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 - www.catallaxys...
Build a Data Application with Streamlit -- www.catallaxys...
Slide deck -- www.catallaxys...
Demo code -- github.com/fea...
Streamlit documentation -- docs.streamlit...
Limited access to Azure OpenAI Service -- learn.microsof...
Generative AI for .NET Developers talk -- github.com/mic...
Quickly automate SQL Server database documentation to Markdown -- thomasswilliam...
st.radio -- docs.streamlit...
Azure OpenAI on Your Data API Reference -- learn.microsof...
30 сен 2024