- System
- Pipelines & Workflows
- Codebase Maps
- System Overview
- Celery Queues
The full stack in one diagram: SvelteKit SPA, Nginx, FastAPI backend, Celery workers, Postgres, OpenSearch, MinIO, and the LLM provider. Start here.
The 8 real queues behind "Celery Workers": gpu, cpu, nlp, embedding, redaction, utility, download, and the dynamic cloud-asr/cpu-transcribe queues, with what runs on each and why.
- Transcription Pipeline
- Post-Transcription Enrichment
- Cloud ASR + Voiceprinting
- Speaker Clustering & Naming
- Search & Indexing
- RAG / Chat Retrieval
Upload through GPU-queue ASR/diarization to post-processing, indexing, and delivery.
What happens after a transcript is finalized: voiceprinting, gender/age detection, LLM speaker-ID suggestions, summarization, topic extraction, and analytics.
How the 8 supported cloud ASR providers plug into one factory, and how voiceprinting still happens when a provider supplies no native embeddings.
From a raw voiceprint to automatic profile matching, cross-file clustering, and human-reviewed promotion to a named speaker.
The query path (BM25 + kNN fused via RRF, then quarantine/redaction filtering) and the write path (chunking + embedding) in one diagram.
Query → scope/plan → retrieval → the local-vs-remote redaction guard → LLM → output redaction → streamed answer with citations.
- Backend Module Map
- Frontend Module Map
How backend/app/{api,auth,schemas,services,tasks,models,db,core,utils} actually relate: one services/ layer called by both the API and Celery.
How the SvelteKit frontend's routes/, components/, stores/, and lib/ fit together, including the community/cloud seam.