llama-stack-mirror/tests/integration/recordings/responses/e08e01e5652a.json
Matthew Farrellee f4ab154ade
Some checks failed
Vector IO Integration Tests / test-matrix (push) Failing after 4s
Update ReadTheDocs / update-readthedocs (push) Failing after 3s
UI Tests / ui-tests (22) (push) Successful in 43s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 3s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
API Conformance Tests / check-schema-compatibility (push) Successful in 7s
Unit Tests / unit-tests (3.13) (push) Failing after 4s
Pre-commit / pre-commit (push) Successful in 1m21s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Python Package Build Test / build (3.12) (push) Failing after 2s
Python Package Build Test / build (3.13) (push) Failing after 2s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 5s
Unit Tests / unit-tests (3.12) (push) Failing after 3s
Test External API and Providers / test-external (venv) (push) Failing after 5s
feat: add dynamic model registration support to TGI inference (#3417)
# What does this PR do?

adds dynamic model support to TGI

add new overwrite_completion_id feature to OpenAIMixin to deal with TGI
always returning id=""

## Test Plan

tgi: `docker run --gpus all --shm-size 1g -p 8080:80 -v /data:/data
ghcr.io/huggingface/text-generation-inference --model-id
Qwen/Qwen3-0.6B`

stack: `TGI_URL=http://localhost:8080 uv run llama stack build
--image-type venv --distro ci-tests --run`

test: `./scripts/integration-tests.sh --stack-config
http://localhost:8321 --setup tgi --subdirs inference --pattern openai`
2025-09-15 15:52:40 -04:00

56 lines
2.8 KiB
JSON

{
"request": {
"method": "POST",
"url": "http://localhost:8080/v1/v1/chat/completions",
"headers": {},
"body": {
"model": "Qwen/Qwen3-0.6B",
"messages": [
{
"role": "user",
"content": "Which planet do humans live on?"
}
],
"stream": false
},
"endpoint": "/v1/chat/completions",
"model": "Qwen/Qwen3-0.6B"
},
"response": {
"body": {
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
"__data__": {
"id": "",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"message": {
"content": "<think>\nOkay, the user is asking which planet humans live on. I need to make sure I answer this accurately. First, I should recall what I know about our solar system. The Earth is our home, and it's in our solar system. There are eight planets in total, right? Let me check that. Mercury, Venus, Earth, Mars, Jupiter, Saturn, Uranus, and Neptune. Yep, that's the list.\n\nBut wait, the user might be confusing Earth with Mars. I should clarify that Earth is the only planet known to support life. The other planets are mostly gas giants and have no liquid water, so they don't support life as Earth does. So the answer should be Earth. I should also mention that although there are other planets, none have liquid water, which makes the answer more complete.\n\nI need to make sure there are no alternatives. Maybe some people might think Mars, but I know that's not the case. Also, it's good to mention that life on Earth is closely linked to the presence of water, which is why Earth is our only planet with that characteristic. That way, the answer is not only accurate but also informative.\n</think>\n\nHumans live on **Earth**, the planet that supports life as we know it. The Earth is the only known planet in our solar system where liquid water exists and where life can occur. Other planets are considered \"gas giants\" or \"ice giants\" due to their extreme conditions and lack of liquid water, making them inhospitable for life.",
"refusal": null,
"role": "assistant",
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": null
}
}
],
"created": 1757550390,
"model": "Qwen/Qwen3-0.6B",
"object": "chat.completion",
"service_tier": null,
"system_fingerprint": "3.3.5-dev0-sha-1b90c50",
"usage": {
"completion_tokens": 312,
"prompt_tokens": 15,
"total_tokens": 327,
"completion_tokens_details": null,
"prompt_tokens_details": null
}
}
},
"is_streaming": false
}
}