OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Data & Analytics

Product Intelligence

Product Intelligence is a multimodal product-catalog application that embeds product images and text, enriches catalog records, and supports hybrid search, recommendations, duplicate detection and price estimates through a typed REST API and a Next.js console.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Product Intelligence — OpenViST project profile in AI Data & Analytics.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a product catalog needs multimodal ingestion and retrieval, or when teams want recommendations, duplicate detection and price estimates accompanied by structured decision traces.

Who it is for

  • Teams building product catalogs that need image-and-text search and enrichment.
  • Catalog operators who need duplicate verdicts, recommendations or comparable-based price estimates with visible decision reasoning.
  • Developers preparing a local backend using the documented Python, Docker, Qdrant and Redis setup.

Documented uses

  • Turn product photos and metadata into enriched, indexed catalog entries.
  • Search a catalog using image similarity, text similarity or a weighted combination.
  • Review duplicate verdicts and recommendations alongside the signals behind them.
  • Inspect price estimates and the comparable products used or excluded.
Before you choose

Requirements & limits

  • The documented backend stack is Python 3.12 and FastAPI, with Qdrant and Redis as backing services and a Next.js console.
  • Image and text embeddings use CLIP and BGE respectively; the README specifies 512-dimensional image vectors and 384-dimensional text vectors.
  • The README says enrichment runs locally with CPU-only PyTorch and no external LLM calls; a cross-encoder is optional.
  • Asynchronous uploads require a separately running worker.
  • The repository documents both Docker-based setup and a host-based backend setup; the latter requires Python 3.12, uv and Docker.

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

Prepare the backend for local use

Set up the documented host-based backend and its backing services.

Before you start

  • Python 3.12
  • uv
  • Docker for Qdrant and Redis

Steps

  1. Install backend dependencies with the command below (the README describes it as the command below plus pre-commit installation).

    Documented command
    make install
    Documented command
    uv sync

  2. Start Qdrant and Redis with the command below.

    Documented command
    make services-up

  3. Start the API with the command below; the README points to http://localhost:8000/docs.

    Documented command
    make run

  4. In a second terminal, start the worker with the command below for asynchronous uploads.

    Documented command
    make worker

Expected outcome

A locally started backend, its Qdrant and Redis services, API documentation, and the worker needed for asynchronous uploads.

Guide limitations

  • The guide covers backend setup, not catalog-ingestion or search execution.
  • The worker is required for asynchronous uploads.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
18 October 2026
Original website title
Vikas9892/product_intelligence · Official homepage title · retained in its source language
How we review sourcesSuggest a correction