Your Documents (PDFs, Docs, Sheets)
              ↓
   Google Cloud Storage (GCS)
              ↓
   Document AI / Dataflow (chunk + clean)
              ↓
   Vertex AI Embeddings (text → vector)
              ↓
   Vertex AI Search / pgvector (store vectors)
              ↓
         n8n Workflow
              ↓
   User gets grounded answer + sources

# Create a bucket
gsutil mb gs://my-company-docs
# Upload documents
gsutil cp *.pdf gs://my-company-docs/raw/

gs://my-company-docs/
  ├── raw/              ← original documents
  ├── processed/        ← cleaned text chunks
  └── embeddings/       ← vector JSON files

# Cloud Function or Dataflow job
from google.cloud import documentai, storage
def chunk_document(text, chunk_size=500, overlap=50):
    words = text.split()
    chunks = []
    for i in range(0, len(words), chunk_size - overlap):
        chunk = " ".join(words[i:i + chunk_size])
        chunks.append({
            "chunk_id": f"chunk_{i}",
            "text": chunk,
            "source": "refund_policy.pdf",
            "page": i // chunk_size + 1
        })
    return chunks

{
  "chunk_id": "refund_policy_001",
  "text": "Refunds are available within 30 days of purchase...",
  "source": "refund_policy.pdf",
  "page": 1,
  "metadata": {
    "department": "finance",
    "last_updated": "2026-01-15"
  }
}

# REST API call
POST https://us-central1-aiplatform.googleapis.com/v1/projects/YOUR_PROJECT/
     locations/us-central1/publishers/google/models/text-embedding-004:predict
Headers:
  Authorization: Bearer $(gcloud auth print-access-token)
  Content-Type: application/json
Body:
{
  "instances": [
    { "content": "Refunds are available within 30 days of purchase..." }
  ]
}

{
  "predictions": [
    {
      "embeddings": {
        "values": [0.023, -0.841, 0.334, ...],
        "statistics": { "truncated": false, "token_count": 42 }
      }
    }
  ]
}

# Create a data store
gcloud alpha discovery-engine data-stores create \
  --project=YOUR_PROJECT \
  --location=global \
  --display-name="company-docs" \
  --industry-vertical=GENERIC \
  --solution-types=SOLUTION_TYPE_SEARCH

-- Enable pgvector extension
CREATE EXTENSION vector;
-- Create table with vector field
CREATE TABLE document_chunks (
  chunk_id     TEXT PRIMARY KEY,
  text         TEXT,
  source       TEXT,
  page         INT,
  metadata     JSONB,
  embedding    VECTOR(768)    -- matches Vertex AI output dimensions
);
-- Create HNSW index for fast similarity search
CREATE INDEX ON document_chunks
USING hnsw (embedding vector_cosine_ops)
WITH (m = 16, ef_construction = 64);

INSERT INTO document_chunks
  (chunk_id, text, source, embedding)
VALUES (
  'refund_policy_001',
  'Refunds are available within 30 days...',
  'refund_policy.pdf',
  '[0.023, -0.841, 0.334, ...]'::vector
);

Webhook Trigger
      ↓
HTTP Request → Vertex AI Embeddings
      ↓
HTTP Request → pgvector / Vertex AI Search
      ↓
Code Node → Format retrieved context
      ↓
HTTP Request → Vertex AI Gemini (chat)
      ↓
Respond to Webhook

{
  "question": "What is the refund policy?",
  "user_id": "user_123"
}

Method:  POST
URL:     https://us-central1-aiplatform.googleapis.com/v1/projects/
         {{ $env.GCP_PROJECT }}/locations/us-central1/publishers/google/
         models/text-embedding-004:predict
Headers:
  Authorization: Bearer {{ $env.GCP_ACCESS_TOKEN }}
  Content-Type:  application/json
Body:
{
  "instances": [
    { "content": "{{ $json.question }}" }
  ]
}

{ "query_vector": [0.021, -0.834, 0.291, ...] }

-- n8n Code Node generates this query
SELECT
  chunk_id,
  text,
  source,
  page,
  1 - (embedding <=> '[0.021, -0.834, 0.291, ...]'::vector) AS similarity
FROM document_chunks
ORDER BY embedding <=> '[0.021, -0.834, 0.291, ...]'::vector
LIMIT 5;

[
  { "chunk_id": "refund_policy_001", "text": "Refunds are available within 30 days...", "source": "refund_policy.pdf", "similarity": 0.97 },
  { "chunk_id": "returns_guide_003", "text": "To initiate a return, visit our portal...", "source": "returns_guide.pdf", "similarity": 0.81 }
]

// n8n Code Node
const results = items[0].json.results;
const question = $node["Webhook Trigger"].json.question;
const context = results
  .map(r => `Source: ${r.source} (Page ${r.page})\nContent: ${r.text}`)
  .join("\n\n---\n\n");
return [{
  json: {
    question: question,
    context: context,
    sources: results.map(r => r.source)
  }
}];

Method: POST
URL:    https://us-central1-aiplatform.googleapis.com/v1/projects/
        {{ $env.GCP_PROJECT }}/locations/us-central1/publishers/google/
        models/gemini-1.5-pro:generateContent
Body:
{
  "contents": [{
    "role": "user",
    "parts": [{
      "text": "You are an internal company assistant.\nAnswer ONLY using the context below.\nIf the answer is not in the context, say: I don't know.\nAlways cite the source document.\n\nContext:\n{{ $json.context }}\n\nQuestion: {{ $json.question }}"
    }]
  }],
  "generationConfig": {
    "temperature": 0.2,
    "maxOutputTokens": 512
  }
}

{
  "answer": "Refunds are available within 30 days of purchase. To initiate a return, visit our returns portal.",
  "sources": ["refund_policy.pdf", "returns_guide.pdf"],
  "confidence": "high"
}

┌─────────────────────────────────────────────────────────┐
│                    n8n WORKFLOW                         │
│                                                         │
│  [Webhook]──→[Vertex AI Embed]──→[pgvector Search]     │
│                                         ↓               │
│                                  [Code: Format]         │
│                                         ↓               │
│                                  [Gemini Chat]          │
│                                         ↓               │
│                                  [Respond]              │
└─────────────────────────────────────────────────────────┘

n8n running on GCP VM / Cloud Run
         ↓
Uses Workload Identity (no hardcoded keys)
         ↓
Accesses GCS, Vertex AI, AlloyDB
via IAM roles:
  - roles/aiplatform.user
  - roles/storage.objectViewer
  - roles/cloudsql.client

# Store API credentials securely
gcloud secrets create vertex-ai-key --data-file=key.json
# n8n fetches at runtime via HTTP Request node
GET https://secretmanager.googleapis.com/v1/projects/YOUR_PROJECT/
    secrets/vertex-ai-key/versions/latest:access