chore: Update Tasks.md documentation to include example of using output JSON in tasks

docs/core-concepts/Tasks.md

@@ -212,6 +212,86 @@ print(f"""
 """)
 ```
 
+## Using Output JSON in Tasks
+
+In the crewAI framework, you can specify that the output of a task should be in JSON format by using the `output_json` parameter. This requires an OpenAI client and ensures that only one output format is set per task. Below is an example demonstrating how to use this feature.
+
+### Example: Defining a Task with JSON Output
+
+Here we define a task that searches for local companies and outputs the results in a JSON format according to a predefined schema using Pydantic models.
+
+```python
+from pydantic import BaseModel
+from typing import List
+
+# Pydantic model definitions
+class CompanyData(BaseModel):
+    Name: str
+    Address: str
+    Phone: str
+    Website: str
+    Email: str
+
+class CompanyList(BaseModel):
+    companies: List[CompanyData] = []
+
+# Task definition using output_json
+task_search_companies = Task(
+    description='Search for local companies using Google Maps. '
+                'The search parameter is "{query}". '
+                'For each company, find the phone number and website. '
+                'Return a JSON list with the details found.',
+    expected_output='List of companies with name, address, phone, website and e-mail in JSON format without additional comments or character escape formatting.',
+    agent=search_agent,
+    tools=[search_tool],
+    async_execution=False,
+    output_json=CompanyList,
+    output_file='companies.json'
+)
+
+# Creating a crew to execute the task
+crew = Crew(
+    agents=[search_agent],
+    tasks=[task_search_companies],
+    verbose=2
+)
+
+# Execute the task
+result = crew.kickoff()
+
+# Accessing the task output
+print(f"""
+    Task completed!
+    Task: {task_search_companies.output.description}
+    Output: {task_search_companies.output.raw_output}
+""")
+```
+
+### Example Output
+
+The output of the task, when accessed, would be a JSON structured as follows:
+
+```json
+{
+    "companies": [
+        {
+            "Name": "Tech Innovators Inc.",
+            "Address": "123 Silicon Valley, CA",
+            "Phone": "+1-800-555-1234",
+            "Website": "https://techinnovators.com",
+            "Email": "[email protected]"
+        },
+        {
+            "Name": "Green Solutions LLC",
+            "Address": "456 Green Street, NY",
+            "Phone": "+1-800-555-5678",
+            "Website": "https://greensolutions.com",
+            "Email": "[email protected]"
+        }
+    ]
+}
+```
+
 ## Tool Override Mechanism
 
 Specifying tools in a task allows for dynamic adaptation of agent capabilities, emphasizing CrewAI's flexibility.
@@ -227,4 +307,4 @@ These validations help in maintaining the consistency and reliability of task ex
 
 ## Conclusion
 
-Tasks are the driving force behind the actions of agents in crewAI. By properly defining tasks and their outcomes, you set the stage for your AI agents to work effectively, either independently or as a collaborative unit. Equipping tasks with appropriate tools, understanding the execution process, and following robust validation practices are crucial for maximizing CrewAI's potential, ensuring agents are effectively prepared for their assignments and that tasks are executed as intended.
+Tasks are the driving force behind the actions of agents in crewAI. By properly defining tasks and their outcomes, you set the stage for your AI agents to work effectively, either independently or as a collaborative unit. Equipping tasks with appropriate tools, understanding the execution process, and following robust validation practices are crucial for maximizing CrewAI's potential, ensuring agents are effectively prepared for their assignments and that tasks are executed as intended.