https://github.com/shreyansh26/rag-ml-engg-open-book
Query the ML Engineering Open Book using RAG
https://github.com/shreyansh26/rag-ml-engg-open-book
gpt-4 langchain openai rag retrieval-augmented-generation
Last synced: 7 months ago
JSON representation
Query the ML Engineering Open Book using RAG
- Host: GitHub
- URL: https://github.com/shreyansh26/rag-ml-engg-open-book
- Owner: shreyansh26
- Created: 2024-04-02T16:31:07.000Z (over 1 year ago)
- Default Branch: master
- Last Pushed: 2024-04-02T17:48:38.000Z (over 1 year ago)
- Last Synced: 2025-01-14T02:13:28.690Z (9 months ago)
- Topics: gpt-4, langchain, openai, rag, retrieval-augmented-generation
- Language: Python
- Homepage:
- Size: 2.93 KB
- Stars: 3
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# RAG-based tool to query the ML Engineeering Open Book
The [ML Engineering Open Book](https://github.com/stas00/ml-engineering) by [Stas Bekman](https://twitter.com/StasBekman) is quite informative and I often tend to refer to it for a quick lookup. I decided to build a quick RAG-based tool to query the repository to find answers to my questions.
Refer steps below to try it out -
1. Clone the ML Engineering Open Book repository
```
git clone https://github.com/stas00/ml-engineering
```
2. Keep the cloned repository in the root folder of this repository or change the path in [app.py](app.py) script.
3. Install dependencies
```
pip install -r requirements.txt
```
4. Run the app
```
python app.py
```
5. Use the [query.py](query.py) script to search with your query.
Optionally, convert the query script to a Gradio app if needed.
I'm sure there can be improvements made in the app, however this version is also proving to be quite useful to me, especially with the sources.