PostgreSQL++ for AI applications

Timescale Vector is engineered for fast search with high recall on millions of vector embeddings, making PostgreSQL your go-to vector database for production AI applications.

Timescale AI week

To celebrate the early access release of Timescale Vector, we're doing a week of AI-related launches!

Monday

Introducing Timescale Vector: How we made PostgreSQL a better vector database

Tuesday

Timescale Vector LangChain Integration

Wednesday

Timescale Vector LlamaIndex Integration

Thursday

Timescale Vector Python Client Library

Friday

Timescale Vector Resources and Tutorials

Query millions of vectors in milliseconds

Timescale Vector enhances pgvector with a state-of-the-art, memory-efficient DiskANN index type. Get the performance of a specialized vector database without the hassle of learning and maintaining one.

Read benchmark blog

Access pgvector's indexes, data types, and operators too. Timescale Vector supports exact and approximate nearest neighbor search, cosine distance, and out-of-the-box support for up to 2,000 dimensional vectors.

PostgreSQL is the vector database you want. Now with the performance you need.

Simplify your AI application stackNo need to manage yet another piece of infrastructure. Forget the operational complexity of data duplication, synchronization, and keeping track of updates across multiple systems. Leverage a single, robust platform for your application’s metadata, vector embeddings, and time-series data.

Lightning-fast time-based vector searchSpeed up searching vectors by time with Timescale Vector’s automatic time-based partitioning and indexing. Efficiently find the most recent embeddings. Constrain your search by document date and other metadata. Store and retrieve LLM chat history with ease.

SQL superpowersWrite full SQL relational queries incorporating vector embeddings, complete with WHERE clauses, ORDER BY, and other PostgreSQL features. Leverage all PostgreSQL data types to store and filter richer metadata. Easily JOIN vector search results with relevant user metadata for more contextually relevant responses.

The simplicity and scalability of Timescale Vector's integrated approach to use Postgres as a vector database allows us to bring an AI product to market much faster.

Nicolas Bream

CEO of PolyPerception

Using Timescale Vector allows us to easily combine PostgreSQL’s classic database features with storage of vector embeddings for Retrieval Augmented Generation (RAG).

Alexis de saint Jean

Innovation Director at Blueway Software

Being able to utilize conditions on vectors for similarity, alongside traditional time and value conditions simplifies our data pipelines and allows us to lean on the strengths of PostgreSQL for searching large datasets very quickly.

Web Begole

CTO at MarketReader. MarketReader

Timescale Vector benefits from Timescale’s experience offering cloud PostgreSQL, and we’re excited to use it to confidently and quickly get our LLM-based features into production.

Software Engineer

LegalTech Company

The simplicity and scalability of Timescale Vector's integrated approach to use Postgres as a vector database allows us to bring an AI product to market much faster.

Nicolas Bream

CEO of PolyPerception

Using Timescale Vector allows us to easily combine PostgreSQL’s classic database features with storage of vector embeddings for Retrieval Augmented Generation (RAG).

Alexis de saint Jean

Innovation Director at Blueway Software

Being able to utilize conditions on vectors for similarity, alongside traditional time and value conditions simplifies our data pipelines and allows us to lean on the strengths of PostgreSQL for searching large datasets very quickly.

Web Begole

CTO at MarketReader. MarketReader

Timescale Vector benefits from Timescale’s experience offering cloud PostgreSQL, and we’re excited to use it to confidently and quickly get our LLM-based features into production.

Software Engineer

LegalTech Company

The simplicity and scalability of Timescale Vector's integrated approach to use Postgres as a vector database allows us to bring an AI product to market much faster.

Nicolas Bream

CEO of PolyPerception

Using Timescale Vector allows us to easily combine PostgreSQL’s classic database features with storage of vector embeddings for Retrieval Augmented Generation (RAG).

Alexis de saint Jean

Innovation Director at Blueway Software

Being able to utilize conditions on vectors for similarity, alongside traditional time and value conditions simplifies our data pipelines and allows us to lean on the strengths of PostgreSQL for searching large datasets very quickly.

Web Begole

CTO at MarketReader. MarketReader

Timescale Vector benefits from Timescale’s experience offering cloud PostgreSQL, and we’re excited to use it to confidently and quickly get our LLM-based features into production.

Software Engineer

LegalTech Company

Scale from POC to Production

One platform for your AI application

Timescale’s enhanced PostgreSQL data platform is the home for your application's vector, relational and time-series data.

Flexible and transparent pricing

No “pay per query” or “pay per index”. Decoupled compute and storage for flexible resource scaling as you grow. Usage-based storage and dynamic compute (coming soon), so you pay only for what you actually use.

Ready to scale from day one

Push to prod with the confidence of automatic backups, failover and High Availability. Use read replicas to scale query load. One-click database forking for testing new embedding and LLM models. Consultative support to guide you as you grow at no extra cost.

Enterprise-grade security and data privacy

SOC2 Type II and GDPR compliance. Data encryption at rest and in motion. VPC peering for your Amazon VPC. Secure backups. Multi-factor authentication.