Create layout/about.md

layout/about.md

@@ -0,0 +1,24 @@
+
+# Meeting Q&A
+
+### What?
+
+This Gradio app is a demo showcasing a meeting Q&A application that retrieves multiple vtt transcripts, uploads them into pinecone as storage, and answers questions using a [fine-tuned llama3 model](https://huggingface.co/tykiww/llama3-8b-meetingQA). Fine-tuning occured using both the instruction tuned alpaca dataset and a noisy synthetic dataset of over 3000+ product, technical, and academic meetings.
+
+### Why?
+
+The goal of the demo is to show you how RAG, prompt-engineering, and fine-tuning can all come together to enhance specific use-cases like meeting querying. This Q&A service seeks to look beyond "summarization" and "next steps" to create a customizable parser that can extract user-defined questions for enhanced specificity.
+
+This is a demo and not a production application. This application is subject to a demand queue.
+
+
+### How?
+
+Just start by following the guide below:
+
+1) On the next page, upload a vtt file from a meeting transcript like Microsoft Teams or Zoom.
+2) Wait for your file to be stored in the vector database.
+3) Query the meeting!
+
+
+This demo is just a peek. More to come!