--- title: "A hosted pipeline, and what is next · QueryLlama" description: "How it runs as a service rather than a desktop app, what is running today, and what comes after." url: "https://royalsoftworks.com/products/queryllama/features/pipeline-and-roadmap/" source: "https://royalsoftworks.com" format: "markdown" note: "Markdown rendering of the HTML page at `url`. Same content, same canonical URL." --- Features · 3 of 3 # A hosted pipeline, and what is next. How it runs as a service rather than a desktop app, what is running today, and what comes after. Architecture ## A hosted pipeline, not a desktop app. A document you upload goes to object storage, gets picked up by an ingestion worker that splits it into overlapping chunks and embeds them, and lands in Postgres ready to be searched — by keyword, by meaning, or both. For your IT team - **Chunking** — Sliding window, ~2,048 characters per chunk with 400-character overlap - **Embeddings** — 768-dimension vectors via Cloudflare Workers AI (BGE base), stored in pgvector - **Keyword search** — Postgres full-text search over a generated tsvector column Built in the open ## What's running today, and what's next. QueryLlama is pre-launch. Rather than blur the line, every capability on this site is labeled by build status — so a design partner or security reviewer knows exactly what they're evaluating today. ### Multi-tenant isolation (Postgres RLS) Core tables scoped by organization at the database layer; per-role rules and full table coverage still being built. In active development ### Document ingestion: chunking + embeddings The worker chunks text on a sliding window, embeds it via Cloudflare Workers AI and stores it in pgvector — plain text today; upload, queueing and PDF/Office parsing still being built. In active development ### Keyword search (Postgres full-text) Full-text search over indexed document chunks. In active development ### Semantic + hybrid search (RRF) Vector similarity search and a reciprocal-rank-fusion blend of keyword and semantic results. In active development ### RAG question-answering with citations Ask a question, get an answer grounded in retrieved chunks with a link back to source. In active development ### Bring-your-own-LLM (enterprise) Point the answering step at your own OpenAI-compatible endpoint. In active development ### Audit-log event writes The append-only table exists; wiring every action through to it is in progress. In active development ### Group-level permissions & tier billing Finer-grained access rules within an org, and metered plan enforcement. Designed, on the roadmap [Previous Answers, your model, and five roles.](https://royalsoftworks.com/products/queryllama/features/answers-and-roles/) [All of QueryLlama features](https://royalsoftworks.com/products/queryllama/features/)