Chat with Your Own Data with Streamlit
In this video, I show how we can make a GPT-4 deployment aware of our own custom data, without needing to fine-tune the model. I talk about meta prompts and the Retrieval Augmented Generation (RAG) pattern, and then show how you can set this up using Azure AI Search and Azure OpenAI. Then, I bring it back to Streamlit and give users the option between chatting with a generic GPT-4 deployment and chatting over custom data.
LINKS AND INFO
Catallaxy Services - https://www.catallaxyservices.com
Build a Data Application with Streamlit -- https://www.catallaxyservices.com/pre...
Slide deck -- https://www.catallaxyservices.com/med...
Demo code -- https://github.com/feaselkl/Build-a-D...
Streamlit documentation -- https://docs.streamlit.io/get-started
Limited access to Azure OpenAI Service -- https://learn.microsoft.com/en-us/leg...
Generative AI for .NET Developers talk -- https://github.com/microsoft/communit...
Quickly automate SQL Server database documentation to Markdown -- https://thomasswilliams.github.io/sql...
st.radio -- https://docs.streamlit.io/develop/api...
Azure OpenAI on Your Data API Reference -- https://learn.microsoft.com/en-us/azu...