Search Collection

from airweave import AirweaveSDK, SearchRequest
client = AirweaveSDK(
    api_key="YOUR_API_KEY",
)
client.collections.search(
    readable_id="customer-support-tickets-x7k9m",
    request=SearchRequest(
        query="How do I reset my password?",
    ),
)

{
  "results": [
    {
      "breadcrumbs": [
        "docs",
        "auth",
        "password-reset.md"
      ],
      "entity_id": "abc123-def456-789012",
      "md_content": "# Password Reset Guide\n\nTo reset your password...",
      "metadata": {
        "file_path": "docs/auth/password-reset.md",
        "last_modified": "2024-03-15T09:30:00Z"
      },
      "score": 0.92,
      "source_name": "GitHub",
      "url": "https://github.com/company/docs/blob/main/docs/auth/password-reset.md"
    },
    {
      "breadcrumbs": [
        "Engineering",
        "User Authentication"
      ],
      "entity_id": "xyz789-abc123-456789",
      "md_content": "## User Authentication\n\nPassword reset is available...",
      "metadata": {
        "page_id": "page-123",
        "workspace": "Engineering"
      },
      "score": 0.85,
      "source_name": "Notion",
      "url": "https://notion.so/page-123"
    }
  ],
  "completion": "To reset your password, navigate to the login page and click 'Forgot Password'. You'll receive an email with a reset link that expires in 24 hours. For security, ensure you're using a strong password with at least 12 characters."
}

Search your collection using semantic and hybrid search.

This is the primary search endpoint providing powerful AI-powered search capabilities:

Search Strategies:

hybrid (default): Combines neural (semantic) and keyword (BM25) matching
neural: Pure semantic search using embeddings
keyword: Traditional keyword-based BM25 search

Features:

Query expansion: Generate query variations to improve recall
Filter interpretation: Extract structured filters from natural language
Reranking: LLM-based reranking for improved relevance
Answer generation: AI-generated answers based on search results

Note: Accepts both new SearchRequest and legacy LegacySearchRequest formats for backwards compatibility.

Search your collection using semantic and hybrid search. This is the primary search endpoint providing powerful AI-powered search capabilities: **Search Strategies:** - **hybrid** (default): Combines neural (semantic) and keyword (BM25) matching - **neural**: Pure semantic search using embeddings - **keyword**: Traditional keyword-based BM25 search **Features:** - **Query expansion**: Generate query variations to improve recall - **Filter interpretation**: Extract structured filters from natural language - **Reranking**: LLM-based reranking for improved relevance - **Answer generation**: AI-generated answers based on search results **Note**: Accepts both new SearchRequest and legacy LegacySearchRequest formats for backwards compatibility.

Authentication

x-api-keystring

API Key authentication via header

Path parameters

readable_idstringRequired

The unique readable identifier of the collection to search

Request

This endpoint expects an object.

SearchRequestobjectRequired

LegacySearchRequestobjectRequired

Response

Search results with optional AI completion

resultslist of maps from strings to any

Array of search result objects containing the found documents, records, or data entities. Each result includes entity_id, source_name, md_content, metadata, score, breadcrumbs, and url.

completionstring or null

AI-generated natural language answer to your query based on the search results. Only included when generate_answer is true in the request.

Authentication

Path parameters

Request

Response

Errors