JBMDL assistant, first version
The first version of the AI assistant I built for Joint Base McGuire-Dix-Lakehurst: ask by text or voice, get cited answers.
A Streamlit app where people ask questions by typing or speaking. A LangChain pipeline answers from the base's public documents, PDFs people upload, or a web search, and cites where each answer came from.
It also translates, so people can ask in more than one language.
Person
Types or speaks
Streamlit app
Speech-to-text, translation, LLM chain
Public documents
Uploaded PDFs
Web search
- Person and Streamlit app: question, answer
- Streamlit app to Public documents
- Streamlit app to Uploaded PDFs
- Streamlit app to Web search