Semantic Search

Query documents using natural language.

Basic Search

curl -X POST https://api.gateflow.ai/v1/data/search \
  -H "Authorization: Bearer gw_prod_..." \
  -H "Content-Type: application/json" \
  -d '{
    "query": "What is the refund policy?",
    "collection": "policies",
    "limit": 10
  }'

Response:

{
  "results": [
    {
      "chunk_id": "chunk_123",
      "document_id": "doc_456",
      "content": "Refunds are available within 30 days of purchase...",
      "score": 0.92,
      "metadata": {
        "filename": "refund-policy.pdf",
        "page": 2
      }
    }
  ]
}

Filters

By Metadata

{
  "query": "refund policy",
  "filters": {
    "department": "legal",
    "year": {"$gte": 2023}
  }
}

By Classification

{
  "query": "employee benefits",
  "classification_max": "internal"
}

Hybrid Search

Combine semantic and keyword search:

{
  "query": "refund policy",
  "mode": "hybrid",
  "keyword_weight": 0.3,
  "semantic_weight": 0.7
}

Search with Rerank

{
  "query": "refund policy",
  "limit": 20,
  "rerank": {
    "enabled": true,
    "model": "rerank-english-v3.0",
    "top_k": 5
  }
}

Next Steps

• Rerank Integration - Improve results
• RAG Injection - Use with LLM