User Question → Search your knowledge base → Feed relevant docs to LLM → Grounded Answer

┌─────────────────────────────────────────────────────────────┐
│                        USER INTERFACE                       │
│          (Web App / Slack Bot / Internal Portal)            │
└──────────────────────┬──────────────────────────────────────┘
                       ↓
┌─────────────────────────────────────────────────────────────┐
│                     API LAYER                               │
│              Cloud Run / Cloud Functions                    │
└──────┬───────────────┬──────────────────┬───────────────────┘
       ↓               ↓                  ↓
┌────────────┐  ┌─────────────┐  ┌──────────────────┐
│  Retrieval │  │  LLM Layer  │  │  Auth & Security  │
│   Engine   │  │  (Vertex AI)│  │  (IAM / IAP)      │
└────────────┘  └─────────────┘  └──────────────────┘
       ↓
┌─────────────────────────────────────────────────────────────┐
│                    VECTOR STORE                             │
│         Vertex AI Vector Search / AlloyDB / pgvector        │
└──────────────────────┬──────────────────────────────────────┘
                       ↓
┌─────────────────────────────────────────────────────────────┐
│                  KNOWLEDGE BASE (Raw Docs)                  │
│     GCS Buckets │ BigQuery │ Drive │ Confluence │ Jira      │
└─────────────────────────────────────────────────────────────┘

[ Raw Documents ]
GCS / Drive / Confluence / SharePoint
        ↓
[ Document AI ]         ← OCR, form parsing, table extraction
        ↓
[ Chunking & Cleaning ] ← Split into ~512 token chunks with overlap
        ↓
[ Vertex AI Embeddings ] ← text-embedding-005 → vector per chunk
        ↓
[ Vector Store ]
Vertex AI Vector Search (managed) or AlloyDB + pgvector (flexible)
        ↓
[ Metadata → BigQuery ] ← source, timestamp, doc_id, chunk_id

# Simplified RAG retrieval flow on GCP
def retrieve(query: str, top_k: int = 5):
    # 1. Embed the user query
    query_embedding = vertexai_embed(query)  # text-embedding-005
    # 2. Vector similarity search
    results = vector_search.find_neighbors(
        embedding=query_embedding,
        num_neighbors=top_k
    )
    # 3. Optional: Re-rank results
    reranked = rerank(query, results)  # Vertex AI Ranking API
    # 4. Fetch full chunk text from GCS / BigQuery
    chunks = fetch_chunks(reranked)
    return chunks

def generate_answer(query: str, chunks: list):
    context = "\n\n".join([c.text for c in chunks])
    prompt = f"""
    You are an internal AI assistant for Acme Corp.
    Answer ONLY based on the provided context.
    If the answer is not in the context, say "I don't have that information."
    Always cite the source document.
    CONTEXT:
    {context}
    QUESTION:
    {query}
    ANSWER:
    """
    response = gemini_pro.generate_content(prompt)
    return response.text

Cloud Run (containerized FastAPI)
  ├── POST /chat          → RAG query endpoint
  ├── POST /ingest        → Trigger document ingestion
  ├── GET  /sources       → List indexed documents
  └── GET  /health        → Health check

IAM Roles         → control who can call the RAG API
IAP               → protect the web UI (Google SSO)
Document-level ACL → filter retrieved chunks by user's permissions
VPC Service Controls → isolate all GCP services in a perimeter

Cloud Logging     → all query logs, errors
Cloud Monitoring  → latency, throughput, error rate dashboards
BigQuery          → store all Q&A pairs for analysis
Vertex AI Evals   → measure answer quality over time

Vertex AI Safety Filters → block harmful outputs
Grounding checks         → ensure answer comes from retrieved context
Confidence scoring       → flag low-confidence answers for human review
Citation enforcement     → always return source doc + page

┌─ INGESTION (Batch + Real-time) ──────────────────────────────┐
│  Cloud Composer (Airflow) → Document AI → Embeddings → VectorDB│
└──────────────────────────────────────────────────────────────┘
┌─ SERVING ────────────────────────────────────────────────────┐
│  Cloud Run (FastAPI RAG service)                              │
│  ├── Vertex AI Vector Search (retrieval)                      │
│  ├── Vertex AI Ranking API (re-rank)                          │
│  └── Gemini 1.5 Pro (generation)                              │
└──────────────────────────────────────────────────────────────┘
┌─ FRONTEND ───────────────────────────────────────────────────┐
│  Next.js on Cloud Run + IAP (Google SSO)                      │
│  or Slack / Google Chat Bot                                   │
└──────────────────────────────────────────────────────────────┘
┌─ OBSERVABILITY ──────────────────────────────────────────────┐
│  Cloud Logging → BigQuery → Looker Dashboard                  │
└──────────────────────────────────────────────────────────────┘