Edo Liberty
@EdoLiberty
Followers
569
Following
29
Media
2
Statuses
56
RT @awsdevelopers: 🗽 NYC tech community, come learn how to build agentic AI applications with experts from #AWS, #Cohere, and Pinecone!. 🤖….
0
7
0
RT @pinecone: 💡If you thought Pinecone was just about dense retrieval, you're missing out! Obviant is delivering 30% more accurate defense….
0
2
0
RT @jack_pertschuk: Come build databases with @hirad_codes and me at @pinecone if this makes you giddy
0
4
0
RT @pinecone: 💡 How @Vanguard_Group boosts customer support with fast, accurate vector search & RAG ⚡️. After testing pgvector, Faiss & Red….
0
4
0
RT @pinecone: We’re proud to announce that Pinecone has been named to @FastCompany's annual list of the world’s most innovative companies o….
0
3
0
We also improved search and recommendation performance. High-performance sparse indexing for text search now outperforms OpenSearch by a big margin! Auto scaling read worker replication (or provisioned capacity; coming soon) allows for seamless scaling to high QPS.
2
0
3
We now use an adaptive indexing log-structured merge tree; different slabs are indexed differently based on their size. It supports millions of small namespaces per index without sacrificing performance.
1
0
2
These are both harder and easier to handle. Very small indexes no longer justify complex indexing or bookkeeping. On the other hand, they can be warmed up in real time and scanned extremely quickly.
0
0
4
We spent several months optimizing Pinecone for agents. Agentic workloads are different from traditional search and recommendation. They involve millions of small namespaces with bursty, unpredictable query patterns. 🧵.
4
2
12
RT @pinecone: ⚡ Rerank API Free Tier.Over the past month we’ve made inference optimizations to expand access to rerank. - Free tier access….
0
6
0
The best vector db in the market is now battle tested by more than 20,000 organizations! Mission critical workloads? Let’s go!!.
Pinecone serverless is now generally available. Build fast and accurate AI applications for mission-critical workloads at up to 50x lower cost. Since public preview, more than 20,000 companies already started building with Serverless.
0
1
4
RT @pinecone: Pinecone serverless is now generally available. Build fast and accurate AI applications for mission-critical workloads at up….
pinecone.io
Since the public preview announcement, more than 20,000 companies have started building with Pinecone serverless. Today, we’re announcing the general availability of Pinecone serverless on AWS.
0
11
0
RT @ShaiDavidai: Earlier today, @Columbia University refused to let me onto campus. Why? Because they cannot protect my safety as a Jewis….
0
10K
0
Pinecone Serverless is out! There is sooo much to be excited about!!.One data point: Common Crawl (~1.4B vectors) on Pinecone Serverless massively improves GPT4 on factual Q&A.
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.
0
1
15
RT @pinecone: Introducing Pinecone serverless, a completely reinvented vector database that lets you easily build fast and accurate GenAI a….
0
81
0