Pinecone @pinecone Twitter profile

Pinned Tweet

Pinecone

4 months

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.

10

90

394

Last Seen Profiles

@GraceALore

@DrKimSue

@CoachGrub_

@navathakuria

@Football2Whs

@dolarhoy

@Connor_Cashmore

@turkmendagz

@alhan

@desertsandvapor

@KARLOLIVE

@Foll0wTheMoney

@okelfo

@XenoBlazeVA

@ShadyBluesinger

@LeeNoSmoke

@elentirvigo

@T_MadTeach

@LtdRna

@TheBus37643251

@_neusestrada

@viviwoshivivi

@EWTNVatican

@the_naaz

@Lix99999

@Inno30mg

@Web3jobsradar

@iGxCarnagee

@triumphcruising

@docetangerina29

@jordanwilkes_1

@Jendeukiliebe

@ecpiiiii

@jarri34

@SookStjean45187

@suka_fantasy

Pinecone

@pinecone

1 year

Let's talk chunking—An 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:

Chunking Strategies for LLM Applications

In the context of building LLM-related applications, chunking is the process of breaking down large pieces of text into smaller segments. It’s an essential technique that helps optimize the relevance...

www.pinecone.io

15

86

538

Pinecone

@pinecone

1 year

Exciting news! 🎉 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)

23

60

328

Pinecone

@pinecone

2 years

Facebook AI Similarity Search (Faiss): The Missing Manual 📘🕵️‍♀️

Introduction to Facebook AI Similarity Search (Faiss)

www.pinecone.io

1

45

276

Pinecone

@pinecone

1 year

Large Language Models have entered the room. It's time to get started with LLMs using LangChain.

LangChain: Introduction and Getting Started

www.pinecone.io

3

23

174

Pinecone

@pinecone

2 years

✨ Introducing our free course on Natural Language Processing (NLP) for Semantic Search! 🧐 Covers everything you need to build state-of-the-art language models, from machine translation to question-answering, and more. 👉 Start here:

Natural Language Processing for Semantic Search

Learn how to build semantic search systems. From machine transition to question-answering.

www.pinecone.io

1

37

148

Pinecone

@pinecone

1 year

A new chapter in our @LangChainAI AI Handbook: Superpower LLMs with Conversational Agents. #LLM #Langchain

LangChain AI Handbook

The handbook to the LangChain library for building applications around generative AI and large language models (LLMs).

www.pinecone.io

2

31

147

Pinecone

@pinecone

1 year

Learn how to build a multi-user chatbot with Langchain and Pinecone in Next.JS.

Building a Multi-User Chatbot with Langchain and Pinecone in Next.JS

Read our step-by-step guide and learn how to build a multi-user langchain chatbot with Langchain and Pinecone in Next.JS. In this example, we’ll imagine that our chatbot needs to answer questions...

www.pinecone.io

2

30

142

Pinecone

@pinecone

10 months

Build a hallucination-free chatbot for any website... In two clicks. Using @Vercel AI SDK + @Pinecone . Here's the starter template:

Pinecone - Vercel AI SDK Starter – Vercel

A Next.js starter chatbot using Vercel's AI SDK and implements the Retrieval-Augmented Generation (RAG) pattern with Pinecone

vercel.com

6

17

141

Pinecone

@pinecone

1 year

Pinecone giveaway! 🎁 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!

19

149

84

Pinecone

@pinecone

1 year

@OpenAI 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:

GitHub - openai/chatgpt-retrieval-plugin: The ChatGPT Retrieval Plugin lets you easily find...

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language. - openai/chatgpt-retrieval-plugin

github.com

3

12

83

Pinecone

@pinecone

1 year

Data Prep 101 with @jamescalam : Learn how to prepare text using @LangChainAI data loaders, tokenization using the tiktoken tokenizers, chunking with LangChain text splitters, and storing data with @huggingface datasets.

LangChain Data Loaders, Tokenizers, Chunking, and Datasets - Data...

