Matvey Arye 🇺🇦
@cevianNY
Followers
507
Following
8K
Media
42
Statuses
1K
Technical Leader @TimescaleDB heading up the AI and vector DB stuff. He/his.
Joined July 2016
Look at what my team has been working on.
It’s mat (@cevianNY), principal eng at @tigerdatadb. I’ve got the mic for a bit. Thought to share what we’ve been building. I’ve been thinking about why LLMs are bad at text-to-sql. Short answer: no context 🧵. Compared to developers, LLMs are more handicapped without context:.
0
0
3
RT @TimescaleDB: 🐯 Timescale is now TigerData! 🚀. Eight years ago, we started as a PostgreSQL-based time-series database. But innovation ne….
0
10
0
RT @acoustik: It's wild that @databricks chose to pay $1 billion (with a 200x multiple) for the slowest Postgres, @neondatabase 🧐 https://t….
0
4
0
RT @TimescaleDB: 🚀 Skip the ETL headaches. Go straight from S3 to PostgreSQL. Traditional ETL pipelines are notorious for creating bottlen….
0
6
0
🚫 Stop treating embedding generation like ETL. ✅ It’s indexing. One of the most common misconceptions in the world of AI and LLMs: 👉 Vector embedding generation = ETL. Nope. It’s much more like building an index. 📊 ETL is about extracting, transforming, and loading data.
1
1
1
Amazing to think I played a small part in building this.
🎉 We’re thrilled to be included in the TWiST500, a list of the top 500 private startups curated by @Jason and @twistartups. It's a special moment for us:.🕰️ Timescale was founded in 2015 with a mission to build the best database for time-series data. 📈 A decade later,.
0
1
3
1 billion embedding? NBD.
Just worked with one of our AI customers at @TimescaleDB with almost 1 BILLION vector embeddings. Who says Postgres can't scale for vectors?!.
0
0
0
RT @bibryam: pgAI - PostgreSQL suite of tools to develop RAG, semantic search, and other AI applications .
github.com
A suite of tools to develop RAG, semantic search, and other AI applications more easily with PostgreSQL - timescale/pgai
0
18
0
This was a huge lift for the team but I am glad we did it. It's the right thing to do.
🐘PGAI VECTORIZER NOW WORKS WITH ANY POSTGRES DATABASE (incl Timescale Cloud, Amazon RDS, Supabase, Azure PostgreSQL, and more). We heard you! After consistent feedback from developers, pgai Vectorizer – the tool for robust embedding creation, management, and experimentation by
0
0
3
Best of all, my team is actively exploring this new direction. We think it’s the future. 🚀. #AI #PostgreSQL #DataIntegration #Innovation.
0
0
1
With PostgreSQL, we have a unique opportunity:. A single platform that can power AI with access to both structured and unstructured data. No silos. Just data.
1
0
0
Let’s skip the pain this time. Let’s not arbitrarily separate our data when AI needs all of it—together.
1
0
0
We’re already heading in a risky direction with separate vector databases that handle only unstructured data. It’s history repeating itself.
1
0
0
💡 For AI applications, do we even need to follow that same path?. Why recreate the same divide between structured and unstructured data?.
1
0
0
Listening to our CTO @michaelfreedman talk about the evolution from data lakes (unstructured) and data warehouses (structured) into unified data lakehouses, I had a thought. .
1
5
10
RT @michaelfreedman: Building a PostgreSQL cloud platform is about more than just managing a database; it's about integrating into your bro….
0
4
0
Manage the embeddings of your documents in S3 through pgai, @PostgreSQL, and @pgvector.
SIMPLIFY DOCUMENT EMBEDDINGS WITH PGAI VECTORIZER: Postgres + Amazon S3. Tired of complex AI pipelines for document embeddings? We've expanded pgai Vectorizer to automatically create searchable vector embeddings in Postgres from documents stored in S3 while keeping the original
0
1
2
RT @michaelfreedman: Fun fact: Weeks ago our initial benchmark results showed Postgres/pgvectorscale crushing Qdrant performance with a de….
0
4
0
The team has put in A LOT of effort into this. I am really proud of the fact that we honestly tried to squeeze the last bit of performance out of Qdrant (our competitor). .
PGVECTOR VS QDRANT: You don’t need a specialized vector database for large scale. Postgres is all you need. 🐘There's a common misconception that Postgres and pgvector can't scale for vectors. That’s why we @TimescaleDB built pgvectorscale, an open-source PostgreSQL extension
0
0
2