AI Internal Knowledge Search - Company Brain Platform

@pytest.mark.asyncio
async def test_rag_search_accuracy():
    """Test RAG pipeline returns accurate, sourced answers."""
    query = "What is our company's remote work policy?"

    response = await client.post(
        "/api/v1/knowledge/search",
        json={"query": query, "sources": ["notion", "docs", "email"]},
        headers={"Authorization": f"Bearer {API_TOKEN}"}
    )

    assert response.status_code == 200
    result = response.json()

    # Validate answer structure
    assert "answer" in result
    assert "sources" in result
    assert len(result["sources"]) > 0

    # Validate source citations
    for source in result["sources"]:
        assert "document_id" in source
        assert "title" in source
        assert "relevance_score" in source
        assert source["relevance_score"] >= 0.7

    # Validate response time
    assert response.elapsed.total_seconds() < 2.0

@pytest.mark.asyncio
async def test_document_ingestion_pipeline():
    """Test document ingestion from multiple sources."""
    # Trigger sync for Notion workspace
    sync_response = await client.post(
        "/api/v1/connectors/notion/sync",
        json={"workspace_id": TEST_WORKSPACE_ID},
        headers={"Authorization": f"Bearer {API_TOKEN}"}
    )

    assert sync_response.status_code == 202
    job_id = sync_response.json()["job_id"]

    # Poll for completion
    status = await wait_for_job_completion(job_id, timeout=300)
    assert status["state"] == "completed"

    # Verify documents indexed
    stats = await client.get(f"/api/v1/index/stats")
    assert stats.json()["total_documents"] > 0
    assert stats.json()["vector_count"] > 0

    # Verify search works on new documents
    search_result = await client.post(
        "/api/v1/knowledge/search",
        json={"query": "newly indexed content test"}
    )
    assert search_result.status_code == 200