In this video, we're going to focus on preparing our text using LangChain data loaders, tokenization using the tiktoken tokenizers, chunking with LangChain t...

www.youtube.com

1

16

80

Pinecone

@pinecone

1 year

🚀🤖 Hold on to your hats, folks! @OpenAI 's ChatGPT plugins are REVOLUTIONIZING the AI landscape, and Pinecone is your express ticket 🎟️ to harnessing their power in production! 🌐 Ready for lift-off? 🌟 Let's dive in and explore this game-changing combo! 🔥🔗 #AI #NextLevelTech

5

6

80

Pinecone

@pinecone

1 year

@mckaywrigley OpenAI combined with a vector database for "long-term memory" = magic.

🪄The OP Stack | Notion

OpenAI + Pinecone is a crazy powerful — some might say… overpowered 😎 — a combination for building AI applications that understand and remember. Especially semantic search, chatbot, question-answe...

gkogan.notion.site

3

7

76

Pinecone

@pinecone

1 year

Demand for Pinecone is extremely high. Here's what we're doing to support our growing number of free users:

Supporting our growing number of free users

Over the past few weeks, the level of excitement around Pinecone has been astounding. There are now over 10,000 daily signups for our free plan, and growing fast. As a managed infrastructure provid...

www.pinecone.io

15

7

77

Pinecone

@pinecone

1 year

📣AI is on the rise and Pinecone is #1 among midsized startups! 🙌🥂🎉

4

11

76

Pinecone

@pinecone

6 months

Introducing Canopy, an open-source #RAG framework to build AI assistants in under an hour. Free storage in Pinecone for up to 100K embeddings, or ~15M words / 30K pages. Supports GPT4-Turbo, with other models coming soon (including open-source).

Introducing Canopy: An easy, free, and flexible RAG framework powered by Pinecone

Canopy lets you build and host your own production-ready chat assistant in under an hour. Learn more and start building today.

www.pinecone.io

4

12

72

Pinecone

@pinecone

2 years

Some exciting news... We raised $28M (Series A) to bring search into the AI age! Read the announcement from our CEO:

$28M to Bring Search into the AI Age

Pinecone raised $28M in Series A funding to bring search into the AI age.

www.pinecone.io

7

71

Pinecone

@pinecone

1 year

@sama 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:

GitHub - openai/chatgpt-retrieval-plugin: The ChatGPT Retrieval Plugin lets you easily find...

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language. - openai/chatgpt-retrieval-plugin

github.com

0

3

65

Pinecone

@pinecone

1 year

🧵 Tips for optimizing Pinecone costs Pinecone is a powerful vector database that can handle large amounts of data, but it's important to manage costs as you scale. Here are some tips...

4

8

63

Pinecone

@pinecone

1 year

❤️ We're proud of ALL the incredible products made with Pinecone, but especially this one by @Shopify Built with the 🪄 OP Stack ( @OpenAI + @pinecone )

tobi lutke

@tobi

1 year

Just how cool is this? (now in your )

86

94

959

4

8

62

Pinecone

@pinecone

1 year

Learn how to build an image recognition app in javascript using Pinecone, @huggingface , and @vercel . #javascript #recognitionapp

Building a Image Recognition App in Javascript using Pinecone, Hugging Face, and Vercel

The world of AI is rapidly expanding, and now the JavaScript/TypeScript ecosystem is joining in. With the emergence of tools like Pinecone, HuggingFace, OpenAI, Cohere, and many others, JavaScript...

www.pinecone.io

1

13

58

Pinecone

@pinecone

11 months

🚀 Calling all builders! Join our hackathon and unleash the power of AI to solve real-world problems. Boost productivity, efficiency, revenue, and business value with innovative applications. #AIHackathon #RealWorldSolutions

Pinecone Hackathon: Jumpstart Real-World AI Applications

Join the week-long hackathon to solve real-world problems with Generative AI tools and platforms.

pinecone-hackathon.devpost.com

5

13

56

Pinecone

@pinecone

1 year

We are excited to be chosen as a vector database provider for @OpenAI 's new ChatGPT plugins. Access to plugins is currently waitlist only, but check out the plugin repository to learn more:

0

11

56

Pinecone

@pinecone

2 years

Roses are red Violets are blue For today's nearest-neighbor search My top_k is you 💐

0

12

53

Pinecone

@pinecone

11 months

AI hackathons are won by zany apps. But the value of AI is in solving real-world problems — with apps that boost productivity, efficiency, revenue, and business value. Announcing a hackathon that encourages, celebrates, and awards builders of AI solutions for real-world problems.

