Multi-Document RAG: A Folder of Unrelated PDFs Is One Long Document with a Nested Outline
The authors propose treating a folder of unrelated PDFs as a single long document with a nested outline for Retrieval-Augmented Generation. They generate one summary line per file and preserve each file’s own table of contents, creating retrieval routes that descend two levels into the document hierarchy. Because the PDFs lack shared fields, no conventional index can be built, so the approach relies on the nested outline to guide retrieval. This method enables RAG over heterogeneous document collections without requiring a unified schema, but it may increase retrieval latency due to the deeper routing structure.
⚡ Key Takeaways
- No shared fields across PDFs means an index cannot be constructed.
- A summary line is generated
Want the full story? Read the original article.
Read on Towards Data Science ↗