Nathan Weinberg
62b3ad349a
fix: return to hardcoded model IDs for Vertex AI ( #4041 )
...
# What does this PR do?
partial revert of b67aef2Closes #3988
## Test Plan
Server side, set up your Vertex AI env vars (`VERTEX_AI_PROJECT`,
`VERTEX_AI_LOCATION`, and `GOOGLE_APPLICATION_CREDENTIALS`) and run the
starter distribution
```bash
$ llama stack list-deps starter | xargs -L1 uv pip install
$ llama stack run starter
```
Client side, formerly broken cURL requests now working
```bash
$ curl http://127.0.0.1:8321/v1/models | jq '.data | map(select(.provider_id == "vertexai"))'
[
{
"identifier": "vertexai/vertex_ai/gemini-2.0-flash",
"provider_resource_id": "vertex_ai/gemini-2.0-flash",
"provider_id": "vertexai",
"type": "model",
"metadata": {},
"model_type": "llm"
},
{
"identifier": "vertexai/vertex_ai/gemini-2.5-flash",
"provider_resource_id": "vertex_ai/gemini-2.5-flash",
"provider_id": "vertexai",
"type": "model",
"metadata": {},
"model_type": "llm"
},
{
"identifier": "vertexai/vertex_ai/gemini-2.5-pro",
"provider_resource_id": "vertex_ai/gemini-2.5-pro",
"provider_id": "vertexai",
"type": "model",
"metadata": {},
"model_type": "llm"
}
]
$ curl -fsS http://127.0.0.1:8321/v1/openai/v1/chat/completions -H "Content-Type: application/json" -d "{\"model\": \"vertexai/vertex_a
i/gemini-2.5-flash\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}], \"max_tokens\": 128, \"temperature\": 0.0}" | jq
{
"id": "p8oIaYiQF8_PptQPo-GH8QQ",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"message": {
"content": "Hello there! How can I help you today?",
"refusal": null,
"role": "assistant",
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": null
}
}
],
...
```
Signed-off-by: Nathan Weinberg <nweinber@redhat.com>
2025-11-03 17:38:16 -08:00
Ashwin Bharambe
471b1b248b
chore(package): migrate to src/ layout ( #3920 )
...
Migrates package structure to src/ layout following Python packaging
best practices.
All code moved from `llama_stack/` to `src/llama_stack/`. Public API
unchanged - imports remain `import llama_stack.*`.
Updated build configs, pre-commit hooks, scripts, and GitHub workflows
accordingly. All hooks pass, package builds cleanly.
**Developer note**: Reinstall after pulling: `pip install -e .`
2025-10-27 12:02:21 -07:00