2

15

52

Pinecone

@pinecone

1 year

You will NOT want to miss this workshop, Building the Future with LLMs, @LangChainAI , and Pinecone—featuring the one and only @hwchase17 ! 👏👏👏

2

9

51

Pinecone

@pinecone

1 year

How do we celebrate closing our $100M series B? Glad you asked. 🎉🎈🎂 Interested in joining Pinecone? Check out our available job opportunities here:

5

2

50

Pinecone

@pinecone

9 months

📹 Want to create your chatbot with the best-performing open-source LLM? 🗣️ @jamescalam 's latest video showcases Falcon 40B in action, integrated with LangChain and Hugging Face Transformers. #AI #Chatbot #OpenSource

BEST Open Source LLM — Falcon 40B Chatbot in LangChain

Falcon 40B is currently the best-performing open source Large Language Model (LLM) in the world. In this video, we'll explore how to use the model with Huggi...

www.youtube.com

1

11

51

Pinecone

@pinecone

1 year

In this video, @jamescalam teaches how to build better prompts for @OpenAI 's GPT-3, @CohereAI LLMs, and open-source LLMs (like those on @huggingface ).

Prompt Engineering with OpenAI's GPT-3 and other LLMs

In this video, we'll talk about how to build better prompts for OpenAI's GPT-3, Cohere LLMs, and open-source LLMs (like those on Hugging Face). We'll treat p...

www.youtube.com

0

12

49

Pinecone

@pinecone

1 year

❤️ This Valentine's Day...

4

2

47

Pinecone

@pinecone

1 year

What happens when you use Elasticsearch, Opensearch, Solr, and Pinecone together—with the final combined ranking produced with Metarank? Vsevolod Goloviznin has an answer. #opensource #vectorsearch

Hybrid Search and Learning-to-Rank with Metarank

As more advanced Large Language Models (LLMs) are released, the dream of an accurate semantic search comes closer to reality. But a classical term search is still hard to beat, even with the largest...

www.pinecone.io

2

5

45

Pinecone

@pinecone

6 months

We’re excited to be a launch partner for @LangChainAI 's new Templates! Easily build and deploy a #chatbot over your own data with the popular #RAG Chatbot Template using Pinecone and @OpenAI : .

0

10

44

Pinecone

@pinecone

1 year

📣 Pinecone, @make_berri , @cerebriumai , @Replit , and @OpenAI are throwing the largest hybrid chatGPT hackathon this weekend! Join us for the chance to win $5k+ in prizes, office hours, late-night virtual lounges, etc. Sign up now, and build the future! .

3

4

44

Pinecone

@pinecone

1 year

❤️ Love the passion for embeddings (and Pinecone) from @dharmesh

Dan Kirner

@DanKirner

1 year

Find someone who looks at you like the way @thesamparr looks at @dharmesh when he talks about vector embeddings.

34

32

582

2

43

Pinecone

@pinecone

1 year

Missed Building the Future with LLMs, LangChain, & Pinecone? We've got you covered:

Building the Future with LLMs, LangChain, & Pinecone

Join Harrison Chase, the creator of the breakout library LangChain, and James Briggs, developer advocate at Pinecone, as we explore the new age of AI and it'...

www.youtube.com

0

4

43

Pinecone

@pinecone

1 year

Attention all AI enthusiasts! Join us for an exclusive in-person meetup in SF, April 27th, on using the @OpenAI + Pinecone to supercharge your product's AI features. Limited spots available. Reserve now for a chance to experience the future of AI!"

6

8

39

Pinecone

@pinecone

9 months

Curious about prompt engineering for LLMs? 🤔 @LangChainAI 's got you covered! Join @jamescalam in Part 2 of the series to learn about PromptTemplates and FewShotPromptTemplates.

Prompt Templates for GPT 3.5 and other LLMs - LangChain #2

In the second part of our LangChain series, we'll explore PromptTemplates, FewShotPromptTemplates, and example selectors. These are key features in LangChain...

www.youtube.com

2

6

39

Pinecone

@pinecone

1 year

One hour till Building the Future with LLMs, LangChain, and Pinecone! Signup quickly and join @hwchase17 , the creator of @LangChainAI , and @jamescalam , developer advocate at Pinecone, as we explore the new age of AI and its biggest enabler — LangChain.

