Fix orchestrations basic concepts

website/docs/user-guide/basic-concepts/human-in-the-loop.mdx

@@ -72,16 +72,20 @@ The workflow follows this pattern:
 from autogen import ConversableAgent, LLMConfig
 import os
 import random
+from dotenv import load_dotenv
+
+load_dotenv()
 
 # Note: Make sure to set your API key in your environment first
 
 # Configure the LLM
-llm_config = LLMConfig(config_list={
-    "api_type": "openai",
-    "model": "gpt-5-nano",
-    "api_key": os.environ.get("OPENAI_API_KEY"),
-    "temperature": 0.2,
-})
+llm_config = LLMConfig(
+    config_list={
+        "api_type": "openai",
+        "model": "gpt-5-nano",
+        "api_key": os.environ.get("OPENAI_API_KEY"),
+    }
+)
 
 # Define the system message for our finance bot
 finance_system_message = """
@@ -170,16 +174,20 @@ Here's the complete, ready-to-run code for our financial compliance Human in the
     from autogen import ConversableAgent, LLMConfig
     import os
     import random
+    from dotenv import load_dotenv
+
+    load_dotenv()
 
     # Note: Make sure to set your API key in your environment first
 
     # Configure the LLM
-    llm_config = LLMConfig(config_list={
-        "api_type": "openai",
-        "model": "gpt-5-nano",
-        "api_key": os.environ.get("OPENAI_API_KEY"),
-        "temperature": 0.2,
-    })
+    llm_config = LLMConfig(
+        config_list={
+            "api_type": "openai",
+            "model": "gpt-5-nano",
+            "api_key": os.environ.get("OPENAI_API_KEY"),
+        }
+    )
 
     # Define the system message for our finance bot
     finance_system_message = """

website/docs/user-guide/basic-concepts/introducing-group-chat.mdx

@@ -59,9 +59,18 @@ from autogen import ConversableAgent, LLMConfig
 from autogen.agentchat import initiate_group_chat
 from autogen.agentchat.group.patterns import AutoPattern
 
+# build a Config List
+llm_config = LLMConfig(
+    config_list={
+        "api_type": "openai",
+        "model": "gpt-5-nano",
+        "api_key": os.environ.get("OPENAI_API_KEY"),
+    }
+)
+
 # Create your specialized agents
-agent_1 = ConversableAgent(name="agent_1", llm_config=llm_config, system_message="...")
-agent_2 = ConversableAgent(name="agent_2", llm_config=llm_config, system_message="...")
+agent_1 = ConversableAgent(name="agent_1", llm_config=llm_config, system_message="goto agent_2")
+agent_2 = ConversableAgent(name="agent_2", llm_config=llm_config, system_message="go back to agent_1")
 
 # Create human agent if needed
 human = ConversableAgent(name="human", human_input_mode="ALWAYS")
@@ -109,16 +118,20 @@ from autogen.agentchat.group.patterns import AutoPattern
 
 import os
 import random
+from dotenv import load_dotenv
+
+load_dotenv()
 
 # Note: Make sure to set your API key in your environment first
 
-# Configure the LLM
-llm_config = LLMConfig(config_list={
-    "api_type": "openai",
-    "model": "gpt-5-nano",
-    "api_key": os.environ.get("OPENAI_API_KEY"),
-    "temperature": 0.2,
-})
+# Build a LLM Config List
+llm_config = LLMConfig(
+    config_list={
+        "api_type": "openai",
+        "model": "gpt-5-nano",
+        "api_key": os.environ.get("OPENAI_API_KEY"),
+    }
+)
 
 # Define the system message for our finance bot
 finance_system_message = """
@@ -261,16 +274,19 @@ Here's the complete, ready-to-run code for our enhanced financial compliance sys
 
     import os
     import random
+    from dotenv import load_dotenv
 
-    # Note: Make sure to set your API key in your environment first
+    load_dotenv()
 
+    # Note: Make sure to set your API key in your environment first, i.e., .env
     # Configure the LLM
-    llm_config = LLMConfig(config_list={
-        "api_type": "openai",
-        "model": "gpt-5-nano",
-        "api_key": os.environ.get("OPENAI_API_KEY"),
-        "temperature": 0.2
-    })
+    llm_config = LLMConfig(
+        config_list={
+            "api_type": "openai",
+            "model": "gpt-5-nano",
+            "api_key": os.environ.get("OPENAI_API_KEY"),
+        }
+    )
 
     # Define the system message for our finance bot
     finance_system_message = """
@@ -539,6 +555,9 @@ Here's the updated code that incorporates automatic termination:
     from typing import Any
     import os
     import random
+    from dotenv import load_dotenv
+
+    load_dotenv()
 
     from autogen import ConversableAgent, LLMConfig
     from autogen.agentchat import initiate_group_chat
@@ -547,12 +566,13 @@ Here's the updated code that incorporates automatic termination:
     # Note: Make sure to set your API key in your environment first
 
     # Configure the LLM
-    llm_config = LLMConfig(config_list={
-        "api_type": "openai",
-        "model": "gpt-5-nano",
-        "api_key": os.environ.get("OPENAI_API_KEY"),
-        "temperature": 0.2,
-    })
+    llm_config = LLMConfig(
+        config_list={
+            "api_type": "openai",
+            "model": "gpt-5-nano",
+            "api_key": os.environ.get("OPENAI_API_KEY"),
+        }
+    )
 
