30 lines
882 B
Markdown
30 lines
882 B
Markdown
# README.md
|
|
# LangGraph Code Review Agent
|
|
|
|
This repository implements a **LangGraph** agent that takes a Python function as input and produces a code review. The review is evaluated by a critic node that scores it on four criteria:
|
|
|
|
1. **PEP8 compliance**
|
|
2. **Type hints**
|
|
3. **Edge case handling**
|
|
4. **Naming conventions**
|
|
|
|
If the critic returns **`needs_revision`** the rewrite node improves the weakest part of the review. The process repeats up to ``max_rounds`` times.
|
|
|
|
The implementation uses only the technologies specified in the assignment: ``langgraph`` and ``langchain-ollama`` (or ``langchain-openai`` if you prefer). No vector database is used.
|
|
|
|
## Installation
|
|
|
|
```bash
|
|
pip install -r requirements.txt
|
|
```
|
|
|
|
## Demo
|
|
|
|
Run the demo with:
|
|
|
|
```bash
|
|
python main.py
|
|
```
|
|
|
|
It will review the example function ``sort_numbers`` and print the draft review, scores, and verdict.
|