Epictetus
5f917f4121
Publisher fixes: - Checkout new branch before push (was pushing main ref) - Verify files staged before commit - Handle duplicate files gracefully - Clean error reporting per stage Skills merged to main: - mcp-server-setup (from pipeshub-ai) - research-pipeline (from Blacknode) - multi-agent-sequential-workflow (from Fast-LLM-Agent-MCP) - unifai-workflow-execution (from UnifAI) - code-review-agent-workflow (from AgentKit)
2.6 KiB
2.6 KiB
name, version, description, inputs, steps, outputs, tags, metadata
| name | version | description | inputs | steps | outputs | tags | metadata | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| unifai-workflow-execution | 1.0.0 | Execute a multi-agent workflow on the UnifAI platform using a specified blueprint and user prompt. |
|
|
|
|
unifai-workflow-execution
Execute a multi-agent workflow on the UnifAI platform using a specified blueprint and user prompt.
Setup
Dependencies:
pip install requests urllib3
Setup steps:
- Install required dependencies using pip install requests urllib3
- Ensure the environment variables are set correctly (BLUEPRINT_ID, BLUEPRINT_NAME, USER_SHORTCUT, POLLING_INTERVAL, UNIFAI_BASE_URL)
Key Files
scripts/execution_workflow.py - Main script for workflow execution
Steps
- Step 1: Resolve the blueprint ID from either direct ID or name lookup (resolve_blueprint_id method)
- Step 2: Create a new session from the blueprint (create_session method)
- Step 3: Submit the session for background execution with the user prompt (submit_session method)
- Step 4: Poll session status until execution completes (poll_session_status method)
Implementation Details
resolve_blueprint_id(client: UnifAIClient) -> str
{...}
# Resolve the blueprint ID from either direct ID or name lookup.
create_session(client: UnifAIClient, blueprint_id: str) -> str
{...}
# Create a new session from the blueprint.
submit_session(client: UnifAIClient, session_id: str) -> dict
{...}
# Submit the session for background execution with the user prompt.
Inputs
- blueprint_id or blueprint_name
- user_shortcut
- user_question
Outputs
- session_id
- workflow_id
Failure Modes
- Blueprint name not found or not unique - error during blueprint resolution
- Session creation fails - error from API response
- Session submission fails - error from API response
- Polling session status fails - error from API response
Source
Extracted from: https://github.com/redhat-community-ai-tools/UnifAI.git Confidence: 0.95