mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-03 19:57:35 +00:00
c3d3a0b833
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Integration Tests (Replay) / Integration Tests (, , , client=, vision=) (push) Failing after 3s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 4s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 7s
Update ReadTheDocs / update-readthedocs (push) Failing after 3s
Test External API and Providers / test-external (venv) (push) Failing after 5s
Vector IO Integration Tests / test-matrix (push) Failing after 7s
Python Package Build Test / build (3.13) (push) Failing after 8s
Python Package Build Test / build (3.12) (push) Failing after 8s
Unit Tests / unit-tests (3.13) (push) Failing after 14s
Unit Tests / unit-tests (3.12) (push) Failing after 14s
UI Tests / ui-tests (22) (push) Successful in 1m7s
Pre-commit / pre-commit (push) Successful in 2m34s
One needed to specify record-replay related environment variables for running integration tests. We could not use defaults because integration tests could be run against Ollama instances which could be running different models. For example, text vs vision tests needed separate instances of Ollama because a single instance typically cannot serve both of these models if you assume the standard CI worker configuration on Github. As a result, `client.list()` as returned by the Ollama client would be different between these runs and we'd end up overwriting responses. This PR "solves" it by adding a small amount of complexity -- we store model list responses specially, keyed by the hashes of the models they return. At replay time, we merge all of them and pretend that we have the union of all models available. ## Test Plan Re-recorded all the tests using `scripts/integration-tests.sh --inference-mode record`, including the vision tests.
39 lines
1.5 KiB
JSON
39 lines
1.5 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:11434/api/generate",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"raw": true,
|
|
"prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWhich planet has rings around it with a name starting with letter S?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
|
|
"options": {
|
|
"temperature": 0.0
|
|
},
|
|
"stream": false
|
|
},
|
|
"endpoint": "/api/generate",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"created_at": "2025-09-03T17:42:17.227488Z",
|
|
"done": true,
|
|
"done_reason": "stop",
|
|
"total_duration": 3003964916,
|
|
"load_duration": 111221916,
|
|
"prompt_eval_count": 30,
|
|
"prompt_eval_duration": 72578583,
|
|
"eval_count": 70,
|
|
"eval_duration": 2819555375,
|
|
"response": "The answer is Saturn! Saturn's ring system is one of the most iconic and well-known in our solar system. The rings are made up of ice particles, rock debris, and dust that orbit around the planet due to its gravitational pull.\n\nWould you like to know more about Saturn's rings or is there something else I can help you with?",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|