Resume Analyser, many LLMs consensus to identify and reduce allucinations, bias and outliers. This is a multistep program (not a ReAct agent) that uses many LLMs to peform operations of classification and evaluation to then process the results with classical DS techniches. Langchain acts as orchestrator. June 2024

demo_unify_resume_analyser.mp4

LLM Resume Analyser: A Comprehensive LLM-Powered Demo App

The LLM Resume Analyser demonstrates the transformative potential of large language models (LLMs) in recruitment, connecting job applicants with employers or recruiters.

Key Features:

Resume Analysis: Extracts and analyzes key skills and qualifications from resumes. Matching Score: Computes a match score for resumes against job descriptions. Semantic Matching: Uses the Unify API to semantically analyze and match resumes with job descriptions using multiple LLMs. Distributed Skills Match: Highlights how job requirements are represented across all applicant skills and experiences. Suggestions and Resume Improvement: Provides suggestions for resume enhancement and compares the original with the improved version. Alternative Job Titles: Suggests other job titles that match the resume. Custom Model Utilization: Allows dynamic routing and integration of various models under OpenAI standards. The app leverages the Unify API for dynamic routing and access to various models, ensuring precise and comprehensive recruitment analysis.

Tech Stack

Streamlit: Used for creating the web application interface that is intuitive and interactive.

Unify AI: Provides the backend LLMs that power the interactions within the application. Unify's API is utilized to send prompts to the LLMs and receive their responses in real-time.

Langchain: LangChain is a powerful framework designed for building applications that integrate with large language models (LLMs), enabling complex interactions and workflows by chaining together various components like prompts, LLMs, and data sources

Introduction

You find more model/provider information in the Unify benchmark interface.

Usage:

1. Visit the application: LLM Resume Analyser
2. Input your Unify API Key. If you don’t have one yet, log in to the Unify Console to get yours.
3. Select the model and provider of your choice
4. Upload your document(s) and click the Submit button
5. Enter your job description and job title
6. Gain insights on Resume match with the job offer and on how to improve your Resume

Repository and Deployment

To run the application locally, follow these steps:

1. Clone the repository to your local machine.

git clone https://github.com/Sanjay8602/LLM-Resume-Analyser-using-Unify

2. Set up your virtual environment and install the dependencies from requirements.txt:

python -m venv .venv    # create virtual environment 

source .venv/bin/activate   # on Windows use .venv\Scripts\activate.bat

pip install -r requirements.txt

3. Run app.py from Streamlit module

python -m streamlit run analyser.py

Contributors

Name	GitHub Profile
OscarArroyoVega	OscarAV
Sanjay Suthar	Sanjay0806
Mayssa Rekik	Mayssa Rekik