update router client

llama_stack/apis/inference/client.py

@@ -98,6 +98,17 @@ async def run_main(host: str, port: int, stream: bool):
     async for log in EventLogger().log(iterator):
         log.print()
 
+    print("Testing a different model provider")
+    iterator = client.chat_completion(
+        ChatCompletionRequest(
+            model="ollama-1",
+            messages=[message],
+            stream=stream,
+        )
+    )
+    async for log in EventLogger().log(iterator):
+        log.print()
+
 
 def main(host: str, port: int, stream: bool = True):
     asyncio.run(run_main(host, port, stream))

llama_stack/providers/adapters/inference/ollama/ollama.py

@@ -105,6 +105,13 @@ class OllamaInferenceAdapter(Inference):
                 delta="",
             )
         )
+
+        yield ChatCompletionResponseStreamChunk(
+            event=ChatCompletionResponseEvent(
+                event_type=ChatCompletionResponseEventType.progress,
+                delta="model={}, url={}".format(model, self.url),
+            )
+        )
         # request = ChatCompletionRequest(
         #     model=model,
         #     messages=messages,