Overview
Interactions let you chain context between API calls. Each response includes an interaction_id, which you can pass as previous_interaction_id in a subsequent request to carry forward the context from the previous call. This enables multi-turn research workflows like follow-up questions, iterative refinement, and conversational agents.
Interactions work across both the Task API and Chat API.
How It Works
- Make an initial request — the response includes an
interaction_id
- Pass it forward — include that value as
previous_interaction_id in your next request
- Continue the chain — each new response returns its own
interaction_id, so you can keep building on prior context
Request and Response Fields
| Field | Location | Description |
|---|
previous_interaction_id | Request (optional) | Interaction ID from a prior call to use as context |
interaction_id | Response | Identifier for this interaction — pass as previous_interaction_id in follow-ups |
BetaTaskRunInput) and Chat API (ChatCompletionRequest) requests, and their corresponding responses.
Task API Usage
from parallel import Parallel
from parallel.types import TaskSpecParam, TextSchemaParam
client = Parallel()
# Initial request
task_run = client.task_run.create(
input="What are the main pricing models used by SaaS companies?",
processor="core",
task_spec=TaskSpecParam(output_schema=TextSchemaParam()),
)
result = client.task_run.result(task_run.run_id, api_timeout=3600)
# Follow-up using the interaction ID
followup = client.task_run.create(
input="Which of these works best for enterprise customers?",
processor="core",
previous_interaction_id=task_run.interaction_id,
task_spec=TaskSpecParam(output_schema=TextSchemaParam()),
)
followup_result = client.task_run.result(followup.run_id, api_timeout=3600)
Cross-Processor Interactions
You can chain interactions across different processors of the Task API.
Interactions are not available for Zero Data Retention (ZDR) customers.
Next Steps
