di qi
@diqitally
Followers
1,527
Following
860
Media
34
Statuses
327
cofounder @lanterndb (yc w24). prev @ycombinator @princeton .
San Francisco, CA
Joined October 2022
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
Botafogo
• 175227 Tweets
#AgathaAllAlong
• 139661 Tweets
Flamengo
• 99518 Tweets
ドラフト
• 70349 Tweets
Brey
• 64930 Tweets
Warriors
• 61365 Tweets
Riquelme
• 53756 Tweets
Cruzeiro
• 52588 Tweets
Lilia
• 48396 Tweets
Anderson Cooper
• 38799 Tweets
#AEWDynamite
• 33753 Tweets
Romero
• 32150 Tweets
Steph
• 23644 Tweets
Gimnasia
• 23629 Tweets
#CNNTownHall
• 23449 Tweets
Sanatan Sanskriti
• 23377 Tweets
Suns
• 16911 Tweets
非公認側
• 13998 Tweets
Clippers
• 12755 Tweets
Luiz Henrique
• 11947 Tweets
Savarino
• 10757 Tweets
Dana Bash
• 10418 Tweets
we went to an
@OpenAI
x
@ycombinator
hackathon this week!
@ngalstyan4
and i built an app to iteratively build postgres extensions - it generated a median aggregate function extension successfully :)
11
13
368
I left my job at
@ycombinator
last year to build a startup. Today was our first in-person office hours for W24 with
@gustaf
!
There's so many things that are special about YC, but for me the optimism stands out the most. I'm excited to experience it from the startup side again :)
18
7
218
We just launched
@lanterndb
on
@ycombinator
! 🚀
Lantern is a Postgres vector database that is easy to use, cost-effective, and scales to billions. We support embedding generation, index compression, and external index creation.
21
23
171
The
@ycombinator
retreat ended a few days ago. It was super exciting although I'm just now catching up on sleep.
We're a company built on Postgres, so one highlight was spending an hour talking about Lantern with one of the
@citusdata
founders.
I'm so grateful for this
2
6
75
i don't need a big house.
i don't need a fancy car.
i don't need to travel the world.
i just need the admiration of the two hundred regulars who comment on every hacker news post to support me in whatever i do.
1
4
38
We built external indexing for pgvector in Postgres.
External indexing offloads the resource-intensive index creation process to external machines to reduce the impact on database performance.
Read the blog post from
@D4RK7ET
below 👇
4
7
37
thanks for the shoutout
@TechCrunch
:)
we're building postgres for ai companies. if you're using a specialized vector db or want to improve your postgres performance, please reach out! we'd love to help.
YC’s latest Demo Day shows fascinating wagers on healthcare, chip design, AI and more
2
20
47
1
4
31
@annaarthoe
he stole from lululemon so he could have a shirt on his back, a table from crate & barrel so he didn't have to eat off the floor
1
0
23
fundraising kicked off about 2 weeks ago, and alumni demo day is tomorrow, so things have been a bit hectic.
excited to be 100% back to building / writing soon, but here's an article from us in the meanwhile :)
Latest blog post - an overview of vector databases and related concepts, including vector embeddings, vector indexing, and vector search
0
3
9
1
1
21
Open AI released their new embedding models last month
We worked with
@JoschkaBraun
to evaluate the new models on a healthcare dataset
We used
@lanterndb
for embedding generation / storage and
@PareaAI
for evaluation
Love learning form other YC cos😊
3
7
21
meeting yc w27 founders and explaining to them that back in my day, zero companies were building for the vision pro
3
0
17
some of
@lanterndb
's engineering updates for april! including
- async tasks
- weighted vector search
-
@ubicloudhq
control plane
- dashboard improvements
0
5
17
Last week we released product quantization (PQ) in Postgres with
@lanterndb
! 🚀
We ran benchmarks over 100M 768d image embeddings. With re-ranking, we got
▶ 90% recall
▶ 73 ms query times
▶ Reduced memory usage from ~300GB => ~60GB
2
3
17
My cofounder
@ngalstyan4
wrote a blog post about how different operations like indexing affect write-ahead logging (WAL) sizes in Postgres 🔍
2
7
16
tech companies getting engineers to talk to customers by calling them "forward deployed engineers" was one of the greatest tricks of my lifetime.
1
0
16
great to see a major tech company that's avoided layoffs over the last 2 years:
0
0
15
We wrote a bit on using Postgres vs. ElasticSearch vs. Algolia for search 👇
4
2
15
we hit 500 stars on github today! ⭐
we have a performance upgrade and new benchmarks coming soon, stay tuned... 😊
2
4
14
🚀 you can now use
@lanterndb
with
@LangChainAI
! 🦜
tutorial coming soon. s/o to
@WHinthorn
for the assist 😊
1
4
14
We added client libraries for Knex, Sequelize, MikroORM, and Drizzle for
@lanterndb
! Perform vector search or embedding generation using your favorite JS ORM ☺️
Let us know what you think!
2
3
13
Do you stream vector embeddings into a Postgres instance? This might be relevant to you.
