Using RAG and Ollama to Make a Health Bot

Using RAG and Ollama to Make a Health Bot

Home

I used RAG to make a medical diagnosis bot that uses med school textbooks to answer questions. Here are the 4 steps I took:

1. RAG storage

I first used Dabarqus, our no-code RAG app (coming soon from Electric Pipelines) to store some public medical textbooks. Notably, for this demo, a neurological textbook.

2. Evaluating the diagnosis

I then grabbed an example neurological assessment from online and had Google Gemini summarize the text.

3. RAG retrieval

I then took the summary I got from Gemini of the assessment and fed that, plus a little context, to Dabarqus to get back some results from our textbooks.

4. Interpretation of RAG data

Finally, this RAG data got passed over to Llama3 via Ollama to be presented in a user-friendly way.

I’m really happy with how it turned out! There’s still a lot of improvement that could be (and will be) made, but this version works as a proof of concept. I still want to add more health info so that I can build an accessible health bot, but one step at a time.

Recent Posts