البناء
A document assistant that cites its sources
Retrieval-augmented generation over internal documents, built around one rule: every answer must point to the paragraph it came from.
- الدور
- Product & engineering
- السنة
- 2024 — حتى الآن
- القطاع
- المؤسسات
- الحالة
- قيد التنفيذ
01التحدي
People spent hours searching policies and contracts. Generic chatbots answered confidently and wrongly.
02المقاربة
Chunking that respects document structure, hybrid search (full-text + vectors) in PostgreSQL, answers constrained to retrieved passages, and an evaluation set that runs on every change.
03المعمارية
Ingestion pipeline → PostgreSQL with pgvector → hybrid retriever → LLM with citation-enforcing prompt → evaluation harness.
Answering with evidence
Ingest
Parse
Chunk by structure
Embed
Retrieve
Full-text
Vector
Re-rank
Answer
LLM
Citations
Evaluation
النتيجة
Status and early results