: • Detailed performance metrics on latency, usage, throughput, and more • Automatic alerts to help you stay on top of key metrics Explore the documentation to get started: https://lnkd.in/esAUaPVA Plus, for those using Prometheus, all metrics are accessible via HTTP service discovery, enabling seamless monitoring of indexes across all regions. Learn more about using Prometheus for Pinecone monitoring here: https://lnkd.in/ezYiyQzB #Pinecone #Datadog #Observability #Monitoring #Prometheus #Serverless #DataAnalytics
-
Build, evaluate and improve the most reliable RAG pipeline possible with Cleanlab & Pinecone — just like Neo from the Matrix!
Today, we’re thrilled to share the latest on our Cleanlab + Pinecone partnership, introducing a new standard for building reliable and scalable Retrieval-Augmented Generation (RAG) systems. Let’s use “The Matrix” to explain: What is RAG? 👉 Think “The Matrix” where Neo uploads an entire course into his mind in seconds. Pinecone’s Role: Pinecone is the memory, storing all knowledge Neo (or an AI) needs to take informed actions. Cleanlab’s Role: Cleanlab curates, tags, and stores organized, efficient knowledge so Neo (or an AI) can act accurately and quickly. Sci-fi is becoming reality, and this partnership is a glimpse into that future. Highlights: • Hallucination-Free AI: Cleanlab’s TLM grounds responses in factual sources. • Real-Time Support: Curated knowledge powers quick, accurate responses. • Trust Scoring: Real-time accuracy checks boost reliability. See how these innovations reshape industries in our latest blog post. Big thanks to Pinecone—excited for what’s next! #vectordb #genai #rag #agents #llms #trustworthyai
Building a Reliable, Curated, and Accurate RAG System with Cleanlab and Pinecone | Pinecone
pinecone.io
-
The 2024-10 version of the Pinecone API is now available, adding support for our inference and import endpoints. You can now bulk import, embed, and rerank your data in our Python, Node, Java, and Go SDKs. https://hubs.ly/Q02VKwMR0
2024 releases - Pinecone Docs
docs.pinecone.io
-
Pairing our Assistant API with Fivetran for data syncing makes for a seamless, downright pleasant experience building a RAG app over your data. Get started with the tutorial here: https://5tran.co/4fgsakw
Many enterprises are using RAG architectures as a gateway into generative AI, but integrating proprietary data can be challenging. That’s where Fivetran and Pinecone come in. With Fivetran’s seamless data syncing and Pinecone’s Assistant, you can securely combine your data with foundation models to gain powerful insights — without the technical headache. Learn how to build an end-to-end RAG architecture and interact with your data using natural language in our latest blog from 🏳️🌈 Corbett Waddingham: https://5tran.co/4fgsakw
-
-
We are excited to celebrate the growth of our team by welcoming Trenton Potgieter, Pinecone's new Staff Solution Engineer. Trenton comes to Pinecone with 13 years in the AI & ML industry, and we are thrilled to have him. Are you interested in joining our talented team? Check out our opportunities today: https://hubs.ly/Q02Td9GB0
-
-
These four new Pinecone Assistant features make it easier to build a trustworthy and customizable chat applications with minimal effort. Read more in this post by Roie Schwaber-Cohen: https://hubs.ly/Q02TxG860
Four features of the Assistant API you aren't using - but should | Pinecone
pinecone.io
-
Clone this new sample app for a jump start on a RAG chatbot over your company data. It combines Box's Text Representation API + Pinecone Inference to turn documents into queryable sets of embeddings you can use to give an LLM context– all while keeping control over your data.
Please checkout this new demo connecting Box and Pinecone. Pinecone is the leading cloud vector database used to create AI applications. 👏 https://lnkd.in/ggE9Pe9G #AI #ML #SoftwareDevelopment #Box #Cloud #Pinecone
[Demo] Box + Pinecone
medium.com
-
We are excited to celebrate the growth of our team by welcoming Bobby Mohr, Pinecone's new VP of Global Sales. Bobby comes to Pinecone from Twilio, and brings 15 years of sales and leadership experience for high growth technology companies. We couldn't be more excited to have him on board! Are you interested in joining our talented team? Check out our opportunities today: https://hubs.ly/Q02Td4QX0
-
-
Pinecone reposted this
Box is making it easier than ever to build AI apps and agents with your enterprise content. Earlier this week, we announced that you can now choose-your-own-model (CYOM) via Box AI API. With that, we’re excited to highlight our new integrations with the developer platforms that will make building those experiences faster and easier: ▫LangChain ▫ Microsoft Copilot Studio ▫ Google Vertex AI Search ▫ LlamaIndex ▫ Pinecone (coming soon) Learn more: https://lnkd.in/g4T6nsAj
-