4

7

40

Pinecone

@pinecone

11 months

💻 Want to explore the MTP-7B model? This GitHub repo provides a comprehensive guide on using it in @huggingface transformers and @LangChainAI Get ready to take your NLP projects to the next level. #GitHub #MTP7B #HuggingFace #LangChain

1

4

37

Pinecone

@pinecone

1 year

ChatGPT Plugins are earth-shattering, and their Retrieval Plugin makes it easy to build your own, using Pinecone:

0

5

37

Pinecone

@pinecone

1 year

One hour until Build overpowered AI apps with the OP stack ( @OpenAI + Pinecone). See what developers built with the OP stack and hear their tips and tricks for going from idea to production.

5

3

36

Pinecone

@pinecone

1 month

Introducing the first hallucination-free LLM. Learn how it works and try it:

Introducing the First Hallucination-Free LLM

www.pinecone.io

5

6

37

Pinecone

@pinecone

11 months

Announcing the Pinecone Summit: AI Transformation without Hallucination, a day-long generative AI event of the summer happening on July 13 in SF.

AI Transformation Summit

Presented by Pinecone with support from Microsoft

summit.pinecone.io

5

12

35

Pinecone

@pinecone

1 year

Congrats to @CohereAI for announcing their multi-lang model! Learn how to use Cohere to generate language embeddings and store them in Pinecone for Semantic Search.

0

5

34

Pinecone

@pinecone

1 year

Curious about what others are building with the OP Stack ( @OpenAI + Pinecone)? We have an event for you. Featuring @jamescalam , DA at Pinecone, @RaineyAllDay , Founder at My AskAI, and @yasser_elsaid_ , Founder at Chatbase. RSVP today:

0

5

35

Pinecone

@pinecone

1 year

ChatGPT plugins unlock a world of possibilities… You can now give ChatGPT access to your internal data so it can provide answers that are relevant for your company! The Retrieval Plugin is a starter kit with built-in connections to Pinecone:

3

34

Pinecone

@pinecone

2 years

🇺🇸🇪🇸🇮🇹 The guide to creating multilingual sentence vectors for 50+ languages:

0

2

34

Pinecone

@pinecone

1 year

Semantic search for 100+ languages, scalable to 100M+ embedding datasets, in a few lines of code. 🤘 Pinecone + @CohereAI Example tutorial:

The vector database to build knowledgeable AI | Pinecone

Search through billions of items for similar matches to any object, in milliseconds. It's the next generation of search, an API call away.

docs.pinecone.io

Nils Reimers

@Nils_Reimers

1 year

Recently I have been playing a lot with the @CohereAI multilingual embedding model and @pinecone vector database: With 2 lines of code, you get an amazingly good search function that works for 100+ languages.

4

8

49

1

5

34

Pinecone

@pinecone

7 months

Pinecone is now HIPAA compliant! Some of the largest enterprises already trust Pinecone to store data and power their mission-critical applications. Those subject to HIPAA can now leverage AI and Pinecone to power and unlock new use cases. Learn more:

Pinecone is now HIPAA compliant

Pinecone is now HIPAA compliant across Amazon Web Services (AWS), Azure, and Google Cloud Provider (GCP).

www.pinecone.io

2

4

33

Pinecone

@pinecone

10 months

@tunguz See:

What is a Vector Database & How Does it Work? Use Cases + Examples

Discover Vector Databases: How They Work, Examples, Use Cases, Pros & Cons, Selection and Implementation. They have combined capabilities of traditional databases and standalone vector indexes while...

www.pinecone.io

1

3

33

Pinecone

@pinecone

1 year

1/ In 2 days, 300+ engineers and engineering leaders will gather for the first-ever Pinecone Meetup in SF to learn about the #OPstack — building overpowered AI apps with OpenAI and Pinecone. Here's what they'll experience and how you can get in before registrations close 👇🧵

3

10

32

Pinecone

@pinecone

1 year

Marathon Q&A session about chatbots, LLMs, frameworks ( @LangChainAI ), vector databases (Pinecone), and building real-world applications using all of the above! Listen now...👇

Mayo Oshin

@mayowaoshin

1 year

Published Recording of @pinecone Q+A twitter spaces with @RoieSchwabco , @yasser_elsaid_ and myself in case you missed it 🔥

