Team Paradox
Back to all systems
System Index · 03/Active/2024 — Present

ARIA

RAG assistant for PDF, YouTube and GitHub ingestion — embeddings, Chroma, semantic retrieval, memory and Groq/LangChain orchestration.

01 — System Overview & Primary Intent

ARIA is a specialized system engineered by Team Paradox in Gorakhpur, led by Om Abhishek Tripathi. Teams learn from scattered PDFs, videos and repos. Needed one memory-aware assistant grounded in their own sources.

02 — Architecture & Flow

01

Ingest pipeline: chunk → embed (HF) → Chroma

02

Query: embed → retrieval → Groq synthesis with citations

03

Memory store for follow-ups

04

Source-grounded answers, no invented URLs

03 — Engineering Decisions & Rationale

  • Chroma for local-first vector store
  • Groq for low-latency synthesis
  • Strict citation framing; fallback to 'not found in sources'

04 — Known Limitations & Failure Modes

Chunking heuristic for scanned PDFs is lossy
No fine-tuning — retrieval quality bounds answers
YouTube transcript dependent on captions

Observed Tech Stack

Next.jsFastAPILangChainGroqChromaHuggingFace

Engineering Governance

All systems undergo internal peer review with strict claims verification. We do not publish simulated benchmarks, fake testimonial quotes, or obfuscated AI wrappers without deterministic fallbacks.

Studio: Team Paradox · Gorakhpur, Uttar Pradesh, India
08Contact

Bring us a problem worth untangling.

A paragraph. Plain words.

No backend yet. Hitting send opens your mail client with a prefilled draft to hello@teamparadox.in — honest, no fake success state. If that fails, write to us directly.