TLDR: a small schema change may make your pipeline 30-50% more efficient. How? - Generate less WAL, use fewer CPU cycles on WAL and applying table / index changes
0
4
12
Tell me you’re a systems programmer without telling me you’re a system programmer (my cofounder)
PL I dislike: Makefile
PL I begrudgingly respect: C++
PL I think is overrated: JS/Python
PL I think is underrated: OCaml
PL I like: C
PL I love: Rust
PL I dream of mastering: C++
2
0
11
kinda funny to see someone scrolling robinhood while bored on a first date
2
0
11
when my dog is sick: home cooked pumpkin rice and fish porridge
when i am sick: mucinex and pizza rolls
1
0
11
We built a Pinecone => Postgres export tool!
With a few lines of code, you can export your Pinecone data to Postgres, and build an index using Lantern.
0
2
9
I built a site to browse the Postgres mailing list archives. It supports search using FTS from Postgres + vector search with the Lantern extension.
I've been using it for testing but cleaned it up a bit to share 🙂
0
3
10
rereading books after a few years with a different perspective is nice
1
0
8
hacker after remotely accessing my computer and seeing how i organize my desktop:
0
0
8
fun talk at
@pgconfnyc
: “elections are weird” featuring many, many more table schemas for elections than you would expect 😅
0
0
7
born too early to explore space
born too late to explore the earth
born just in time to compete with GPT4 for my own job
1
1
7
This week we worked on docs for using
@lanterndb
with
@llama_index
!
We added an overview of how to get started:
We also added a guide to auto-retrieval:
Would love to learn more about the tutorials people like with LlamaIndex :)
0
3
7
Thank you to our partners,
@gustaf
@bradflora
@dflieb
@garrytan
@daltonc
, as well as others at YC I've gotten to know over the last few years
When I did YC S20, it was fully remote. I'm grateful I got the chance to experience it in-person this time 🧡
0
0
6
The
@GetOnboardAI
team set up a Learn This Repo for Lantern! It's a free tool to ask questions about our source code.
Our source code is available at
Give it a try! ☺️
Introducing , a free tool from Onboard AI.
LTR let's you chat with 300+ of our most popular open source repos for free. From Redis, to Postgres, to NextJS, to LangChain.
Why did we build this?
1. The best way to become a better programmer other than
1
3
13
1
2
6
@snowmaker
cofounder matching is such a great product :) i'm always recommending it and work at a startup to people
0
1
5
played around with full text search in postgres this weekend
1
1
4
To use it, just call CREATE INDEX with external=true. Concurrent indexing is supported, and subsequent reindexes also use external indexing
Our pgvector fork to enable external indexing:
Our CLI to run the external indexing server:
0
0
5
customers in 2003: pdfs are bad
customers in 2013: pdfs are bad
customers in 2023: pdfs are bad
founders in 2024: we fixed it!! you can now chat with pdfs… using ai.
customers: what
3
0
5
today's schedule:
8:00am - 2:00pm: try to fix this bug
2:01 - 2:03pm: fix the bug
2:04 - 7:00pm: complain to the people around me about how ridiculous finding that bug was
0
0
5
@eshear
I don’t think this is a proof for that? Both are invalid.
- a plank of wood is not a boat
- adding a plank of wood to something that isn’t a blank of wood doesn’t make it a boat
And yet a boat can be comprised of wood planks.
Something can exist only in the aggregate.
0
0
5
investors: do you have a plan for monetization?
founders: i have concepts of a plan
0
0
4
🚀
@lanterndb
is now available on
@llama_index
! 🦙
s/o to
@disiok
for the assist, you guys are so fast :) excited to ship tutorials next week
1
1
4
I feel like southern Thanksgiving recipes don't actually need all this butter, they just add it in because they saw it and thought why not
1
0
3
@ShaanVP
I think they're a lens to understand people better - not just the subject but also yourself, your friends, people with similar or dissimilar traits.
0
0
3
0
0
3
Our managed service is currently in beta at – reach out for access!
Or self-host! Our source code is available at
It's been incredible to work with
@ngalstyan4
and
@D4RK7ET
on this. I can’t believe the number of 4am nights 😅
1
0
3
This week we released product quantization (PQ) in Postgres.
For 35M 768 dimension vectors with (m=16), PQ can reduce the index size from ~105GB to ~10GB.
If you’re self-hosting, this can take your monthly cost from ~$1000 to ~$100.
1
1
3
@chefjeffsf
@andrew__rea
I have some conflict about this -- I agree but at the same time for myself these were often fundamentally bad experiences that I don't want to feel "thankful" for
1
0
3
@mralanagon
@ycombinator
@lanterndb
Hey! I'm not aware of Firebase supporting vector search.
AI / Vector support is our core focus. Unlike the others, we built features like PQ quantization, external indexing, inline embedding generation in Postgres, etc. that specifically target AI application needs.
1
0
1
@nooriefyi
@D4RK7ET
We'll be releasing some additional Postgres extensions next week!
For external indexing, we'd love to support other more expensive indexing processes, such as GIN and GIST.
0
0
3
I would like to experience Papa John's as an 8 year old again, the purest form of joy
1
0
3
@Zach_Kamran
@ycombinator
@gustaf
@ngalstyan4
I can’t believe I only got to work in person for 3 days 😅
0
0
2