https://github.com/weaviate-tutorials/llm_vs_rag_demo
Demo illustrating what LLMs are great (and not so great) at, and how RAG can help
https://github.com/weaviate-tutorials/llm_vs_rag_demo
Last synced: about 1 year ago
JSON representation
Demo illustrating what LLMs are great (and not so great) at, and how RAG can help
- Host: GitHub
- URL: https://github.com/weaviate-tutorials/llm_vs_rag_demo
- Owner: weaviate-tutorials
- Created: 2023-12-12T16:50:43.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2023-12-12T18:30:18.000Z (over 2 years ago)
- Last Synced: 2025-03-29T06:11:22.538Z (about 1 year ago)
- Language: Python
- Size: 23 MB
- Stars: 4
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# LLM vs RAG
## Introduction
This demo shows benefits of using retrieval augmented generation over vanilla LLM usage.
## Usage
### Basic example
1. Install `requirements.txt` (`pip install -r requirements.txt`).
1. Run an instance of Weaviate (e.g. `docker-compose up -d` from your shell).
1. Run `eg1_create_collection.py` to create a collection.
1. Run `eg2_import_arxiv.py` and `eg2_import_pdf.py` to import text data from various PDFs.
1. Run `streamlit run Demo_app.py` from your shell.
There is also a multi-modal example - documentation to come :).
## Build amazing GenAI apps with Weaviate
- Start with the [Quickstart guide](https://weaviate.io/developers/weaviate/quickstart)
- The [RAG guide](https://weaviate.io/developers/weaviate/starter-guides/generative) is a good next step
- The [Academy](https://weaviate.io/developers/academy) is a holistic guide combining theory & practice
- The [Recipes](https://github.com/weaviate/recipes) show you practical end-to-end examples