OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Pany

Pany is a self-hosted semantic-search application that stores document and image embeddings in PostgreSQL with pgvector and lets users search the uploaded content through a browser interface.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Pany — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Pany when you need natural-language or image-based search over uploaded content and want embeddings stored alongside data in PostgreSQL.

Who it is for

  • Developers with PostgreSQL who want semantic search without a separate vector database.
  • Teams organizing searchable document collections, product catalogues, support documentation or image libraries.

Documented uses

  • Upload PDFs, text files and images to a searchable collection.
  • Find documents or images with a natural-language text query.
  • Find visually similar images by uploading an image.
  • Join semantic-search results with existing PostgreSQL records using SQL.
Before you choose

Requirements & limits

The project is open source under the MIT license. The README documents local Python installation and Docker-based setup; it does not establish hosted-service pricing or account requirements.

  • Requires Python 3.9 or later, PostgreSQL with pgvector and at least 4 GB of RAM for the documented local setup.
  • Uses PostgreSQL and pgvector for embedding storage rather than a separate vector database.
  • The README describes CLIP embeddings and cross-modal text and image search.
  • The project is beta software, and its API may change before version 1.0.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Pany locally with Python

Start Pany locally and reach its browser interface for uploading and searching files.

Before you start

  • Python 3.9 or later
  • PostgreSQL with the pgvector extension
  • At least 4 GB of RAM

Steps

  1. Install Pany with the command below.

    Documented command
    pip install pany

  2. Run pany.

  3. Open http://localhost:8000 to upload files and start searching.

Expected outcome

A local browser interface for uploading documents or images and searching them.

Guide limitations

  • The README labels Pany beta software and says its API may change before version 1.0.
  • The PostgreSQL database and pgvector extension are prerequisites.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
laxmanclo/pany · Official homepage title · retained in its source language
How we review sourcesSuggest a correction