5

6

74

0

4

30

Pinecone

@pinecone

1 year

Ready to level up your chatbot game? Join us for a deep dive into retrieval augmentation, a powerful technique for boosting the performance of conversational agents. Register now! #Chatbots #ConversationalAI #Retrievalugmentation #Workshop "

1

3

30

Pinecone

@pinecone

1 year

Learn how to build an image recognition app in javascript using Pinecone, @huggingface , and @vercel . #javascript #AI #typescript

Building a Image Recognition App in Javascript using Pinecone, Hugging Face, and Vercel

The world of AI is rapidly expanding, and now the JavaScript/TypeScript ecosystem is joining in. With the emergence of tools like Pinecone, HuggingFace, OpenAI, Cohere, and many others, JavaScript...

www.pinecone.io

0

4

30

Pinecone

@pinecone

2 years

Last week we announced a live workshop on Nov 16 about Semantic Search, ft @Nils_Reimers ( @huggingface ) & @DaveBergstein (Pinecone). The response was 🔥🔥 Hundreds of engineers, product mgrs, and data scientists already registered!! Here's what you'll learn + link to register 👇

1

7

29

Pinecone

@pinecone

2 years

We're so excited to be welcoming @Nils_Reimers , NLP researcher at @huggingface and creator of SBERT, back to join us for another live webinar on March 24 featuring how GPL can supercharge your semantic search use cases. Register now:

0

4

29

Pinecone

@pinecone

1 year

Use @OpenAI Embedding API to generate language embeddings and index those embeddings in the Pinecone vector database for fast and scalable vector search. #vectorsearch #openai #API

OpenAI's New GPT 3.5 Embedding Model for Semantic Search

In this video, we'll learn how to use OpenAI's new embedding model text-embedding-ada-002.We will learn how to use the OpenAI Embedding API to generate langu...

www.youtube.com

0

1

29

Pinecone

@pinecone

1 year

@gdb 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:

GitHub - openai/chatgpt-retrieval-plugin: The ChatGPT Retrieval Plugin lets you easily find...

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language. - openai/chatgpt-retrieval-plugin

github.com

0

3

29

Pinecone

@pinecone

1 year

@stef @paulg @gpt_index Another 🔥 project added to the 🪄 OP Stack list:

🪄The OP Stack | Notion

OpenAI + Pinecone is a crazy powerful — some might say… overpowered 😎 — a combination for building AI applications that understand and remember. Especially semantic search, chatbot, question-answe...

gkogan.notion.site

3

0

29

Pinecone

@pinecone

1 year

Another overpowered app built with the OP stack ( @openai + Pinecone) by @yasser_elsaid_

Yasser

@yasser_elsaid_

1 year

Introducing Naval GPT: Chat with @naval about health, wealth, and happiness! This was created by embedding Naval's ideas and storing them in @pinecone then using @OpenAI 's GPT-4 to get the answers. @LangChainAI Built using

20

61

429

2

5

28

Pinecone

@pinecone

9 months

🚀🔥 Ready to level up your Llama 2 game? Join us for a webinar featuring @jamescalam and @RLanceMartin from @LangChainAI as they unveil the secrets to supercharging Llama 2 with RAG! 🦙🦹 Don't miss out, see you tomorrow @ 3PM PST! 👉

LangChain x Pinecone: Supercharge Llama 2 with RAG

Register now for LangChain x Pinecone: Supercharge Llama 2 with RAG on crowdcast, scheduled to go live on July 26, 2023, 03:00 PM PDT.

www.crowdcast.io

1

6

27

Pinecone

@pinecone

1 year

Join us in NYC on March 21 for the Pinecone Meetup: Building with LLMs and Vector Databases An evening of talks by - @DouzeMatthijs (creator of Faiss) - @NathanielRoth3 (Dir of Eng), @saahil9jain , Sam Bean from @YouSearchEngine - And more Get your seat:

0

10

27

Pinecone

@pinecone

10 months

We ❤️ this community. Thank you to everyone at our AI Transformation Summit today!

2

1

27

Pinecone

@pinecone

1 year

Learn how @LangChainAI drives transformation across industries and in technology, changing how we interact with AI models.

