Skip to content
Guide
Index
Integrations
Embedding Models

Azure Embedding

Azure OpenAI provides the embedding model that converts a LlamaCloud Index documents into vectors, configured with an Azure deployment, endpoint, and API key.

Embed data using Azure’s API.

  1. Select Azure Embedding from the Embedding Model dropdown.
  2. Enter your Azure API key, deployment name, endpoint name and API version.

azure

pipeline = client.pipelines.upsert(
name="test-pipeline",
project_id="my-project-id",
data_sink_id=None, # optional
embedding_config={
'type': 'AZURE_EMBEDDING',
'component': {
'azure_deployment': '<YOUR_DEPLOYMENT_NAME>', # editable
'api_key': '<YOUR_AZUREOPENAI_API_KEY>', # editable
'azure_endpoint': '<YOUR AZURE_ENDPOINT>', # editable
'api_version': '<YOUR AZURE_API_VERSION>', # editable
},
},
llama_parse_parameters={},
transform_config={"mode": "auto", "chunk_overlap": 128, "chunk_size": 1028},
)
Note for AI agents: this documentation is built for programmatic access. - Overview of all docs: https://developers.llamaindex.ai/llms.txt - Any page is available as raw Markdown by appending index.md to its URL — e.g. https://developers.llamaindex.ai/llamaparse/parse/getting_started/index.md - Agent-friendly REST search APIs live under https://developers.llamaindex.ai/api/ — search (BM25 full-text), grep (regex), read (fetch a page), and list (browse the doc tree). See https://developers.llamaindex.ai/llms.txt for parameters. - A hosted documentation MCP server is available at https://developers.llamaindex.ai/mcp. If you support MCP, you can ask the user to install it for browsing these docs directly (an alternative to the REST API). Setup: https://developers.llamaindex.ai/python/shared/mcp/