Skip to main content
Archived

This project has been archived by its maintainers, and is no longer receiving any updates.

pgvector-rag

A simple library for working with RAG documents using pg_vector in PostgreSQL.

Documents will pass through an optimization stage where the content is converted to markdown, submitted to Anthropic's Sonet 3.5 to optimize the content, and the response is used to a store a conside revision of the document.

OpenAI's text-embedding-3-small is used to generate the embeddings for the for the document and used to generate the embeddings to compare against in the database.

Schema is contained in the postgres directory.

Install with pip install pgvector-rag.

Release files for pgvector-rag 0.5.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for pgvector-rag 0.5.0
File Size Uploaded
pgvector_rag-0.5.0.tar.gz 9.7 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for pgvector-rag 0.5.0
File Interpreter ABI Platform
pgvector_rag-0.5.0-py3-none-any.whl Python 3 none any Details

Total release size: 16.1 kB

Release files / pgvector_rag-0.5.0.tar.gz

Download URL pgvector_rag-0.5.0.tar.gz
Size 9.7 kB
Tags Source
SHA-256 checksum
How to use checksums
023339d0ee3de8b96055aee44b9112d7a61a20d0f8d4602f9a7835e7d7845dc0
BLAKE2b-256 checksum
How to use checksums
f1c1db27bebaa65334e78cff1e052c2ba07333b34018ea09fff3917262fcb85a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.0.1 CPython/3.12.7

Release files / pgvector_rag-0.5.0-py3-none-any.whl

Download URL pgvector_rag-0.5.0-py3-none-any.whl
Size 6.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
5fead8d77b3007460e0c4adc0056943eb4b239e96bc6933bb927a89a814b52dd
BLAKE2b-256 checksum
How to use checksums
23dd9a6e00d732f19fb66a2207646b4d38d1c1026e31e1344d33ebba5e98481c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.0.1 CPython/3.12.7
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page