black formatting

activities.py

@@ -2,24 +2,26 @@ from dataclasses import dataclass
 from temporalio import activity
 from ollama import chat, ChatResponse
 
+
 @dataclass
 class OllamaPromptInput:
     prompt: str
     context_instructions: str
 
+
 class OllamaActivities:
     @activity.defn
     def prompt_ollama(self, input: OllamaPromptInput) -> str:
-        model_name = 'mistral'
+        model_name = "mistral"
         messages = [
             {
-                'role': 'system',
-                'content': input.context_instructions,
+                "role": "system",
+                "content": input.context_instructions,
             },
             {
-                'role': 'user',
-                'content': input.prompt,
-            }
+                "role": "user",
+                "content": input.prompt,
+            },
         ]
 
         response: ChatResponse = chat(model=model_name, messages=messages)

run_ollama.py

@@ -1,21 +1,23 @@
 from ollama import chat, ChatResponse
 
+
 def main():
-    model_name = 'mistral'
-    
+    model_name = "mistral"
+
     # The messages to pass to the model
     messages = [
         {
-            'role': 'user',
-            'content': 'Why is the sky blue?',
+            "role": "user",
+            "content": "Why is the sky blue?",
         }
     ]
-    
+
     # Call ollama's chat function
     response: ChatResponse = chat(model=model_name, messages=messages)
-    
+
     # Print the full message content
     print(response.message.content)
 
-if __name__ == '__main__':
-    main()
+
+if __name__ == "__main__":
+    main()

workflows.py

@@ -158,10 +158,6 @@ class EntityOllamaWorkflow:
     # Return (context_instructions, prompt) for summarizing the conversation
     def prompt_summary_with_history(self) -> tuple[str, str]:
         history_string = self.format_history()
-        context_instructions = (
-            f"Here is the conversation history between a user and a chatbot: {history_string}"
-        )
-        actual_prompt = (
-            "Please produce a two sentence summary of this conversation."
-        )
+        context_instructions = f"Here is the conversation history between a user and a chatbot: {history_string}"
+        actual_prompt = "Please produce a two sentence summary of this conversation."
         return (context_instructions, actual_prompt)