https://github.com/mahikshith/llm_resume_parser

Parse resume with local LLM [ollama] in JSON format
https://github.com/mahikshith/llm_resume_parser

llama3 ollama pyhton3

Last synced: about 1 month ago
JSON representation

Parse resume with local LLM [ollama] in JSON format

• Host: GitHub
• URL: https://github.com/mahikshith/llm_resume_parser
• Owner: mahikshith
• Created: 2024-12-23T08:12:02.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-12-23T09:57:19.000Z (over 1 year ago)
• Last Synced: 2025-04-12T17:44:31.930Z (about 1 year ago)
• Topics: llama3, ollama, pyhton3
• Language: Jupyter Notebook
• Homepage:
• Size: 84 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: readme.md

Awesome Lists containing this project

README

          
**This repo is ""Work in Progress""**

## objective : 

To parse a resume and extract relevant information in a valid structured 'JSON' format using LLM 

For this I have used OLLAMA : Llama 3.2 - 3b model via langchain_ollama  

llm_script folder contains the code for the LLM and output parser 

And the script has been run in the ollama_resume_runner.ipynb and tested on a resume 

## Output : 

The output is a JSON file containing the extracted information from the resume. 

## Future work / improvements : 

1. Create a GUI for the user to input the resume 

2. Parse the information in JSON or document format 

3. Scrape Linkedin profile from the resume and extract relevant information

4. Create a knowledge base [embeddings + metadata] using the extracted information for each user

5. Create a internal chatbot using the knowledge base

6. Deploy on AWS