https://github.com/jlenon7/rag_rerank

🤖 Implementation of Compression RAG techniques to teach GPT about Escape from Tarkov ammo items.
https://github.com/jlenon7/rag_rerank

Last synced: 16 days ago
JSON representation

🤖 Implementation of Compression RAG techniques to teach GPT about Escape from Tarkov ammo items.

• Host: GitHub
• URL: https://github.com/jlenon7/rag_rerank
• Owner: jlenon7
• License: mit
• Created: 2024-12-05T21:23:07.000Z (17 days ago)
• Default Branch: main
• Last Pushed: 2024-12-05T21:23:18.000Z (17 days ago)
• Last Synced: 2024-12-06T07:46:56.645Z (17 days ago)
• Language: Python
• Size: 251 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# RAG ReRanker 🤖

> Implementation of Compression RAG techniques to teach GPT about Escape from Tarkov ammo items.

## Tools

The project uses the following tools to work:

- [LangChain](https://python.langchain.com/docs/introduction/)

- [Chroma as Vector DB](https://www.trychroma.com/)

- [GPT 3.5 Turbo as LLM](https://platform.openai.com/docs/models#gpt-3-5-turbo)

- [Cohere Rerank](https://cohere.com/rerank)

- [ADA 002 for Text Embedding](https://platform.openai.com/docs/models#embeddings)

## Running

To run the project first create a new Python environment and activate it. I'm using [Anaconda](https://www.anaconda.com/) for setting the python version that pipenv should use to set up the environment. The command bellow will automatically setup the environment with conda and pipenv:

```shell

make env

```

Now install all the project dependencies:

```shell

make install-all

```

Clone the repositories you want the model to code review:

```shell

make clone

```

Insert the file chunks in Chroma database by running:

```shell

make insert 

```

Ask something by running the following:

```shell

make ask

```

You can change your question inside `bin/ask.py`.