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

Jev Doc Search

Jev Doc Search is an open-source Python project that uses Jev’s multiple-choice selection and PageIndex’s hierarchical representation to find pages likely to answer questions in long documents. Jev chooses among section nodes and then their children until the search reaches relevant pages; a flat page-by-page method is also shown for shorter PDFs.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Jev Doc Search — 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 it when a long document is too large for a single page-by-page Jev Choice and you want to narrow the search through a hierarchical document tree.

Who it is for

  • Developers building question-to-page lookup for long reports or PDFs.
  • Researchers who want to narrow document searches from sections to likely answer pages.
  • Teams adapting the example workflows to search handbook or report content.

Documented uses

  • Find the page likely to answer a natural-language question in a long PDF.
  • Navigate a report by selecting likely sections and then pages.
  • Use a flat page-choice workflow for a shorter document.
Before you choose

Requirements & limits

  • The hierarchical workflow depends on PageIndex to submit the PDF and provide its document structure.
  • The documented setup requires both TypeSafe and PageIndex API keys.
  • Flat search places page text into one Choice and is constrained by a 32k-token request limit and a maximum of 255 options.
  • The repository identifies its license as Apache 2.0.

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

Set up Jev Doc Search for PDF page search

Prepare the project and API credentials for the documented PDF search workflows.

Before you start

  • Python environment
  • The repository’s requirements file
  • A TypeSafe API key
  • A PageIndex API key

Steps

  1. Install dependencies with the command below.

    Documented command
    pip install -r requirements.txt

  2. Set the TYPESAFE_API_KEY environment variable.

  3. Set the PAGEINDEX_API_KEY environment variable.

Expected outcome

The documented dependencies and credentials are configured for the repository’s flat or PageIndex-backed search examples.

Guide limitations

  • These setup steps do not themselves run a search.
  • The flat page-search method is limited by Jev’s input-token capacity and a maximum of 255 Choice options.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
VectifyAI/jev-doc-search · Official homepage title · retained in its source language
How we review sourcesSuggest a correction