     # Define the system message for our finance bot
     finance_system_message = """

website/docs/user-guide/basic-concepts/introducing-tools.mdx

@@ -84,20 +84,23 @@ First, let's create a function that checks for duplicate payments:
 import os
 from typing import Annotated, Any
 from datetime import datetime, timedelta
+from dotenv import load_dotenv
 
 from autogen import ConversableAgent, LLMConfig
 from autogen.agentchat import initiate_group_chat
 from autogen.agentchat.group.patterns import AutoPattern
 
+load_dotenv()
 # Note: Make sure to set your API key in your environment first
 
 # Configure the LLM
-llm_config = LLMConfig(config_list={
-    "api_type": "openai",
-    "model": "gpt-5-nano",
-    "api_key": os.environ.get("OPENAI_API_KEY"),
-    "temperature": 0.2,
-})
+llm_config = LLMConfig(
+    config_list={
+        "api_type": "openai",
+        "model": "gpt-5-nano",
+        "api_key": os.environ.get("OPENAI_API_KEY"),
+    }
+)
 
 # Mock database of previous transactions
 def get_previous_transactions() -> list[dict[str, Any]]:
@@ -254,7 +257,7 @@ transactions = [
 
 # Format the initial message
 initial_prompt = (
-    "Please process the following transactions one at a time, checking for duplicates:\n\n" +
+    "Please process the following transactions one at a time, checking for duplicates:\n note: strictly goto summary_bot once all tasks are done and generate final summary\n\n" +
     "\n".join([f"{i+1}. {tx}" for i, tx in enumerate(transactions)])
 )
 ```
@@ -324,20 +327,23 @@ Here's the complete, ready-to-run code for our enhanced financial compliance sys
     import random
     from typing import Annotated, Any
     from datetime import datetime, timedelta
+    from dotenv import load_dotenv
 
     from autogen import ConversableAgent, LLMConfig
     from autogen.agentchat import initiate_group_chat
     from autogen.agentchat.group.patterns import AutoPattern
 
+    load_dotenv()
     # Note: Make sure to set your API key in your environment first
 
     # Configure the LLM
-    llm_config = LLMConfig(config_list={
-        "api_type": "openai",
-        "model": "gpt-5-nano",
-        "api_key": os.environ.get("OPENAI_API_KEY"),
-        "temperature": 0.2,
-    })
+    llm_config = LLMConfig(
+        config_list={
+            "api_type": "openai",
+            "model": "gpt-5-nano",
+            "api_key": os.environ.get("OPENAI_API_KEY"),
+        }
+    )
 
     # Mock database of previous transactions
     def get_previous_transactions() -> list[dict[str, Any]]:

website/docs/user-guide/basic-concepts/structured-outputs.mdx

@@ -51,11 +51,12 @@ class ResponseModel(BaseModel):
     field3: list[str]
 
 # 2. Create LLM configuration with the structured output model
-llm_config = LLMConfig(config_list={
+llm_config = LLMConfig(
+    config_list={
         "api_type": "openai",
         "model": "gpt-5-nano",
+        "response_format": ResponseModel,  # Specify the response format
     },
-    response_format=ResponseModel,  # Specify the response format
 )
 
 # 3. Create agent with structured output configuration
@@ -107,13 +108,12 @@ Next, let's update our summary agent to use this structured output model:
 ```python hl_lines="7 12-16"
 # Configure the LLM for summary bot with structured output
 summary_llm_config = LLMConfig(
-   {
+   config_list = {
         "api_type": "openai",
         "model": "gpt-5-nano",
         "api_key": os.environ.get("OPENAI_API_KEY"),
-        "temperature": 0.2,
+        "response_format": AuditLogSummary,  # Using our Pydantic model for structured output
     },
-    response_format=AuditLogSummary,  # Using our Pydantic model for structured output
 )
 
 # Define the system message for the summary agent
@@ -274,12 +274,13 @@ Here's the complete, ready-to-run code for our financial compliance system with
         }
 
     # Configure the LLM for finance bot (standard configuration)
-    finance_llm_config = LLMConfig(config_list={
-        "api_type": "openai",
-        "model": "gpt-5-nano",
-        "api_key": os.environ.get("OPENAI_API_KEY"),
-        "temperature": 0.2
-    })
+    finance_llm_config = LLMConfig(
+        config_list={
+            "api_type": "openai",
+            "model": "gpt-5-nano",
+            "api_key": os.environ.get("OPENAI_API_KEY"),
+        }
+    )
 
     # Define the system message for our finance bot
     finance_system_message = """
@@ -332,7 +333,6 @@ Here's the complete, ready-to-run code for our financial compliance system with
             "api_type": "openai",
             "model": "gpt-5-nano",
             "api_key": os.environ.get("OPENAI_API_KEY"),
-            "temperature": 0.2,
         },
         response_format=AuditLogSummary,  # Using the Pydantic model for structured output
     )
@@ -371,7 +371,7 @@ Here's the complete, ready-to-run code for our financial compliance system with
 
     # Format the initial message
     initial_prompt = (
-        "Please process the following transactions one at a time, checking for duplicates:\n\n" +
+        "Please process the following transactions one at a time, checking for duplicates:\n note: strictly goto summary_bot once all tasks are done and generate final summary\n\n" +
         "\n".join([f"{i+1}. {tx}" for i, tx in enumerate(transactions)])
     )