Hamza/sovereign_ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Validate local OCR retrieval for scanned PDFs

Browse Source
This commit is contained in:
Hamza Ayed
2026-10-03 19:29:39 +03:00
parent 332f43aaf0
commit 0587347157
5 changed files with 326 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
SovereignAI-Starter/evals/knowledge_retrieval_extended.jsonl
+1
View File
@@ -11,3 +11,4 @@
{"id": "skill-permissions-en", "query": "How does the server restrict tools for a selected skill?", "document": "skills.md", "expected_evidence": "allowed_tools", "text": "Each local agent skill declares an allowed_tools set. The server filters the advertised tools and rejects any model call outside that set."}
{"id": "long-guide-deep-approval-en", "query": "What must happen before a proposed production change can be saved?", "document": "long_technical_guide.md", "expected_evidence": "two-stage approval", "source_path": "evals/fixtures/long_technical_guide.md"}
{"id": "pdf-archive-page-limit-en", "query": "What is the maximum number of pages accepted when indexing one PDF?", "document": "archive_retention_policy.pdf", "expected_evidence": "30 pages", "source_path": "evals/fixtures/archive_retention_policy.pdf"}
{"id": "scanned-pdf-ocr-deadline-en", "query": "What calendar date ends the archive restoration approval window?", "document": "scanned_approval_notice.pdf", "expected_evidence": "17 October 2026", "source_path": "evals/fixtures/scanned_approval_notice.pdf"}