phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 09:53:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: return to hardcoded model IDs for Vertex AI (#4041)

Browse source 
# What does this PR do?
partial revert of b67aef2

Vertex AI doesn't offer an endpoint for listing models from Google's
Model Garden

Return to hardcoded values until such an endpoint is available

Closes #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>
This commit is contained in:
Nathan Weinberg 2025-11-03 20:38:16 -05:00 • committed by GitHub
parent cb40da210f
commit 62b3ad349a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 10 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

10
src/llama_stack/providers/remote/inference/vertexai/vertexai.py
View file

@ -4,6 +4,7 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from collections.abc import Iterable
import google.auth.transport.requests
from google.auth import default
@ -42,3 +43,12 @@ class VertexAIInferenceAdapter(OpenAIMixin):
Source: https://cloud.google.com/vertex-ai/generative-ai/docs/start/openai
"""
return f"https://{self.config.location}-aiplatform.googleapis.com/v1/projects/{self.config.project}/locations/{self.config.location}/endpoints/openapi"
async def list_provider_model_ids(self) -> Iterable[str]:
"""
VertexAI doesn't currently offer a way to query a list of available models from Google's Model Garden
For now we return a hardcoded version of the available models
:return: An iterable of model IDs
"""
return ["vertexai/gemini-2.0-flash", "vertexai/gemini-2.5-flash", "vertexai/gemini-2.5-pro"]