Azure Blob Storage Data Source

Guide

Index

Integrations

Data Sources

Guide to configuring Azure Blob Storage as a data source in LlamaCloud, including UI, API, and client setup for multiple authentication methods.

Load data from Azure Blob Storage.

Configure via UI

We can load data by using two different types of authentication methods:

1. Account Key Authentication Mechanism

azure_blob

2. Service Principal Authentication Mechanism

azure_blob

3. SAS URL Authentication Mechanism

azure_blob

Configure via API / Client

1. Account Key Authentication Mechanism

from llama_cloud.types.data_source_create_params import (
  CloudAzStorageBlobDataSource,
)

data_source = client.data_sources.create(
    name="my-data-source",
    component=CloudAzStorageBlobDataSource(
        container_name='<container_name>',
        account_url='<account_url>',
        blob='<blob>',  # optional
        prefix='<prefix>',  # optional
        account_name='<account_name>',
        account_key='<account_key>',
    ),
    source_type="AZURE_STORAGE_BLOB",
    project_id="my-project-id",
)

const dataSource = await client.dataSources.create({
  name: 'my-data-source',
  component: {
    container_name: '<container_name>',
    account_url: '<account_url>',
    blob: '<blob>',  // optional
    prefix: '<prefix>',  // optional
    account_name: '<account_name>',
    account_key: '<account_key>',
  },
  source_type: 'AZURE_STORAGE_BLOB',
  project_id: 'my-project-id',
});

from llama_cloud.types import CloudAzStorageBlobDataSource

ds = {
    'name': '<your-name>',
    'source_type': 'AZURE_STORAGE_BLOB',
    'component': CloudAzStorageBlobDataSource(
        container_name='<container_name>',
        account_url='<account_url>',
        blob='<blob>',  # optional
        prefix='<prefix>',  # optional
        account_name='<account_name>',
        account_key='<account_key>',
    )
}
data_source = client.data_sources.create_data_source(request=ds)

const ds = {
    'name': '<your-name>',
    'sourceType': 'AZURE_STORAGE_BLOB',
    'component': {
        'container_name': '<container_name>',
        'account_url': '<account_url>',
        'blob': '<blob>',  // optional
        'prefix': '<prefix>',  // optional
        'account_name': '<account_name>',
        'account_key': '<account_key>',
    }
}

data_source = await client.dataSources.createDataSource({
  body: ds
})

2. Service Principal Authentication Mechanism

from llama_cloud.types.data_source_create_params import (
  CloudAzStorageBlobDataSource,
)

data_source = client.data_sources.create(
    name="my-data-source",
    component=CloudAzStorageBlobDataSource(
        container_name='<container_name>',
        account_url='<account_url>',
        blob='<blob>',  # optional
        prefix='<prefix>',  # optional
        client_id='<client_id>',
        client_secret='<client_secret>',
        tenant_id='<tenant_id>',
    ),
    source_type="AZURE_STORAGE_BLOB",
    project_id="my-project-id",
)

const dataSource = await client.dataSources.create({
  name: 'my-data-source',
  component: {
    container_name: '<container_name>',
    account_url: '<account_url>',
    blob: '<blob>',  // optional
    prefix: '<prefix>',  // optional
    client_id: '<client_id>',
    client_secret: '<client_secret>',
    tenant_id: '<tenant_id>',
  },
  source_type: 'AZURE_STORAGE_BLOB',
  project_id: 'my-project-id',
});

from llama_cloud.types import CloudAzStorageBlobDataSource

ds = {
    'name': '<your-name>',
    'source_type': 'AZURE_STORAGE_BLOB',
    'component': CloudAzStorageBlobDataSource(
        container_name='<container_name>',
        account_url='<account_url>',
        blob='<blob>',  # optional
        prefix='<prefix>',  # optional
        client_id='<client_id>',
        client_secret='<client_secret>',
        tenant_id='<tenant_id>',
    )
}
data_source = client.data_sources.create_data_source(request=ds)

const ds = {
    'name': '<your-name>',
    'sourceType': 'AZURE_STORAGE_BLOB',
    'component': {
        'container_name'='<container_name>',
        'account_url'='<account_url>',
        'blob'='<blob>',  // optional
        'prefix'='<prefix>',  // optional
        'client_id'='<client_id>',
        'client_secret'='<client_secret>',
        'tenant_id'='<tenant_id>',
    }
}

data_source = await client.dataSources.createDataSource({
  body: ds
})

3. SAS URL Authentication Mechanism

from llama_cloud.types.data_source_create_params import (
  CloudAzStorageBlobDataSource,
)
data_source = client.data_sources.create(
    name="my-data-source",
    component=CloudAzStorageBlobDataSource(
        container_name='<container_name>',
        account_url='<account_url>/?<SAS_TOKEN>',
        blob='<blob>',  # optional
        prefix='<prefix>',  # optional
    ),
    source_type="AZURE_STORAGE_BLOB",
    project_id="my-project-id",
)

const dataSource = await client.dataSources.create({
  name: 'my-data-source',
  component: {
    container_name: '<container_name>',
    account_url: '<account_url>/?<SAS_TOKEN>',
    blob: '<blob>',  // optional
    prefix: '<prefix>',  // optional
  },
  source_type: 'AZURE_STORAGE_BLOB',
  project_id: 'my-project-id',
});

from llama_cloud.types import CloudAzStorageBlobDataSource

ds = {
    'name': '<your-name>',
    'source_type': 'AZURE_STORAGE_BLOB',
    'component': CloudAzStorageBlobDataSource(
        container_name='<container_name>',
        account_url='<account_url>/?<SAS_TOKEN>',
        blob='<blob>',  # optional
        prefix='<prefix>',  # optional
    )
}
data_source = client.data_sources.create_data_source(request=ds)

const ds = {
    'name': '<your-name>',
    'sourceType': 'AZURE_STORAGE_BLOB',
    'component': {
        'container_name': '<container_name>',
        'account_url': '<account_url>/?<SAS_TOKEN>',
        'blob': '<blob>',  // optional
        'prefix': '<prefix>',  // optional
    }
}

data_source = await client.dataSources.createDataSource({
  body: ds
})

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/