from azure.search.documents.indexes.models import (
    SearchIndex,
    KnowledgeBase,
    KnowledgeSource
)

# Create knowledge base
kb = KnowledgeBase(
    name="company-knowledge",
    description="Corporate documentation and policies",
    knowledge_sources=[
        KnowledgeSource(
            name="sharepoint-docs",
            type="sharepoint",
            connection_string="...",
            site_url="https://company.sharepoint.com"
        ),
        KnowledgeSource(
            name="azure-storage",
            type="azureblob",
            connection_string="...",
            container_name="documents"
        )
    ],
    reasoning_effort="medium",  # low, medium, high
    include_citations=True
)

kb_client.create_or_update(kb)

from azure.ai.projects import AIProjectClient

# Query knowledge base through agent
agent = project_client.agents.create(
    model="gpt-4",
    instructions="Answer questions using company knowledge.",
    tools=[{
        "type": "knowledge_base",
        "knowledge_base_id": kb.id
    }]
)

thread = project_client.agents.create_thread()
message = project_client.agents.create_message(
    thread.id,
    "user",
    "What is our return policy?"
)

run = project_client.agents.create_run(thread.id, agent.id)
response = project_client.agents.wait_for_run(thread.id, run.id)

# Response includes:
# - Grounded answer
# - Source citations
# - Activity log
# - Confidence scores

from azure.search.documents.indexes.models import (
    SearchIndexerSkillset,
    SplitSkill,
    AzureOpenAIEmbeddingSkill,
    EntityRecognitionSkill
)

skillset = SearchIndexerSkillset(
    name="document-enrichment",
    description="Extract and vectorize content",
    skills=[
        # Split text into chunks
        SplitSkill(
            context="/document",
            text_split_mode="pages",
            maximum_page_length=2000,
            page_overlap_length=500,
            inputs=[{"name": "text", "source": "/document/content"}],
            outputs=[{"name": "textItems", "target_name": "chunks"}]
        ),
        # Generate embeddings
        AzureOpenAIEmbeddingSkill(
            context="/document/chunks/*",
            resource_uri="https://your-openai.openai.azure.com",
            deployment_id="text-embedding-ada-002",
            inputs=[{"name": "text", "source": "/document/chunks/*"}],
            outputs=[{"name": "embedding", "target_name": "vector"}]
        ),
        # Extract entities
        EntityRecognitionSkill(
            context="/document",
            categories=["Person", "Organization", "Location"],
            inputs=[{"name": "text", "source": "/document/content"}],
            outputs=[{"name": "entities", "target_name": "entities"}]
        )
    ]
)

indexer_client.create_or_update_skillset(skillset)

# Configure vectorizer
from azure.search.documents.indexes.models import (
    AzureOpenAIVectorizer,
    VectorSearch,
    VectorSearchProfile
)

vectorizer = AzureOpenAIVectorizer(
    name="my-vectorizer",
    azure_open_ai_parameters={
        "resource_uri": "https://your-openai.openai.azure.com",
        "deployment_id": "text-embedding-ada-002",
        "api_key": "your-key"
    }
)

# Add to index
index = SearchIndex(
    name="auto-vectorized-index",
    fields=[
        SimpleField(name="id", type="Edm.String", key=True),
        SearchableField(name="content", type="Edm.String"),
        SearchField(
            name="content_vector",
            type="Collection(Edm.Single)",
            vector_search_dimensions=1536,
            vector_search_profile_name="my-profile"
        )
    ],
    vector_search=VectorSearch(
        profiles=[VectorSearchProfile(
            name="my-profile",
            vectorizer_name="my-vectorizer"
        )],
        vectorizers=[vectorizer]
    )
)

# Index documents with security fields
documents = [
    {
        "id": "doc1",
        "content": "Confidential information",
        "security_filter": ["group1", "user123"]
    }
]

search_client.upload_documents(documents)

# Query with security filter
user_groups = ["group1", "group2"]
filter_expression = " or ".join(
    [f"security_filter/any(g: g eq '{group}')" for group in user_groups]
)

results = search_client.search(
    search_text="confidential",
    filter=filter_expression
)

from azure.monitor.query import LogsQueryClient

logs_client = LogsQueryClient(credential)

# Query search logs
query = """
AzureDiagnostics
| where ResourceType == "SEARCHSERVICES"
| where OperationName == "Query.Search"
| summarize 
    QueryCount = count(),
    AvgDuration = avg(DurationMs),
    AvgResultCount = avg(ResultCount)
  by SearchText = Query_s
| order by QueryCount desc
| take 20
"""

response = logs_client.query_workspace(
    workspace_id="your-workspace-id",
    query=query,
    timespan=timedelta(days=7)
)