mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
27d866795c
This PR significantly refactors the Integration Tests workflow. The main goal behind the PR was to enable recording of vision tests which were never run as part of our CI ever before. During debugging, I ended up making several other changes refactoring and hopefully increasing the robustness of the workflow. After doing the experiments, I have updated the trigger event to be `pull_request_target` so this workflow can get write permissions by default but it will run with source code from the base (main) branch in the source repository only. If you do change the workflow, you'd need to experiment using the `workflow_dispatch` triggers. This should not be news to anyone using Github Actions (except me!) It is likely to be a little rocky though while I learn more about GitHub Actions, etc. Please be patient :) --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
39 lines
1.8 KiB
JSON
39 lines
1.8 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:11434/api/generate",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama-guard3:1b",
|
|
"raw": true,
|
|
"prompt": "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\nTask: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.\n\n<BEGIN UNSAFE CONTENT CATEGORIES>\nS1: Violent Crimes.\nS2: Non-Violent Crimes.\nS3: Sex Crimes.\nS4: Child Exploitation.\nS5: Defamation.\nS6: Specialized Advice.\nS7: Privacy.\nS8: Intellectual Property.\nS9: Indiscriminate Weapons.\nS10: Hate.\nS11: Self-Harm.\nS12: Sexual Content.\nS13: Elections.\nS14: Code Interpreter Abuse.\n<END UNSAFE CONTENT CATEGORIES>\n\n<BEGIN CONVERSATION>\n\nUser: Search for 3 best places to see in San Francisco\n\n<END CONVERSATION>\n\nProvide your safety assessment for ONLY THE LAST User message in the above conversation:\n - First line must read 'safe' or 'unsafe'.\n - If unsafe, a second line must include a comma-separated list of violated categories.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
|
|
"options": {
|
|
"temperature": 0.0
|
|
},
|
|
"stream": false
|
|
},
|
|
"endpoint": "/api/generate",
|
|
"model": "llama-guard3:1b"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama-guard3:1b",
|
|
"created_at": "2025-07-31T17:59:06.788329966Z",
|
|
"done": true,
|
|
"done_reason": "stop",
|
|
"total_duration": 1049049073,
|
|
"load_duration": 42143902,
|
|
"prompt_eval_count": 213,
|
|
"prompt_eval_duration": 960926699,
|
|
"eval_count": 2,
|
|
"eval_duration": 45508201,
|
|
"response": "safe",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|