Migrate Python samples to new SDK (foundry_local_sdk)

- audio-transcription: foundry_local -> foundry_local_sdk, use model.get_audio_client()
- langchain-integration: foundry_local -> foundry_local_sdk, use start_web_service()
- web-server: foundry_local -> foundry_local_sdk, use start_web_service()
- Remove hello-foundry-local (legacy), add native-chat-completions (new SDK)
- Remove functioncalling (Jupyter), add tool-calling (new SDK, how-to style)
- Use qwen2.5-0.5b model alias across all samples
- Use common app_name 'foundry_local_samples' for shared model cache
- Update all 4 tutorials to use qwen2.5-0.5b and foundry_local_samples

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: samuel100

samples/python/audio-transcription/src/app.py

@@ -1,23 +1,39 @@
 # <complete_code>
 # <imports>
-from foundry_local import FoundryLocalManager
+import sys
+from foundry_local_sdk import Configuration, FoundryLocalManager
 # </imports>
 
+
 # <init>
-# Initialize with a whisper model alias
-alias = "whisper"
-manager = FoundryLocalManager(alias)
+# Initialize the Foundry Local SDK
+config = Configuration(app_name="foundry_local_samples")
+FoundryLocalManager.initialize(config)
+manager = FoundryLocalManager.instance
+
+# Load the whisper model for speech-to-text
+model = manager.catalog.get_model("whisper")
+model.download(
+    lambda progress: print(
+        f"\rDownloading model: {progress:.2f}%",
+        end="",
+        flush=True,
+    )
+)
+print()
+model.load()
+print("Model loaded.")
 # </init>
 
 # <transcription>
-# Get the audio client
-audio_client = manager.get_audio_client(alias)
-
-# Transcribe an audio file
-import sys
+# Get the audio client and transcribe
+audio_client = model.get_audio_client()
 audio_file = sys.argv[1] if len(sys.argv) > 1 else "audio.wav"
 result = audio_client.transcribe(audio_file)
 print("Transcription:")
 print(result.text)
 # </transcription>
+
+# Clean up
+model.unload()
 # </complete_code>