hiring-agent

Thu, 25 Jun 2026 18:26:53 +0800

interviewstreet/hiring-agent

Hiring Agent

Resume-to-Score pipeline that extracts structured data from PDFs, enriches with GitHub signals, and outputs a fair, explainable evaluation.

Overview

Hiring Agent parses a resume PDF to Markdown, extracts sectioned JSON using a local or hosted LLM, augments the data with GitHub profile and repository signals, then produces an objective evaluation with category scores, evidence, bonus points, and deductions. You can run fully local with Ollama or use Google Gemini.

Architecture

Flow

pymupdf_rag.py converts PDF pages to Markdown-like text.
pdf.py calls the LLM per section using Jinja templates under prompts/templates.
github.py fetches profile and repos, classifies projects, and asks the LLM to select the top 7.
evaluator.py runs a strict-scored evaluation with fairness constraints.
score.py orchestrates everything end to end and writes CSV when development mode is on.

Key modules

models.py Pydantic schemas and LLM provider interfaces.
llm_utils.py Provider initialization and response cleanup.
transform.py Normalization from loose LLM JSON to JSON Resume style.
prompts/ All Jinja templates for extraction and scoring.

Installation and Setup

Prerequisites

Python 3.11+

The repository pins .python-version to 3.11.13.
One LLM backend (either of them)
- Ollama for local models Install from the official site, then run ollama serve.
- Google Gemini if you have an API key, get it from here.

Quick setup with pip

$ git clone https://github.com/interviewstreet/hiring-agent
$ cd hiring-agent

$ python -m venv .venv
# Linux or macOS
$ source .venv/bin/activate
# Windows
# .venv\Scripts\activate

$ pip install -r requirements.txt

Ollama Models

Pull the model you want to use. For example:

`1`	`$ ollama pull gemma3:4b`

If you want different results, you can pull other models such as:

# For higher system configuration
$ ollama pull gemma3:12b

# For lower system configuration
$ ollama pull gemma3:1b

Configuration

Copy the template and set your environment variables.

`1`	`$ cp .env.example .env`

Environment variables

Variable	Values	Description
`LLM_PROVIDER`	`ollama` or `gemini`	Chooses provider. Defaults to Ollama.
`DEFAULT_MODEL`	for example `gemma3:4b` or `gemini-2.5-pro`	Model name passed to the provider.
`GEMINI_API_KEY`	string	Required when `LLM_PROVIDER=gemini`.
`GITHUB_TOKEN`	optional	Inherits from your shell environment, improves GitHub API rate limits.

Provider mapping lives in prompt.py and models.py. The config.py file has a single flag:

1
2

# config.py
DEVELOPMENT_MODE = True  # enables caching and CSV export

You can leave it on during iteration. See the next section for details.

How it works

1) PDF extraction

pymupdf_rag.py and pdf.py read the PDF using PyMuPDF and convert pages to Markdown-like text.
The to_markdown routine handles headings, links, tables, and basic formatting.

2) Section parsing with templates

prompts/templates/*.jinja define strict instructions for each section Basics, Work, Education, Skills, Projects, Awards.
pdf.PDFHandler calls the LLM per section and assembles a JSONResume object (see models.py).

3) GitHub enrichment

github.py extracts a username from the resume profiles, fetches profile and repos, and classifies each project.
It asks the LLM to select exactly 7 unique projects with a minimum author commit threshold, favoring meaningful contributions.

4) Evaluation

evaluator.py uses templates that encode fairness and scoring rules.
Scores include open_source, self_projects, production, and technical_skills, plus bonus and deductions, then an explanation for evidence.

5) Output and CSV export

score.py prints a readable summary to stdout.
When DEVELOPMENT_MODE=True it creates or appends a resume_evaluations.csv with key fields, and caches intermediate JSON under cache/.

CLI usage

End to end scoring

Provide a path to a resume PDF.

`1`	`$ python score.py /path/to/resume.pdf`

What happens:

If development mode is on, the PDF extraction result is cached to cache/resumecache_<basename>.json.
If a GitHub profile is found in the resume, repositories are fetched and cached to cache/githubcache_<basename>.json.
The evaluator prints a report and, in development mode, appends a CSV row to resume_evaluations.csv.

Directory layout

.
├── .env.example
├── .python-version
├── config.py
├── evaluator.py
├── github.py
├── llm_utils.py
├── models.py
├── pdf.py
├── prompt.py
├── prompts/
│   ├── template_manager.py
│   └── templates/
│       ├── awards.jinja
│       ├── basics.jinja
│       ├── education.jinja
│       ├── github_project_selection.jinja
│       ├── projects.jinja
│       ├── resume_evaluation_criteria.jinja
│       ├── resume_evaluation_system_message.jinja
│       ├── skills.jinja
│       ├── system_message.jinja
│       └── work.jinja
├── pymupdf_rag.py
├── requirements.txt
├── score.py
└── transform.py

Provider details

Ollama

Set LLM_PROVIDER=ollama
Set DEFAULT_MODEL to any pulled model, for example gemma3:4b
The provider wrapper in models.OllamaProvider calls ollama.chat

Gemini

Set LLM_PROVIDER=gemini
Set DEFAULT_MODEL to a supported Gemini model, for example gemini-2.0-flash
Provide GEMINI_API_KEY
The wrapper in models.GeminiProvider adapts responses to a unified format

Contributing

Please read the CONTRIBUTING.md for detailed guidelines on filing issues, proposing changes, and submitting pull requests. Key principles include:

Keep prompts declarative and provider-agnostic.
Validate changes with a couple of real resumes under different providers.
Add or adjust unit-free smoke tests that call each stage with minimal inputs.

PDF Parsing on Producthunt daily