Atlas Metis: RAG Engine
Platform Status Brief
March 11, 2026
Confidential
01 — Overview
Platform Status

The Atlas Metis RAG Engine is a multi-tenant RAG-as-a-Service platform with a three-tier dashboard architecture (Master Admin, Org Admin, End User Portal), multi-provider embedding support (OpenAI + Gemini), and multimodal ingestion. The core product — document ingestion, hybrid search, AI-powered answers, cost tracking, cross-tenant analytics, and real-time health monitoring — is fully operational. The platform now serves three distinct user tiers with purpose-built interfaces. Remaining work focuses on OAuth token refresh, connector expansion, and deployment hardening.

55
API Routes
44
Python Modules
7
Health Checks / Tenant
E2E
Pipeline Verified

System Status

02 — Operations
How a Client Gets Onboarded
Current onboarding time: < 5 minutes from tenant creation to first query.
03 — Current State
Operational Systems
Single File Ingestion
Upload PDF, DOCX, TXT, CSV, audio, images (with Gemini) — auto-process to searchable vectors
Hybrid Search
Semantic + keyword search combined via Reciprocal Rank Fusion
Cohere Reranking
Cross-encoder reranking boosts raw scores from ~0.016 to ~0.97
LLM Generation
GPT-4o-mini generates grounded answers with source citations
Self-RAG Validation
Validates chunk relevance before generating — catches hallucinations
SSE Streaming
Real-time streaming responses via Server-Sent Events
Multi-Tenant Isolation
Verified — Tenant A cannot see Tenant B’s data
Dual API Key Auth
Tenant keys (scoped) + Admin keys (full access) with bcrypt
Job Tracking
Every ingestion tracked with status, timing, and error capture
Health Diagnostics
7 automated checks per tenant with alert creation and resolution
Admin Dashboard
Fleet overview, alert center, metrics bar, diagnostics trigger
Usage Tracking
Queries, tokens, rerank units tracked per tenant per period
Cost Tracking
Real pricing from OpenAI ($0.13/1M), Cohere, and Gemini ($0.15/1M tokens)
Rate Limiting
Sliding window rate limiter enforced per API key
File Size Limits
100MB upload cap prevents memory exhaustion on large files
Gemini Embeddings
Multimodal: images, video, audio natively embedded via Gemini Embeddings 2
04 — Issues
Issues by Priority
P1 Major Gaps
FeatureIssue
OAuth Refresh Google Drive/Dropbox tokens expire after ~1 hour with no refresh
P2 Pre-Production
FeatureIssue
HyDE Fallback Advertised but not implemented
Connector Types 8 of 11 declared types not implemented (only Drive, Dropbox, Webhook)
Eval RPC Mismatch Eval worker uses match_chunks RPC vs retrieval’s hybrid_search
Docker/Railway Deploy Config exists but not tested
Smoke Test Suite tests/ directory empty — no automated test coverage
All P0s resolved. URL ingestion, batch upload, and connector sync pipelines are fully wired and operational. Six of seven original P1s have been fixed (cost tracking, collection counters, Celery fallbacks, concept clustering, auth performance, query cache).
05 — Product Architecture
Three-Tier Dashboard Architecture

Atlas Metis serves three distinct user tiers, each with a purpose-built interface, authentication model, and API layer.

Access Levels

LayerAccessAuthURL Pattern
Master Admin Atlas Minds team Admin API key /admin
Org Admin Client admins Supabase Auth /dashboard
End User Anyone with link None (public) /portal/{org-slug}
Master Admin (Atlas Minds)
Fleet Health
Cross-Tenant Analytics
Revenue & Cost Tracking
Org Comparison
Diagnostics & Alerts
Org Admin (Client)
Document Management
Collection Management
Query Playground
Usage & Billing
Settings & API Keys
End User Portal
Chat Interface
Streaming Responses
Source Citations
Per-Org Branding
No Login Required

Data Flow by Tier

Public
End User
Portal API
Public
No auth required
Backend
Supabase
Authenticated
Org Admin
Customer API
Auth’d
Supabase Auth
Backend
Supabase
Admin
Master Admin
Admin API
Admin Key
Full access
Backend
Supabase
06 — Infrastructure
Technical Architecture
External
Client App
Gateway
FastAPI
55 routes • async
Security
Auth Layer
Dual key • bcrypt
Ingestion Pipeline
Parse → Chunk → Embed → Store
Retrieval Pipeline
Search → Rerank → Validate → Generate
Diagnostics
7 Health Checks → Alerts → Auto-Resolve
Database
Supabase
pgvector • RLS
Embeddings + LLM
OpenAI + Gemini
Multi-provider • 3072d • Multimodal
Reranking
Cohere
Rerank v3.5
Task Queue
Redis / Celery
Not running
07 — Roadmap
Path to Production
A
Fix P0s — Critical Dead Code
✓ Completed 2026-03-05
  • URL ingestion, batch upload, connector sync — all wired
  • Celery sync fallbacks added for all dependent endpoints
B
Fix P1s + Multi-Provider Embeddings
✓ Completed 2026-03-11
  • Cost tracking, collection counters, concept clustering, auth caching, query cache
  • Multi-provider embeddings (OpenAI + Gemini) with multimodal support
  • Rate limiting, file size limits, faithfulness checks, auto-slug
C
Three-Tier Dashboard + Analytics
✓ Completed 2026-03-11
  • End User Portal — public chat interface per organization with streaming and citations
  • Master Admin analytics — cross-tenant usage, cost trends, org comparison
  • Org Admin dashboard — document/collection management, query playground, billing
D
Remaining Work
Estimated: 3–5 days
  • OAuth token refresh for Google Drive / Dropbox connectors (P1)
  • Implement HyDE (Hypothetical Document Embeddings) fallback
  • Build remaining 8 connector types (SharePoint, S3, Notion, etc.)
  • Fix eval RPC mismatch (match_chunks vs hybrid_search)
  • Docker Compose + Railway deployment — test and validate
  • End-to-end smoke test suite
Total estimated time to production-ready: 3–5 days
Built by Atlas Minds
atlas-minds.com
March 11, 2026