Azure Blob Storage

Connect an Azure Blob Storage container to Agent Context. Agent Context reads structured files from your container and makes them queryable with SQL. Each file becomes a table.

Setup

1. Go to Agent Context in the dashboard
2. Click Add Source → Azure Blob Storage
3. Enter your storage account, credentials, and the path to the file
4. Click Test Connection to verify, then Save

Connection Parameters

Parameter	Required	Description
Storage Account	Yes	Azure Storage account name
Access Key	No	Storage account access key (from Azure Portal → Storage account → Access keys)
SAS Token	No	Shared access signature scoped to the container
Custom Endpoint	No	Custom Azure Storage endpoint (for Azure Government, Azure China, or Azurite)
Path	Yes	Container and file path: container/path/to/file.csv
File Format	No	Auto-detected from extension. Override: csv, tsv, parquet, json, jsonl

Alternatively, you can paste a connection string with all parameters.

Provide either an Access Key or a SAS Token for authentication. For public containers, both can be omitted.

Supported File Formats

Format	Extension	Notes
Parquet	.parquet	Columnar format. Best performance for large datasets.
CSV	.csv	Auto-detects delimiter, headers, and column types.
TSV	.tsv	Tab-separated values.
JSON	.json	JSON array format.
JSONL	.jsonl	Newline-delimited JSON. One record per line.

Troubleshooting

Issue	Fix
Access denied	Verify the access key or SAS token has read access to the container.
No tables found	Check that the path points to a supported file format.
Container not found	Verify the storage account name and container name in the path.
Timeout	Check network connectivity. If using a custom endpoint, verify the URL.