Skip to main content

A library for interfacing with pg_vector for RAG

This project has been archived.

The maintainers of this project have marked this project as archived. No new releases are expected.

Project description

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.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pgvector_rag-0.5.0.tar.gz (9.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

pgvector_rag-0.5.0-py3-none-any.whl (6.4 kB view details)

Uploaded Python 3

File details

Details for the file pgvector_rag-0.5.0.tar.gz.

File metadata

  • Download URL: pgvector_rag-0.5.0.tar.gz
  • Upload date:
  • Size: 9.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.12.7

File hashes

Hashes for pgvector_rag-0.5.0.tar.gz
Algorithm Hash digest
SHA256 023339d0ee3de8b96055aee44b9112d7a61a20d0f8d4602f9a7835e7d7845dc0
MD5 3793dd54a45d6c1b015bac05e342ef97
BLAKE2b-256 f1c1db27bebaa65334e78cff1e052c2ba07333b34018ea09fff3917262fcb85a

See more details on using hashes here.

File details

Details for the file pgvector_rag-0.5.0-py3-none-any.whl.

File metadata

  • Download URL: pgvector_rag-0.5.0-py3-none-any.whl
  • Upload date:
  • Size: 6.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.12.7

File hashes

Hashes for pgvector_rag-0.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 5fead8d77b3007460e0c4adc0056943eb4b239e96bc6933bb927a89a814b52dd
MD5 905ce248e703748ceeb304d8ef7320a1
BLAKE2b-256 23dd9a6e00d732f19fb66a2207646b4d38d1c1026e31e1344d33ebba5e98481c

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page