block / block/frfr

Extract document references for automated discovery

Open
#6 0 comments 0 reactions 1 assignee Claimed by @cameronhotchkies View on GitHub
Dominant language
Go
Stars
20
Forks
4
PR merge metrics
No merged PRs in 30d

Description

## Problem
Documents often reference other standards, frameworks, and related docs in bibliographies, "further reading" sections, and inline hyperlinks. We currently don't capture these, missing an opportunity for automated document discovery.

## Proposal
Extract bibliography entries, citations, and hyperlinked documents as `external_reference` facts to enable a "retrieve next level" workflow: upload one document, discover 6 more to fetch.

## Implementation
1. Add `external_reference` fact type to identify citations, bibliography entries, and hyperlinks to external documents
2. Update extraction prompt to classify external document references
3. Build workflow to present extracted references as retrievable documents
4. Add UI for "fetch referenced documents" action
5. Consider pattern matching for common citation formats (ISO standards, NIST, RFCs, etc.) and URL patterns

## Expected Outcome
User uploads SOC 2 report that references ISO 27001, NIST CSF, links to 4 policy documents → system presents list of 6 documents to retrieve → user clicks "fetch all" → knowledge base grows automatically.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.