LangChain AI Handbook

The handbook to the LangChain library for building applications around generative AI and large language models (LLMs).

www.pinecone.io

0

6

27

Pinecone

@pinecone

11 months

Welcome to our latest hackathon sponsors @zapier and @convex_dev , alongside @awscloud , @OpenAI , @huggingface , @LangChainAI , @cohere , @Netlify , @vercel , @Kumospace_ and @ClerkDev in our hackathon for real-world apps, with over 100k in prizes! Join today!

2

6

25

Pinecone

@pinecone

11 months

💡Explore the GitHub notebook for Open-LLaMa in @huggingface and @LangChainAI Learn how to effectively use this model, prompts included, to unlock new possibilities in your NLP workflows. #OpenLLaMa #HuggingFace #LangChain #NLP

0

5

26

Pinecone

@pinecone

1 year

A vector database plays a vital role in the success of AI-driven applications and solutions. Learn how:

Vector Databases: Long-Term Memory for Artificial Intelligence

Vector databases store data such as text, video or images that are converted into vector embeddings for AI models to access them quickly.

thenewstack.io

0

1

24

Pinecone

@pinecone

9 months

Learn how to fully implement an audio recommendation solution using AI.

Audio Recommendation with OpenAI and Vector DBs

Explore the creation of an audio recommendation system using Python in this step-by-step guide. The article covers the basics of recommendation systems, their importance in the era of audio streami...

www.pinecone.io

0

2

24

Pinecone

@pinecone

1 year

Real-time data has become commonplace in many organizations, and with it, the ability to quickly process and store vector embeddings has become increasingly important. Learn to generate and store embeddings at scale in real-time scenarios.

Streaming Embedding Generation with Databricks and Pinecone

Combining Databricks and Pinecone provides us with the perfect pipeline to answer these challenges. Databricks offers Structured streaming and Delta Live Tables as means to create a streaming...

www.pinecone.io

0

3

24

Pinecone

@pinecone

1 year

Take your search results to the next level! We’ve upgraded our index to support sparse-dense embeddings in a new way. Read the announcement to learn more, and start building today.

Introducing support for sparse-dense embeddings for better search result

Index support for any sparse-dense embeddings now available in public preview for all users. Read announcement to learn more.

www.pinecone.io

0

3

24

Pinecone

@pinecone

1 year

“Companies who build [ChatGPT] plugins will need this vector database component, this long-term memory.”

VentureBeat

@VentureBeat

1 year

I spent the weekend noodling about the implications of ChatGPT plugins, OpenAI's latest chess move. Here are 5 key ways plugins could change the #AI game:

2

8

18

1

5

24

Pinecone

@pinecone

1 year

A HUGE thank you to all who showed up and showed out to Build Overpowered AI Apps with the OP Stack! Want more events? Let us know! #OPStack #Pinecone #AI #ML

2

1

24

Pinecone

@pinecone

1 year

Mark your calendars! You've been building with the OP Stack ( @OpenAI and Pinecone), and we've been watching. Join us on Feb 21st to learn tips and tricks for going from idea to production with the OP stack. #OpenAI #AI #ML #Machinelearning

3

4

24

Pinecone

@pinecone

6 months

👀 In case you missed it live, our workshop with @Haystack_AI is now available for replay. RAG, agents, and memory come together to create high-performance Conversational AI – tune in and learn more:

Supercharge Conversational AI with Pinecone x Haystack

In this workshop, we will delve into RAG, agents, and memory — how to integrate them all using Pinecone and Haystack to create high-performance, up-to-date, ...

www.youtube.com

0

6

23

Pinecone

@pinecone

2 years

CEO Edo shares his experience building Pinecone, as well as insight into the product’s recent updates and innovation in vector search. Read more here:

Inside the Pinecone

Edo Liberty, Pinecone CEO, provides a glimpse into the journey behind building a database company, including some insights into the latest innovations around the product and vector search.

www.pinecone.io

0

4

21

Pinecone

@pinecone

1 year

GLHF to all participating in this weekend's GPT-4 Hackathon, competing for $20,000 prize money + $1,000 in Pinecone credits. We're a proud Gold Sponsor alongside @OpenAI @AnthropicAI + others. Huge thanks to organizers @iporollo @AviSchiffmann @SHACK15sf !

