Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/lukasmosser/icml2024_finder
Find relevant sessions at ICML 2024
https://github.com/lukasmosser/icml2024_finder
Last synced: 28 days ago
JSON representation
Find relevant sessions at ICML 2024
- Host: GitHub
- URL: https://github.com/lukasmosser/icml2024_finder
- Owner: LukasMosser
- License: apache-2.0
- Created: 2024-07-17T12:38:24.000Z (4 months ago)
- Default Branch: main
- Last Pushed: 2024-07-24T05:45:39.000Z (4 months ago)
- Last Synced: 2024-07-24T07:07:58.889Z (4 months ago)
- Language: Python
- Size: 1.26 MB
- Stars: 1
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ICML 2024 Session Finder.
Welcome to the ICML 2024 Session Finder! This tool helps you search for sessions and ask questions about them using a Retrieval Augmented Generation (RAG) pattern. The selected sessions include the session name, authors, time, location, and abstract, which are added to the language model's prompt.
## Just get me to the tool
Access the [ICML Session Finder here: Link](https://lukasmosser--icml-finder-run.modal.run/)
## Features
- Session Search: Search for ICML sessions using natural language queries.
- Selected Sessions: Add sessions to your list of selected sessions.
- Session Chat: Ask questions about your selected sessions and receive AI-generated responses.
## How to Use
1. Set a Good Window Height: Adjust the chat window height in the sidebar.
2. Ask Questions: Ask any questions about all the sessions to find relevant content.
3. Utilize the Language Model: Request the language model to perform tasks on the selected sessions, such as "Make me a schedule for these" or "Tell me what these have in common."
4. Enjoy ICML!
## Why?!
I participated in the [Parlance Labs Conference - Mastering LLMs: A Conference For Developers & Data Scientists](https://maven.com/parlance-labs/fine-tuning) which gave me 1000s of dollars of free credits for all kinds of services including [Modal Labs](https://modal.com/) and [OpenAI](https://openai.com) and I wanted to put them to good use and make something practical.
## Tech Stack
- Hosting: [Modal Labs](https://modal.com/)
- CI/CD: [Github Actions](https://github.com)
- LLM: [OpenAI GPT-4o-mini](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/)
- Embeddings: [OpenAI Text-003-large](https://openai.com/index/new-embedding-models-and-api-updates/)
- VectorDB: [LanceDB](https://lancedb.com/)
- Reranker: [Cohere.ai](https://cohere.ai)
- Frontend: [Streamlit](https://streamlit.com)
- Dataset Hosting: [Huggingface Datasets](https://huggingface.co/datasets/porestar/icml2024_embeddings)
The dataset is downloaded from [ICML Downloads](https://icml.cc/Downloads)
## Socials and Disclaimer
If you have any questions leave an issue on [Github](https://github.com/LukasMosser/icml2024_finder)!
If you like this give me shoutout on [Twitter](https://twitter.com/porestar) or [LinkedIn](https://www.linkedin.com/in/lukas-mosser/)!
Last updated Thursday July 21st!
Double check the programme for correctness!
No warranty provided or any claims to the content.