select open change scope Open full search

PG.CENTER connects PostgreSQL documentation, reference, and ecosystem knowledge. Maintained by Pigsty.

Extensions / AI and vectors

ai

Helper functions for AI workflows in PostgreSQL

pgext.cloud · Source code · Documentation · License text · Control file

Overview

Packagepgai
Version0.11.3-dev
PostgreSQL versions16 · 17 · 18
RepositoryUnspecified
Extension typeSQL only
Project statusArchived
Requires CREATE EXTENSIONYes
Requires preloadNo
TrustedNo
RelocatableNo
Schemaai
Stars5,806
Latest commit2026-05-27
Latest release2025-10-14
Catalogue updated2026-08-30

Related extensions

Requires

plpython3uPL/Python3U untrusted procedural language
vectorvector data type and ivfflat and hnsw access methods

See also

tencentdb_aiTencentDB extension for calling large-model APIs and building in-database RAG workflows.
pg_deeplakeDeeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.
pgtokenPostgreSQL extension for compact, codebook-compressed LLM token ID storage. Encode once, retrieve forever. O(1) token count without decoding.
ollamaOllama client for PostgreSQL
ai_toolkitAI-powered query generation and explanation tools for PostgreSQL.
rds_aiAlibaba Cloud RDS extension for calling LLMs, generating embeddings, semantic retrieval, and end-to-end RAG from SQL
avocadoAvocadoDB PostgreSQL extension for deterministic context compilation for AI agents.
lantern_extrasConvenience functions for working with vector embeddings
pgclawStore LLM or OpenClaw agents as PostgreSQL values and process watched rows with a background worker
google_ml_integrationGoogle Cloud machine learning integration extension for registering model endpoints, generating embeddings, and invoking predictions from SQL.
pg_llmIntegrates local and remote large-language models with chat, sessions, text-to-SQL, audit and vector-backed knowledge features.
pg_aiPostgreSQL extension that provides (RAG capable)SQL functions to interpret data using multi modal LLMs and vectors.

Same project

pgaiIn-database predictive analytics using LSTM, Prophet, ARIMA, and SARIMA models.