Run Multiple Queries

Audience: Developers

Run Multiple Queries with Async Taskgroup

Run multiple research queries with shared configuration (profile, webhook) using the SDK's taskgroup API.

Create a task group with multiple queries

from gl_odr_sdk import DeepResearchClient

client = DeepResearchClient()

taskgroup = client.taskgroups.create(
    profile="ESSENTIAL",
    query=[
        "What is AI?",
        "What is machine learning?",
        "What is deep learning?",
    ],
)
# All tasks share the same profile and optional webhook
print(f"Taskgroup ID: {taskgroup.taskgroup_id}")
print(f"Tasks: {taskgroup.tasks}")

Stream from the whole group

Consume a single stream that aggregates events from all tasks in the group:

for event in client.taskgroups.stream(taskgroup.taskgroup_id):
    print(f"{event.event_type}: {event.value}")

Check group status and get results

# Group status (SUCCESS, PARTIAL_FAILURE, etc.)
group = client.taskgroups.get(taskgroup.taskgroup_id)
print(f"Status: {group.status}")

# Result for a specific task in the group
task_result = client.taskgroups.get_task(
    taskgroup_id=taskgroup.taskgroup_id,
    task_id=taskgroup.tasks[0],
)
if task_result.data:
    print(task_result.data.result)

See the Quick Start Guide and Taskgroups API Contract for full request/response formats.