0

4

23

Pinecone

@pinecone

6 months

To date, we haven't published much about the algorithms that power our indexes. Until now. Let's get this conversation started .

Great Algorithms Are Not Enough

Compared to bolt-on vector databases, Pinecone is thoughtfully designed to meet the escalating demands of GenAI applications, ensuring enhanced performance and scalability.

www.pinecone.io

0

7

22

Pinecone

@pinecone

1 year

📚 The #LangChain AI Handbook by @jamescalam and Francisco Ingham unlocks the power of large language models, revolutionizing industries and transforming tech interactions. #AI #Technology #LLMs

LangChain AI Handbook

The handbook to the LangChain library for building applications around generative AI and large language models (LLMs).

www.pinecone.io

0

3

23

Pinecone

@pinecone

10 months

Reducing AI Hallucinations: Learn about data, modeling, and inference methods to minimize this problem in Language Models!

Understanding Hallucinations in AI: A Comprehensive Guide

Explore the intriguing world of hallucinations in AI language models in our comprehensive guide. Uncover the causes, implications, and future trends in AI hallucinations, shedding light on this...

www.pinecone.io

1

4

21

Pinecone

@pinecone

1 year

"Toss a Pinecone on the fire and the fire will get weird." — @Scobleizer Should be on a t-shirt.

Robert Scoble

@Scobleizer

1 year

“Humansauce” is still relevant. Sprinkle humansauce on all AI generated content and it will be much more entertaining. What is humansauce? It is your weird way of looking at the world. Soon you will bottle this up and put it in a vector database like @pinecone . Then you…

17

9

84

1

6

22

Pinecone

@pinecone

3 months

You know 'em, you love 'em, now they're official #Integration partners -- check out everything @llama_index x @pinecone on our new page!

The vector database to build knowledgeable AI | Pinecone

Search through billions of items for similar matches to any object, in milliseconds. It's the next generation of search, an API call away.

docs.pinecone.io

0

4

23

Pinecone

@pinecone

2 years

Learn why semantic search leads to happier users, where it can be used, what it takes to build a semantic search system, and how to do it step-by-step. Featuring @Nils_Reimers ( @huggingface )! Save your spot: #nlp #machinelearning #ML #AI

0

10

20

Pinecone

@pinecone

10 months

The AI Transformation Summit on July 13 in San Francisco is a prime opportunity to gain practical skills, invaluable insights, and breakthrough inspiration for any engineering teams working on AI initiatives. Here are 5 reasons not to miss the AI Transformation Summit: 1. 💪…

3

5

21

Pinecone

@pinecone

3 months

We recently announced Pinecone serverless, a completely reimagined vector database, to Iet companies build more knowledgeable AI applications. We break it down for you with 5 reasons to start building with Pinecone serverless today. Check it out! .

5 reasons to build with Pinecone serverless

We recently announced Pinecone serverless in public preview. This blog shares the top five reasons to start building with Pinecone serverless today.

www.pinecone.io

0

2

21

Pinecone

@pinecone

9 months

🎯 Calling all Llama 2 enthusiasts! Join us in this webinar, where @jamescalam and @RLanceMartin will teach you how to unleash the power of RAG. See you today @ 3PM PST! ⏰

LangChain x Pinecone: Supercharge Llama 2 with RAG

Register now for LangChain x Pinecone: Supercharge Llama 2 with RAG on crowdcast, scheduled to go live on July 26, 2023, 03:00 PM PDT.

www.crowdcast.io

0

4

22

Pinecone

@pinecone

2 years

We’re teaming up with @deepset_ai to make building intelligent Q&A apps even easier (Pinecone + Haystack). Want to be a beta tester? Complete this form

0

4

22

Pinecone

@pinecone

1 year

Another 🔥 cookbook from @colintjarvis using @OpenAI + @pinecone + @LangChainAI

Colin Jarvis

@colintjarvis

1 year

Since plugins launched, many of you have been trying to create tool-using language models for your own apps. To support this we're excited to release a cookbook which takes you through this here: Hope you enjoy it, we're stoked to see what you build!

