Leonid Pershin
5832c5cf75
- Updated the `provision_llm` function to utilize the `/api/tags` endpoint for verifying available models, improving accuracy in model management. - Introduced a new `already_have_ollama_tag` function to ensure exact tag matching, preventing mismatches during model checks. - Enhanced the `pull_stream` function to require a successful status from the API before proceeding, ensuring reliable model downloads. - Added logic to handle unwritten blob files, improving the robustness of the model pulling process. - Updated documentation and tests to reflect these changes, ensuring clarity and reliability in Ollama model operations.
71 lines
2.3 KiB
Python
71 lines
2.3 KiB
Python
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from gpu_rent.llm_runtime import (
|
|
already_have_ollama_tag,
|
|
decide_runtime,
|
|
normalize_runtime,
|
|
parse_ollama_models,
|
|
write_ollama_models_preset,
|
|
)
|
|
|
|
|
|
def test_normalize_runtime():
|
|
assert normalize_runtime(None) == "none"
|
|
assert normalize_runtime("OLLAMA") == "ollama"
|
|
with pytest.raises(ValueError):
|
|
normalize_runtime("llamacpp")
|
|
with pytest.raises(ValueError):
|
|
normalize_runtime("foo")
|
|
|
|
|
|
def test_decide_runtime_flags_win():
|
|
assert (
|
|
decide_runtime(flag=None, ollama_flag=True, from_config="none") == "ollama"
|
|
)
|
|
assert (
|
|
decide_runtime(flag="ollama", ollama_flag=False, from_config="none") == "ollama"
|
|
)
|
|
assert decide_runtime(flag=None, ollama_flag=False, from_config="ollama") == "ollama"
|
|
|
|
|
|
def test_parse_ollama_models(tmp_path: Path):
|
|
path = tmp_path / "m.yaml"
|
|
path.write_text(
|
|
"models:\n - name: huihui_ai/qwen2.5-abliterate:7b\n default: true\n - qwen2.5:3b\n",
|
|
encoding="utf-8",
|
|
)
|
|
entries = parse_ollama_models(path)
|
|
assert [e.name for e in entries] == [
|
|
"huihui_ai/qwen2.5-abliterate:7b",
|
|
"qwen2.5:3b",
|
|
]
|
|
assert entries[0].default is True
|
|
|
|
|
|
def test_parse_empty_manifest(tmp_path: Path):
|
|
path = tmp_path / "empty.yaml"
|
|
path.write_text("models: []\n", encoding="utf-8")
|
|
assert parse_ollama_models(path) == []
|
|
assert parse_ollama_models(tmp_path / "missing.yaml") == []
|
|
|
|
|
|
def test_write_preset(tmp_path: Path):
|
|
path = tmp_path / "out.yaml"
|
|
write_ollama_models_preset(path, "recommended")
|
|
entries = parse_ollama_models(path)
|
|
assert entries[0].name == "huihui_ai/qwen2.5-vl-abliterated:7b"
|
|
write_ollama_models_preset(path, "big")
|
|
assert parse_ollama_models(path)[0].name == "huihui_ai/qwen2.5-vl-abliterated:32b"
|
|
write_ollama_models_preset(path, "text")
|
|
assert parse_ollama_models(path)[0].name == "huihui_ai/qwen2.5-abliterate:7b"
|
|
|
|
|
|
def test_already_have_ollama_tag_exact_only():
|
|
have = {"qwen2.5:7b", "foo:latest"}
|
|
assert already_have_ollama_tag(have, "qwen2.5:7b")
|
|
assert not already_have_ollama_tag(have, "qwen2.5:3b")
|
|
assert already_have_ollama_tag(have, "foo")
|
|
assert already_have_ollama_tag(have, "foo:latest")
|