llama-stack-mirror/tests/integration/recordings/responses/9e7a83d3d596.json
Ashwin Bharambe 27d866795c
feat(ci): add support for running vision inference tests (#2972)
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>
2025-07-31 11:50:42 -07:00

42 lines
1.4 KiB
JSON

{
"request": {
"method": "POST",
"url": "http://0.0.0.0:11434/v1/v1/completions",
"headers": {},
"body": {
"model": "llama3.2:3b-instruct-fp16",
"prompt": "Respond to this question and explain your answer. Complete the sentence using one word: Roses are red, violets are ",
"stream": false
},
"endpoint": "/v1/completions",
"model": "llama3.2:3b-instruct-fp16"
},
"response": {
"body": {
"__type__": "openai.types.completion.Completion",
"__data__": {
"id": "cmpl-726",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"text": "Blue.\n\nExplanation: This is a play on words from the classic Valentine's Day poem \"Roses are red, violets are blue.\" The original poem typically ends with the line \"sent my love to you,\" but in this adaptation, I've altered it to rhyme by replacing \"blue\" with \"blue\" (a pun). However, it also makes a clever non-literary response."
}
],
"created": 1753984322,
"model": "llama3.2:3b-instruct-fp16",
"object": "text_completion",
"system_fingerprint": "fp_ollama",
"usage": {
"completion_tokens": 81,
"prompt_tokens": 50,
"total_tokens": 131,
"completion_tokens_details": null,
"prompt_tokens_details": null
}
}
},
"is_streaming": false
}
}