10

153

813

1

3

21

Pinecone

@pinecone

11 months

Let the games begin! 🏁👩‍💻👨‍💻 Good luck to our 1,200+ hackathon participants competing for $100k+ in credits & prizes from our partners: @awscloud @Netlify @vercel @OpenAI @LangChainAI @ClerkDev @CohereAI @huggingface @convex_dev @zapier @Kumospace_

Pinecone Hackathon: Jumpstart Real-World AI Applications

Join the week-long hackathon to solve real-world problems with Generative AI tools and platforms.

pinecone-hackathon.devpost.com

0

3

21

Pinecone

@pinecone

4 months

A new @LangChainAI video tutorial explains how to take a RAG app from prototype to deployment using @pinecone serverless - Prototype a RAG chain w/ @pinecone in notebook - Convert the chain into a web service w/ LangServe - Deploy w/ Hosted LangServe

LangChain

@LangChainAI

4 months

RAG with Pinecone Serverless Congrats to our friends at @pinecone for the recent launch of Pinecone Serverless! This has a few benefits for developers, including usage-base-pricing (>10x lower costs), improved latency, and effortless scaling (no more pods or storage limits).…

2

68

294

1

21

Pinecone

@pinecone

5 months

Introducing the Pinecone Reference Architecture for AWS– the fastest way to get your AI app in production. Learn how it works in our blog post, then deploy in the time it takes to bake a cookie:

1

9

21

Pinecone

@pinecone

1 year

🚀 Level up your development skills with the #LangChain AI Handbook. Revolutionize industries and redefine tech with intelligent applications. #AI #Development

LangChain AI Handbook

The handbook to the LangChain library for building applications around generative AI and large language models (LLMs).

www.pinecone.io

0

6

21

Pinecone

@pinecone

5 months

With Thanksgiving approaching, we’re extra thankful to be named the most popular vector database across industry reports by @Retool @MenloVentures & @Streamlit . We're also the only vector database on the inaugural @Fortune 2023 50 AI Innovator list.

Pinecone recognized as the most popular vector database

Pinecone is named the most popular and most used vector database across industry reports. We are also the only vector database on the inaugural Fortune 2023 50 AI Innovator list.

www.pinecone.io

10

2

21

Pinecone

@pinecone

1 year

Why is real-time processing a challenge? Learn why and how to combat it:

Streaming Embedding Generation with Databricks and Pinecone

Combining Databricks and Pinecone provides us with the perfect pipeline to answer these challenges. Databricks offers Structured streaming and Delta Live Tables as means to create a streaming...

www.pinecone.io

0

4

21

Pinecone

@pinecone

1 year

A HUGE thank you to everyone who joined us last night for Building with LLMs and Vector Databases. And an extra special thank you to our incredible speakers @DouzeMatthijs , @isafulf , @NathanielRoth3 , and @saahil9jain .

1

21

Pinecone

@pinecone

1 year

@BorisMPower "For searching over many vectors quickly, we recommend using a vector database." Docs:

The vector database to build knowledgeable AI | Pinecone

Search through billions of items for similar matches to any object, in milliseconds. It's the next generation of search, an API call away.

docs.pinecone.io

1

20

Pinecone

@pinecone

11 months

📢 Don't miss the Pinecone Summit on July 13! 🤖 Join us and @microsoft for actionable talks on generative AI by leading engineers. Get your tickets now at !

AI Transformation Summit

Presented by Pinecone with support from Microsoft

summit.pinecone.io

1

20

Pinecone

@pinecone

7 months

🎊 Join our hackathon on Oct 17 at the legendary @agihouse_org , in partnership with @truera_ai and @llama_index !

AGI House

@agihouse_org

8 months

Building and launching an LLM app? We've got TruEra, Pinecone, LlamaIndex, etc the entire Infra stack to help! Come join us on 10/7 12pm - 10pm @ AGI House!

1

4

24

1

5

20

Pinecone

@pinecone

9 months

Research shows that LLMs provide the best results when given fewer, more relevant documents in the context, rather than large numbers of unfiltered documents.

Less is More: Why Use Retrieval Instead of Larger Context Windows

The idea of a large context window seems appealing at first — just give the model all your data and let it figure it out. However, Research shows that LLMs provide the best results when given fewer,...

www.pinecone.io

0

1

20

Pinecone

@pinecone

3 years

An illustrated guide to Hierarchical Navigable Small Worlds (HNSW):

0

2

20