Tag: RAG

Showing 1-3 of 3

Apr 13, 20268 min readModel Release BriefIntermediate240 min build

Group-Chat AI with Witness-Based Memory to Reduce Accidental Privacy Leaks

Learn how to build a group-chat AI that 'reads the room' and stores facts only for users who witnessed them. Includes design, prototype steps, and privacy trade-offs.

group-chat privacy witness-memory memory tutorial

+3 more

TutorialsUnited Kingdom

Open

Mar 28, 20267 min readModel Release BriefIntermediate180 min build

LaunchStack (PDR AI): Self‑hostable startup accelerator for PRDs, onboarding, and marketing docs

Self-hostable LaunchStack (PDR AI) centralizes PRDs, onboarding, marketing and legal docs into a searchable, citeable workspace with role-based reviews and page-level retrieval.

open-source startup self-hosting RAG pgvector

+3 more

LangChain Next.js PostgreSQL

Model BreakdownsFrance

Open

Mar 12, 20266 min readTooling Deep DiveIntermediate

Isaacus’ Kanon 2: retrieval models, a hierarchical Enricher, and the semchunk chunker

Isaacus offers Kanon 2 Embedder and Reranker for legal retrieval, Kanon 2 Enricher to turn long documents into knowledge graphs, plus semchunk—vendor claims worth piloting.

legal-ai retrieval embeddings knowledge-graphs RAG

+3 more

semchunk open-source startup