Spaces:
Running
Running
| title: Agentic Resume Parser | |
| emoji: 👀 | |
| colorFrom: pink | |
| colorTo: indigo | |
| sdk: gradio | |
| sdk_version: 5.34.2 | |
| app_file: app.py | |
| pinned: false | |
| license: mit | |
| # 🧠 Resume Screener Agent - AI-Powered Matching Tool | |
| This Space hosts a LangChain-powered Resume Screening Agent that matches resumes to job descriptions with structured, explainable scoring. Designed to run on CPU and lightweight models, it works perfectly within Hugging Face Spaces. | |
| --- | |
| ## 🚀 Features | |
| - ✅ Match resumes with job descriptions in seconds | |
| - ✅ Score compatibility (0–100) | |
| - ✅ Extract matched skills | |
| - ✅ Explain decisions with structured JSON output | |
| - ✅ Runs entirely on CPU (swap OpenAI with HuggingFacePipeline for full offline) | |
| --- | |
| ## 🛠️ How It Works | |
| 1. Paste plain text **resume** and **job description**. | |
| 2. Agent evaluates using an LLM prompt chain. | |
| 3. Outputs: | |
| - `MatchScore` (0–100) | |
| - `KeySkills` (list) | |
| - `Justification` (text) | |
| --- | |
| ## 💡 Built With | |
| - [LangChain](https://www.langchain.com/) | |
| - [Gradio](https://gradio.app/) | |
| - CPU-compatible LLMs (e.g., `flan-t5-base`, `oasst-sft-1-pythia`) | |
| --- | |
| ## 📦 Requirements | |
| ```txt | |
| gradio | |
| langchain | |
| openai # Optional, replace with transformers + HuggingFacePipeline | |