⚡Retriever StudioLoading…
⏱️7 Days Starter Trial➔ Upgrade
📁 Custom Dev Client Portal⚡ Retriever RAG Studio

📊 Overview & Usage Telemetry

Monitor active knowledge documents, financial token spend, semantic cache hit rates, and API performance.

Total Documents
0
No documents indexed yet
Monthly Token Quota
0 / 250k
starter Plan Tier
Semantic Cache Hit Rate
0%
⚡ Sub-50ms Latency Saved
Avg Query Latency
0 ms
Hybrid Rerank Active
⚡Core Subsystems & Latency
9/9 Engines Operational
ColBERT MaxSim RerankerRetrieval
~14ms
Sublinear BM25 Keyword SearchRetrieval
~3ms
pgvector HNSW Dense VectorsVector
~8ms
GraphRAG HDBSCAN TopicsGraph
~35ms
Docling Layout OCR ParserIngestion
v2.1
RLM Python REPL SandboxSandbox
~18ms
Telemetry Anomaly SentinelDefense
Nominal
Edge AI Token ShieldRate-Limit
Active
LlamaGuard 3 Safety RailsModeration
S1–S13

🚀 RAG Studio Onboarding Quickstart

💡 Model Token Financial Spend

Gemini 3.6 Flash (Default Inference)$0.000 (Included in Trial)
Llama 3.3 70B (Groq Fast Inference)$0.000 (Included in Trial)
GPT-4o (High-Precision Fallback)BYOK Key Required