Blog
Postgres·Pgvector·Cloud·Llm·Demo
A code chatbot in 15 minutes with Postgres
Learn how to build a powerful, scalable code chatbot using Lantern on Ubicloud in under 15 minutes. All open-source tooling, from embedding models to cloud providers.
October 24, 2024 · 7 min read
Di Qi
Cofounder
Demo
Bank Compliance Automation with Lantern and Ecliptor
In this article, we show how to use Lantern, Ecliptor, and OpenAI models to automate compliance checks in the banking industry. We'll use Ecliptor for document processing, Lantern for vector search, and OpenAI's embedding models and LLMs to automate compliance checks.
October 21, 2024 · 9 min read
Di Qi
Cofounder
Postgres·Pgvector
CREATE INDEX EXTERNALLY: Offloading pgvector Indexing from Postgres
We introduce external indexing for pgvector in Postgres to reduce performance issues caused by large dataset indexing. External indexing offloads the indexing process to external machines, reducing the impact on database performance.
October 1, 2024 · 6 min read
Varik Matevosyan
Software Engineer
Postgres·Pgvector
Understanding pgvector's HNSW Index Storage in Postgres
In this article, we'll explore how pgvector works under the hood, focusing on how the HNSW index is stored in Postgres.
August 19, 2024 · 8 min read
Varik Matevosyan
Software Engineer
Cloud·Postgres
Analysis of Key PostgreSQL Configuration Differences Among Cloud Providers
We dicuss some differences in PostgreSQL configuration parameters among cloud providers, why they matter, and their implications for users.
August 13, 2024 · 5 min read
Narek Galstyan
Cofounder
Learn·Benchmark·Pgvector
Hybrid Vector Search in Postgres
Hybrid vector search combines the strengths of sparse and dense vector searches to improve search quality. We evaluate its performance on several datasets from the BEIR framework using Postgres.
August 5, 2024 · 8 min read
Di Qi
Cofounder
Pinecone·Postgres·Benchmark·Pgvector
Postgres vs. Pinecone
We respond to Pinecone's recent blog post comparing Postgres and Pinecone. We show that Postgres can outperform Pinecone in the same benchmarks Pinecone covered in their article.
July 18, 2024 · 11 min read
Narek Galstyan
Cofounder
Pinecone
When using Pinecone, do not rely on returned scores - recalculate distances locally
When benchmarking Pinecone against Postgres, we noticed some inconsistencies with returned results. We recommend recalculating and re-sorting returned results locally when using Pinecone for nearest neighbor vector queries.
July 17, 2024 · 4 min read
Narek Galstyan
Cofounder
Postgres
Dynamically loaded extensions in Postgres in the browser
We build on top of pglite to support loading Postgres extensions directly in the browser. We share a demo using geospatial search and vector search from Lantern, and discuss technical challenges we encountered.
July 12, 2024 · 6 min read
Varik Matevosyan
Software Engineer
Postgres·Learn·Permissions
Understanding Postgres Table Permissions
This blog post helps interpret Postgres's terse permission strings with examples and visuals.
July 10, 2024 · 7 min read
Narek Galstyan
Cofounder
Postgres·Vector·Optimization
Use separate tables for asynchronous embedding generation
In this article, we'll explore a problem faced when extending traditional Postgres tables with an additional column for embeddings. We will describe a typical setting for asynchronous embedding generation and will show how table schema design can have a significant impact on storage and performance efficiency.
May 8, 2024 · 7 min read
Narek Galstyan
Cofounder
Postgres·WAL·Index
Understanding and Estimating Write-Ahead Log (WAL) Size in Postgres
This blog post looks into the underlying plumbing of WAL records - when they are created, what information they contain, and how different database operations like indexing affect the kind of WAL records being created.
May 7, 2024 · 10 min read
Narek Galstyan
Cofounder
Product
April 2024 - Engineering Updates
Engineering updates for April 2024, including asynchronous tasks, weighted vector search, and more.
May 1, 2024 · 2 min read
Di Qi
Cofounder
Benchmark·Product
Product Quantization in Postgres
We implemented product quantization in Lantern and benchmarked it using the LAION 100M 768-dimensional vector dataset.
March 5, 2024 · 8 min read
Di Qi
Cofounder
Varik Matevosyan
Software Engineer
Benchmark·OpenAI
Evaluating OpenAI's new embedding models with Lantern and Parea AI
OpenAI's newest embedding models promise huge performance increases. Using Lantern's Postgres vector database, and Parea AI's testing platform, we'll measure the new models in a real-world test.
February 29, 2024 · 6 min read
Di Qi
Cofounder
Learn
Vector databases explained
We give an overview of vector databases, and major concepts around them, including vector embeddings, vector indexing, and vector search.
March 29, 2024 · 12 min read
Di Qi
Cofounder
Search·Algolia·ElasticSearch
Postgres vs ElasticSearch vs Algolia - Comparing the Best Search Solutions
Don't overcomplicate things with an external search engine like ElasticSearch or Algolia. Postgres as your search engine and database makes things simple and scalable for a few great reasons.
February 2, 2024 · 11 min read
Di Qi
Cofounder
Learn
Improving vector search over documents using HyDE
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.
January 22, 2024 · 7 min read
Di Qi
Cofounder
Danyil Blyschak
Software Engineer
Embedding·Learn
Picking the right embedding model for your vector database
Why choosing the right embedding model for vector search makes all the difference, and how to experiment with embedding models more effectively with Lantern
January 15, 2024 · 12 min read
Di Qi
Cofounder
Danyil Blyschak
Software Engineer
Pinecone·Migration·Product·Learn
Migrating from Pinecone to Lantern
Pinecone is a popular closed-source vector database. We built a Python library to support migrating data from Pinecone to Lantern. This article covers how we built it and how to use it.
January 6, 2024 · 6 min read
Di Qi
Cofounder
HNSW·Learn·Memory·Index·Quantization·Vector
Estimating memory footprint of your HNSW index
This interactive visualization will help you quickly reason about the resources necssary to host your embeddings and serve nearest neighbor queries over them
December 22, 2023 · 10 min read
Narek Galstyan
Cofounder
Learn·Search·Postgres
Full Text Search + Vector Search with Postgres
Search is a common need for many applications. Postgres supports search out of the box with regex matching and full text search. This can be augmented with vector search.
December 16, 2023 · 11 min read
Di Qi
Cofounder
Learn·Vector·HNSW·Index
The Hierarchial Navigable Small Worlds (HNSW) Algorithm
An explanation of the Hierarchial Navigable Small Worlds (HNSW) Algorithm
November 19, 2023 · 4 min read
Di Qi
Cofounder
Learn·Embedding
Embeddings and choosing the right model
An overview of embeddings and what to consider when choosing an embedding model
November 13, 2023 · 6 min read
Di Qi
Cofounder
Benchmark·Product
90x faster than pgvector — Lantern's HNSW Index Creation Time
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.
October 20, 2023 · 8 min read
Varik Matevosyan
Software Engineer
Company
Launching Lantern — a PostgreSQL vector database for building AI applications
Today we’re launching Lantern, an open-source PostgreSQL vector database.
September 13, 2023 · 3 min read
Narek Galstyan
Cofounder