client/types: add logprobs support (#601)

examples/chat-logprobs.py

@@ -0,0 +1,31 @@
+from typing import Iterable
+
+import ollama
+
+
+def print_logprobs(logprobs: Iterable[dict], label: str) -> None:
+  print(f'\n{label}:')
+  for entry in logprobs:
+    token = entry.get('token', '')
+    logprob = entry.get('logprob')
+    print(f'  token={token!r:<12} logprob={logprob:.3f}')
+    for alt in entry.get('top_logprobs', []):
+      if alt['token'] != token:
+        print(f'    alt -> {alt["token"]!r:<12} ({alt["logprob"]:.3f})')
+
+
+messages = [
+  {
+    'role': 'user',
+    'content': 'hi! be concise.',
+  },
+]
+
+response = ollama.chat(
+  model='gemma3',
+  messages=messages,
+  logprobs=True,
+  top_logprobs=3,
+)
+print('Chat response:', response['message']['content'])
+print_logprobs(response.get('logprobs', []), 'chat logprobs')

examples/chat-with-history.py

@@ -15,7 +15,8 @@ messages = [
   },
   {
     'role': 'assistant',
-    'content': 'The weather in Tokyo is typically warm and humid during the summer months, with temperatures often exceeding 30°C (86°F). The city experiences a rainy season from June to September, with heavy rainfall and occasional typhoons. Winter is mild, with temperatures rarely dropping below freezing. The city is known for its high-tech and vibrant culture, with many popular tourist attractions such as the Tokyo Tower, Senso-ji Temple, and the bustling Shibuya district.',
+    'content': """The weather in Tokyo is typically warm and humid during the summer months, with temperatures often exceeding 30°C (86°F). The city experiences a rainy season from June to September, with heavy rainfall and occasional typhoons. Winter is mild, with temperatures
+    rarely dropping below freezing. The city is known for its high-tech and vibrant culture, with many popular tourist attractions such as the Tokyo Tower, Senso-ji Temple, and the bustling Shibuya district.""",
   },
 ]
 

examples/generate-logprobs.py

@@ -0,0 +1,24 @@
+from typing import Iterable
+
+import ollama
+
+
+def print_logprobs(logprobs: Iterable[dict], label: str) -> None:
+  print(f'\n{label}:')
+  for entry in logprobs:
+    token = entry.get('token', '')
+    logprob = entry.get('logprob')
+    print(f'  token={token!r:<12} logprob={logprob:.3f}')
+    for alt in entry.get('top_logprobs', []):
+      if alt['token'] != token:
+        print(f'    alt -> {alt["token"]!r:<12} ({alt["logprob"]:.3f})')
+
+
+response = ollama.generate(
+  model='gemma3',
+  prompt='hi! be concise.',
+  logprobs=True,
+  top_logprobs=3,
+)
+print('Generate response:', response['response'])
+print_logprobs(response.get('logprobs', []), 'generate logprobs')