feat(azure-blob): simplify and fix authentication

Author: georgeh0

Cargo.lock

@@ -114,11 +114,13 @@ json5 = "0.4.1"
 aws-config = "1.6.2"
 aws-sdk-s3 = "1.85.0"
 aws-sdk-sqs = "1.67.0"
-azure_core = "0.21.0"
-azure_storage = "0.21.0"
-azure_storage_blobs = "0.21.0"
 time = { version = "0.3", features = ["macros", "serde"] }
 numpy = "0.25.0"
 infer = "0.19.0"
 serde_with = { version = "3.13.0", features = ["base64"] }
 google-cloud-aiplatform-v1 = "0.4.0"
+
+azure_core = "0.21.0"
+azure_storage = "0.21.0"
+azure_storage_blobs = "0.21.0"
+azure_identity = "0.21.0"

Cargo.toml

@@ -0,0 +1 @@
+.env

examples/azure_blob_embedding/.gitignore

@@ -31,21 +31,13 @@ def azure_blob_text_embedding_flow(
     container_name = os.environ["AZURE_BLOB_CONTAINER_NAME"]
     prefix = os.environ.get("AZURE_BLOB_PREFIX", None)
 
-    # Authentication options (in priority order)
-    connection_string = os.environ.get("AZURE_BLOB_CONNECTION_STRING", None)
-    account_key = os.environ.get("AZURE_BLOB_ACCOUNT_KEY", None)
-    sas_token = os.environ.get("AZURE_BLOB_SAS_TOKEN", None)
-
     data_scope["documents"] = flow_builder.add_source(
         cocoindex.sources.AzureBlob(
             account_name=account_name,
             container_name=container_name,
             prefix=prefix,
             included_patterns=["*.md", "*.mdx", "*.txt", "*.docx"],
             binary=False,
-            connection_string=connection_string,
-            account_key=account_key,
-            sas_token=sas_token,
         )
     )
 

examples/azure_blob_embedding/main.py

@@ -46,13 +46,8 @@ class AmazonS3(op.SourceSpec):
 
 
 class AzureBlob(op.SourceSpec):
-    """Import data from an Azure Blob Storage container. Supports optional prefix and file filtering by glob patterns.
-
-    Authentication options (in priority order):
-    1. connection_string - Full connection string with credentials
-    2. sas_token - Shared Access Signature token
-    3. account_key - Storage account access key
-    4. None - Anonymous access (for public containers)
+    """
+    Import data from an Azure Blob Storage container. Supports optional prefix and file filtering by glob patterns.
     """
 
     _op_category = op.OpCategory.SOURCE
@@ -63,6 +58,3 @@ class AzureBlob(op.SourceSpec):
     binary: bool = False
     included_patterns: list[str] | None = None
     excluded_patterns: list[str] | None = None
-    account_key: str | None = None
-    sas_token: str | None = None
-    connection_string: str | None = None