Source identity
Normalized objects retain checksums, citations, safety state, and corpus fingerprints through retrieval.
Project Brief
Content Intelligence
The repository normalizes synthetic text, transcript-derived, OCR-derived, and Markdown material into provenance-rich objects, gates retrieval inputs for safety, produces local lexical/vector records, and exposes portable hybrid retrieval logic used by a public cited-answer demo.
Live Demo
Open the standalone retrieval workspace
Open the standalone surface to see the published corpus status, ask a question, and inspect citations without scrolling through the project narrative.
Implemented Pipeline
From source adapters to RAG-ready evidence
The pipeline preserves source identity, checksums, citations, safety state, and corpus fingerprints through retrieval.
Privacy and answer-grounding gates block unreviewed inputs and require cited, bounded responses.
Inspect first
- Live cited retrieval over the reviewed release corpus
- Source adapter and information-object contracts
- Corpus fingerprint and public-safety review output
- Deterministic retrieval evaluations and sample report
Evidence
What the workflow proves
Conversion and normalization
Transcript and OCR-style examples become cleaned, citation-preserving corpus records after public-safety review.
Retrieval-ready index
Generated lexical and vector records support portable hybrid retrieval for a public cited-answer demo.
Evaluated boundary
Privacy and answer-grounding gates block unreviewed inputs and require cited, bounded responses.
Serving Layer
Hybrid retrieval with a safe fallback
The repository exposes portable hybrid retrieval logic over the same safety-reviewed records used by the public cited-answer demo.
Projects Qualification
Supporting project · prototype claims · qualified use
Strong general AI systems alternate with unusually clear provenance and governance evidence; less education-specific than the top three.
Safety Boundary
Source-grounded, source-limited
Public examples must use synthetic, sanitized, public-domain, or clearly licensed source material. Raw private artifacts, private source paths, credentials, course identifiers, and copyrighted lecture text stay outside the public repository and public RAG index.