Lantern @lanterndb profile

Lantern

@lanterndb

Followers

357

Following

47

Media

1

Statuses

40

Open-source PostgreSQL vector database to build AI applications. YC W24. GitHub:

https://t.co/6jTbWlzAee

San Francisco, California

Joined June 2023

Don't wanna be here? Send us removal request.

Explore tweets Explore followers Explore following

Explore trending content on Musk Viewer

Se o Twitter • 412221 Tweets

#CrisMorenaDay • 239043 Tweets

Peter • 185617 Tweets

Lucas • 148244 Tweets

Alexandre de Moraes • 118759 Tweets

Threads • 59688 Tweets

Lali • 51565 Tweets

Vatican • 48297 Tweets

De La Cruz • 45069 Tweets

#AEWDynamite • 44949 Tweets

Bahia • 39655 Tweets

#jjk268 • 35859 Tweets

Luciano • 33282 Tweets

Xandão • 28403 Tweets

デコピン • 27481 Tweets

焼肉の日 • 25106 Tweets

Bluesky • 21190 Tweets

Klaus • 20167 Tweets

#ドンシェルジュ • 19509 Tweets

Margarita • 17030 Tweets

Wesley • 15567 Tweets

Hulk • 15293 Tweets

Kaio Jorge • 14148 Tweets

BOSSNOEUL TBNW Q5 • 13351 Tweets

Bernard • 12496 Tweets

Gerson • 11261 Tweets

Battaglia

先頭打者ホームラン

nati jota

ウルショ

Seabra

Everton Ribeiro

ネオユニ

Scarpa

Calleri

Luiz Araújo

フルイド

Loyola

Atlético Mineiro

Igor Gomes

ロブロイ

मेजर ध्यानचंद

राष्ट्रीय खेल

ラグ改善

Jack Perry

Rogério Ceni

Bruno Henrique

Matheus Cunha

Zubeldia

#صاحي_او_نعسان

Last Seen Profiles

@SunitaBaral_

@JackyBrunne

@solarpow3r

@ponyboiofficial

@whatisrussiaorg

@collectjihyo

@iammefor

@LukaHorne97766

@RMjq43q

@MARZHWA

@deviin27

@com_in_

@tdiddy0419

@Mg_danh

@muramon611

@rutu_25

@SgfEdge

@MichaelNeumeir

@capturecheop

@FRiENDi_Oman

Lantern

@lanterndb

8 months

We sped up index creation by 90x over pgvector. HNSW index creation in Postgres is single threaded. This makes index creation slow - you aren’t able to take advantage of multiple cores. We built external index creation to solve this.

90x faster than pgvector — Lantern's HNSW Index Creation Time | Lantern Blog

Index creation time is a critical database metric. Learn more about how Lantern enables 90x faster index creation times than pgvector, and how Lantern compares to Pinecone.

lantern.dev

0

6

19

Lantern

@lanterndb

1 year

Hello world!💡 We're here to shine light on your vector data. ➡️⬅️⬆️⬇️

0

2

11

Lantern

@lanterndb

5 months

Latest blog post - an overview of vector databases and related concepts, including vector embeddings, vector indexing, and vector search

Vector databases explained | Lantern Blog

We give an overview of vector databases, and major concepts around them, including vector embeddings, vector indexing, and vector search.

lantern.dev

0

3

9

Lantern

@lanterndb

8 months

Choosing the right embedding model for your use case is key. Lantern's automatic embedding generation feature makes evaluating models easy. Our latest blog post shows how different embedding models can give different results on code data.

Picking the right embedding model for your vector database | Lantern Blog

Why choosing the right embedding model for vector search makes all the difference, and how to experiment with embedding models more effectively with Lantern

lantern.dev

0

4

9

Lantern

@lanterndb

7 months

Hypothetical Document Embeddings (HyDE) are a neat way to improve the quality of vector search by making your query more similar to your embeddings with an LLM. We wrote an article that gives an overview and walks through an insurance chatbot example.

Improving vector search over documents using HyDE | Lantern Blog

The HyDE technique uses LLMs to improve the quality of vector search over text. In this article, we explain how it works and walk through an example with Lantern as a vector database.

lantern.dev

0

3

5

Lantern

@lanterndb

1 year

@skeptrune @ashvardanian Thanks for your concern! We are in close collaboration with @ashvardanian and unum

1

4