Output readability improvement

playground/agents/agent_with_basemodel_output_type.py

@@ -1,10 +1,28 @@
+"""
+* WORKING
+
+What this script does:
+Structured output example
+
+Requirements:
+Add the folowing API key(s) in your .env file:
+   - OPENAI_API_KEY (this example works best with Openai bc it uses openai function calling structure)
+
+Note:
+If you are running playground examples in the project files directly (without swarms installed via PIP),
+make sure to add the project root to your PYTHONPATH by running the following command in the project's root directory:
+  'export PYTHONPATH=$(pwd):$PYTHONPATH'
+"""
+
 from pydantic import BaseModel, Field
-from swarms import OpenAIChat
-from swarms import Agent
+from swarms import Agent, OpenAIChat
 
 
 # Initialize the schema for the person's information
 class Schema(BaseModel):
+    """
+    This is a pydantic class describing the format of a structured output
+    """
     name: str = Field(..., title="Name of the person")
     agent: int = Field(..., title="Age of the person")
     is_student: bool = Field(..., title="Whether the person is a student")
@@ -12,15 +30,6 @@ class Schema(BaseModel):
         ..., title="List of courses the person is taking"
     )
 
-
-# Convert the schema to a JSON string
-tool_schema = Schema(
-    name="Tool Name",
-    agent=1,
-    is_student=True,
-    courses=["Course1", "Course2"],
-)
-
 # Define the task to generate a person's information
 task = "Generate a person's information based on the following schema:"
 
@@ -30,22 +39,13 @@ agent = Agent(
     system_prompt=(
         "Generate a person's information based on the following schema:"
     ),
-    # Set the tool schema to the JSON string -- this is the key difference
-    # tool_schema=tool_schema,
     llm=OpenAIChat(),
-    max_loops=3,
-    autosave=True,
-    dashboard=False,
+    max_loops=1,
     streaming_on=True,
     verbose=True,
-    interactive=True,
-    # Set the output type to the tool schema which is a BaseModel
-    # output_type=tool_schema,  # or dict, or str
-    metadata_output_type="json",
     # List of schemas that the agent can handle
-    list_base_models=[tool_schema],
-    function_calling_format_type="OpenAI",
-    function_calling_type="json",  # or soon yaml
+    list_base_models=[Schema],
+    agent_ops_on=True
 )
 
 # Run the agent to generate the person's information

swarms/structs/agent.py

@@ -671,6 +671,10 @@ class Agent(BaseStructure):
 
     ########################## FUNCTION CALLING ##########################
 
+    def response_readability(self, response) -> str:
+        """Specifies the name of the agent in capital letters in pink and the response text in blue."""
+        return f"\033[1;35m{self.name.upper()}:\033[0m \033[34m{response}\033[0m"
+
     def run(
         self,
         task: Optional[str] = None,
@@ -726,7 +730,7 @@ class Agent(BaseStructure):
                             response = self.llm(
                                 task_prompt, *args, **kwargs
                             )
-                            print(response)
+                            print(self.response_readability(response))
 
                             self.short_memory.add(
                                 role=self.agent_name, content=response
@@ -746,7 +750,7 @@ class Agent(BaseStructure):
                                 if img is None
                                 else (task_prompt, img, *args)
                             )
-                            response = self.llm(*response_args, **kwargs)
+                            response = self.response_readability(self.llm(*response_args, **kwargs))
 
                             # Print
                             if self.streaming_on is True: