# 🤝 Multi-Meeting Q&A RAG 🤝

![](../assets/emoji_meeting.png)

## What is this ?

This is a demo meeting Q&A app that retrieves multiple meeting transcripts and answers questions for analysis across meetings.

Context uses retrieval augmented generation (RAG) and the LLM uses the latest [Llama3.1 model](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct). 


## Why is this important?

**The value** of the underlying technology is its ability to retrieve necessary context and analysis from *multiple* documents to draw answers from within minutes!

Think uploading hundreds of documents and then chaining the LLMs to automatically attack multiple structured questions in delivering a tailored report.


## How to use?

There are 2 ways to start!

1. Quickstart: ⏭️ Just skip over to the Q&A Tab and ask a question to immediately query the existing meeting demo database.

2. Upload your own docs:

    1. 🪙 On the next page, Start by generating a unique token
    2. 📁 upload several vtt files from a meeting transcript from a service like Microsoft Teams or Zoom
    3. ⤮ Wait for your file to be stored in the vector database.
    4. ❓ Query across the meetings you uploaded!


## Notes

For the purposes of this demo, the pre-stored meetings are a "clean" set of synthetic meetings aimed at inquiring about challenges with meeting effectiveness. I know, how meta. This demo can be taken a step further by using our [fine tuned model](https://huggingface.co/tykiww/llama3-8b-meetingQA) trained both on the alpaca dataset and a *noisy* synthetic dataset of over 3000 product, technical, and academic meetings. Unfortunately, the lack of a persistent GPU on the free Huggingface Zero GPU spaces posed some challenges, so the fancy 3.1 model should do just fine! It's already a massive improvement over the base Llama 3 family of models.

Additionally, in the spirit of a demo, we are trading off accuracy with speed by using a single vector store rather than a carefully crafted node system.

Furthermore, for security purposes, uploaded meetings will only be retained for 1 hour and will automatically be deleted without warning. To query your meetings, please use your specific session key to access the data you uploaded.

This demo is just a peek. More to come!