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

Resume Screening Rag Pipeline

Resume Screening RAG Pipeline is an open-source proof-of-concept chatbot that uses retrieval-augmented generation to retrieve and process resumes for hiring managers. It can find resumes similar to a job description or retrieve information about applicants identified by ID, then use the retrieved material for comparisons, analysis, summaries, or screening support.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Resume Screening Rag Pipeline — 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 to explore how a RAG chatbot can retrieve resume context for screening queries, or as a proof-of-concept starting point for a hiring workflow. The README cautions that the hosted demo’s file uploader is unstable.

Who it is for

  • Hiring managers exploring resume collections against job descriptions.
  • Developers and researchers studying RAG-based resume retrieval and screening workflows.

Documented uses

  • Retrieve resumes relevant to a job description using similarity search and RAG Fusion.
  • Look up additional information for specified applicants using their IDs.
  • Use retrieved resume content as context for candidate comparisons, analysis, and summaries.
Before you choose

Requirements & limits

The repository is public and identifies an Apache-2.0 license. A hosted Streamlit demo is linked from the project README.

  • The system’s stated scope is a proof of concept and work in progress, not a validated hiring decision process.
  • The README says the deployed file uploader is unstable and recommends against using it.
  • The described retrieval pipeline uses sub-queries, combines and re-ranks results, and traces retrieved chunks to full resume documents.
  • The repository documents local setup and a Streamlit interface; its listed primary language is Jupyter Notebook.

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 and start the local Streamlit demo

Clone the repository, install its dependencies, and start the documented Streamlit interface.

Before you start

  • A local environment with Git, Python, pip, and the project repository available.

Steps

  1. Clone the repository using the documented Git command.

  2. Install dependencies with the README’s pip command.

  3. Start the interface with the documented Streamlit command.

Expected outcome

The project’s Streamlit demo interface is started locally.

Guide limitations

  • The README calls the project a work in progress and proof of concept.
  • The documented commands do not establish that setup or execution will succeed in a particular environment.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Resume Screening Rag PipelineRetrieve resumes relevant to a job description using similarity search and RAG Fusion.WebThe repository is public and identifies an Apache-2.0 license. A hosted Streamlit demo is linked from the project README.
Rag Powered AI Assistant Transforming Data Retrieval And Analysis Across The Web And PdfsRetrieve relevant passages from web and PDF content to answer a question.Web
LangChain in Supabase Edge FunctionsInitialize and start a Supabase project locally.Cloud, Server
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
Hungreeee/Resume-Screening-RAG-Pipeline · Official homepage title · retained in its source language
How we review sourcesSuggest a correction