Allow setting environment variables from llama stack run and fix ollama

llama_stack/providers/remote/inference/ollama/config.py

@@ -6,17 +6,17 @@
 
 from typing import Any, Dict
 
-from llama_stack.distribution.datatypes import RemoteProviderConfig
+from pydantic import BaseModel
 
 
-DEFAULT_OLLAMA_PORT = 11434
+DEFAULT_OLLAMA_URL = "http://localhost:11434"
 
 
-class OllamaImplConfig(RemoteProviderConfig):
-    port: int
+class OllamaImplConfig(BaseModel):
+    url: str = DEFAULT_OLLAMA_URL
 
     @classmethod
     def sample_run_config(
-        cls, port_str: str = str(DEFAULT_OLLAMA_PORT)
+        cls, url: str = "${env.OLLAMA_URL:http://localhost:11434}", **kwargs
     ) -> Dict[str, Any]:
-        return {"port": port_str}
+        return {"url": url}

llama_stack/providers/remote/inference/ollama/ollama.py

@@ -82,7 +82,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
         return AsyncClient(host=self.url)
 
     async def initialize(self) -> None:
-        print("Initializing Ollama, checking connectivity to server...")
+        print(f"checking connectivity to Ollama at `{self.url}`...")
         try:
             await self.client.ps()
         except httpx.ConnectError as e:

llama_stack/providers/remote/inference/tgi/config.py

@@ -21,7 +21,7 @@ class TGIImplConfig(BaseModel):
     )
 
     @classmethod
-    def sample_run_config(cls, url: str = "${env.TGI_URL}"):
+    def sample_run_config(cls, url: str = "${env.TGI_URL}", **kwargs):
         return {
             "url": url,
         }

llama_stack/providers/remote/inference/vllm/config.py

@@ -29,6 +29,7 @@ class VLLMInferenceAdapterConfig(BaseModel):
     def sample_run_config(
         cls,
         url: str = "${env.VLLM_URL}",
+        **kwargs,
     ):
         return {
             "url": url,