rust-kgdb 0.6.48 → 0.6.49

package/CHANGELOG.md

@@ -2,6 +2,35 @@
 
 All notable changes to the rust-kgdb TypeScript SDK will be documented in this file.
 
+## [0.6.49] - 2025-12-17
+
+### Core Concepts Section Added
+
+#### New "What We Bring and Why" Section
+Simple Problem → Solution format explaining our 5 core innovations:
+
+1. **Schema-Aware Query Generation**
+   - Problem: LLMs hallucinate predicates
+   - Solution: Auto-extract schema, inject into prompts
+
+2. **Built-in Database (Not BYODB)**
+   - Problem: Other frameworks generate queries but need external DB
+   - Solution: rust-kgdb IS the database
+
+3. **Audit Trail (Provenance)**
+   - Problem: Where did that answer come from?
+   - Solution: Full reasoning trace with every answer
+
+4. **Deterministic Execution**
+   - Problem: Same question → different answers
+   - Solution: Same hash for same input (compliance-ready)
+
+5. **ARCADE 1-Hop Cache**
+   - Problem: Slow embedding neighborhood lookups
+   - Solution: Pre-cached 1-hop neighbors for O(1) context
+
+---
+
 ## [0.6.48] - 2025-12-17
 
 ### Clearer Product Definition

package/README.md

@@ -25,6 +25,30 @@
 
 ---
 
+## Core Concepts: What We Bring and Why
+
+### 1. Schema-Aware Query Generation
+**Problem**: LLMs generate SPARQL with made-up predicates (`?person :fakeProperty ?value`).
+**Solution**: We auto-extract your schema and inject it into prompts. The LLM can ONLY reference predicates that actually exist in your data.
+
+### 2. Built-in Database (Not BYODB)
+**Problem**: LangChain/DSPy generate queries, but you need to find a database to run them.
+**Solution**: rust-kgdb IS the database. Generate query → Execute query → Return results. All in one package.
+
+### 3. Audit Trail (Provenance)
+**Problem**: LLM says "Provider P001 is suspicious" - where did that come from?
+**Solution**: Every answer includes a reasoning trace showing which SPARQL queries ran, which rules matched, and what data was found.
+
+### 4. Deterministic Execution
+**Problem**: Ask the same question twice, get different answers.
+**Solution**: Same input → Same query → Same database → Same result → Same hash. Reproducible for compliance.
+
+### 5. ARCADE 1-Hop Cache
+**Problem**: Embedding lookups are slow when you need neighborhood context.
+**Solution**: Pre-cache 1-hop neighbors. When you find "Provider", instantly know its outgoing predicates (hasRiskScore, hasClaim) without another query.
+
+---
+
 ## AI Answers You Can Trust
 
 **The Problem**: LLMs hallucinate. They make up facts, invent data, and confidently state falsehoods. In regulated industries (finance, healthcare, legal), this is not just annoying—it's a liability.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "rust-kgdb",
-  "version": "0.6.48",
+  "version": "0.6.49",
   "description": "High-performance RDF/SPARQL database with AI agent framework. GraphDB (449ns lookups, 35x faster than RDFox), GraphFrames analytics (PageRank, motifs), Datalog reasoning, HNSW vector embeddings. HyperMindAgent for schema-aware query generation with audit trails. W3C SPARQL 1.1 compliant. Native performance via Rust + NAPI-RS.",
   "main": "index.js",
   "types": "index.d.ts",