Using RAG
Your Toolhouse agents can perform Retrieval Augmented Generation (RAG) using your own data. Toolhouse includes a fully managed RAG pipeline that includes storage, upload, chunking, and retrieval. Toolhouse RAG is already integrated into your agent.
Here's how Toolhouse RAG works:
You upload files to the Toolhouse RAG.
Toolhouse triggers the RAG pipeline. Your RAG files will be analyzed to determine the chunking strategy.
You assign a RAG folder to one or more agents.
When you call the agent, it will know that it has a RAG folder available and it will be automatically prompted to use your RAG folder to complement its knowledge and better inform its context.
Basic flow
Supported File Types
Toolhouse RAG supports most text-based files and PDFs. The size limit is 10 MB for each file you upload.
application/pdf
.txt
text/plain
.text
text/plain
.log
text/plain
.ini
text/plain
.conf
text/plain
.csv
text/plain
.asc
text/plain
.lst
text/plain
.md
text/plain
.sh
text/plain
.py
text/plain
.js
text/plain
.css
text/plain
.html
text/plain
.htm
text/plain
.xml
text/plain
.json
text/plain
.yaml
text/plain
.yml
text/plain
Last updated