Build in
with Postgres
Lantern Cloud is an open-source Postgres vector database and toolkit for developers to build production-ready AI applications.
Trusted by companies building for scale
Owen Colegrove
Founder, SciPhi
"Lantern is essential to our search infrastructure. We've seen a massive performance improvement over traditional vector databases thanks to serverless indexing."
Daksh Gupta
Founder, Greptile
"We love Lantern! They made it easy for us to implement hybrid search in our application, combining the benefits of text search and vector search all in one."
Kevin Tang
Founder, Firebender
"Lantern is the real deal. They helped make our AI search implementation a breeze and we're able to run it in production with minimal overhead."
Vector search and BM25 in Postgres
Get advanced search functionality inside Postgres with extensions — no separate vector database or search engine required.
Vector search with pgvector
Search over vectors and dense embeddings from machine learning models, and product recommendation engines. Go beyond with accelerated indexing.
Text search with BM25
Use the BM25 ranking algorithm to find the highest relevance search results based on text search criteria. Process large text corpora, providing the best semantic matches available in Postgres.
Hybrid search
Combine vector search with BM25 to get the best of both worlds. Optimize your search results to deliver the most relevant content to users.
Scale to millions with serverless indexing
Scale effortlessly without compromising database performance by offloading vector index creation to a separate machine from your database.
Database scaling visualization
Database #1
Database #2
Infinite scalability
Go as many as 100% resource usage on your DB, without affecting your users or search.
Performance
Build on custom indexes without affecting other query performance.
Seamless integration
Deploy with optimized index creation for vector index creation.
Embedding generation and LLM integrations
Simplify AI workflows by generating embeddings directly within your database.
Generate vectors and run LLMs in Postgres
Use SQL commands to generate vectors and run LLM models.
Support for 20+ embedding models and LLMs
Access to OpenAI, Cohere, JINA and other open source models.
Automatically generate vector and LLM responses
Generate vectors on LLM inference based on your existing data.
Table: Products
| Name | Description | Vector |
|---|---|---|
| Fluffy Socks with... | Cozy socks with... | [0.1,0.5,0.3,...] |
| Dingaling | Using this end of the... | [0.2,0.8,0.5,...] |
| Plum and Pear... | Chocolate filled with... | [0.9,0.1,0.7,...] |
| Pumpkin... | Decorating... | [0.3,0.6,0.2,...] |
| Pencil... | Recording... | [0.4,0.3,0.5,...] |
Easy to use — just use SQL or your favorite ORM
No need to learn a new API or framework. Just use SQL, Prisma, or integrate with your favorite ORM.
-- Create a table with vector support
CREATE TABLE IF NOT EXISTS articles (
id SERIAL PRIMARY KEY,
title TEXT NOT NULL,
content TEXT NOT NULL,
embedding VECTOR(384)
);
-- Insert data and generate embeddings
INSERT INTO articles (title, content, embedding)
VALUES (
'How to use vector search',
'This article explains how to implement vector search...',
embedding('text-embedding-ada-002', 'This article explains how to implement vector search...')
);
-- Search by vector similarity
SELECT title, content, 1 - (embedding <=> embedding('text-embedding-ada-002', 'How to search with vectors')) as similarity
FROM articles
ORDER BY similarity DESC
LIMIT 5;Lantern Cloud
We're open-source, so you can self-host our service or use our managed service for easy setup and scaling.
Free tier
Experiment with vector search and LLMs on a free tier that won't expire.
- All databases included
- Embedding generation
- Vector and LLM generation
- Query insights
- Community support
Production
Everything in free, plus high-performance production workloads.
- Everything in free, plus:
- Unlimited storage
- Automatic backups
- Scale-to-zero resources
- Responsive SLAs
- Priority support