🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
Python agentai-societiesartificial-intelligencecommunicative-aicooperative-aideep-learninglarge-language-modelsmulti-agent-systemsnatural-language-processing
title: "Messages" icon: messages
doc_code_map: - "camel/messages/**/*.py"
TheBaseMessage class is the backbone for all message objects in
the CAMEL chat system. It offers a consistent structure for agent
communication and easy conversion between message types.
Explore and run every code sample directly in this Colab notebook.
Get Started
To create aBaseMessage instance, supply these arguments:
- role_name: Name of the user or assistant
- role_type:
RoleType.ASSISTANTorRoleType.USER - content: The actual message text
- meta_dict (optional): Additional metadata
- video_bytes (optional): Attach video bytes
- image_list (optional): List of PIL Image objects
- image_detail (optional): Level of image detail (default: "auto")
- video_detail (optional): Level of video detail (default: "low")
message = BaseMessage( role_name="test_user", role_type=RoleType.USER, content="test content" )
</Card>
<Card title="Convenient Constructors" icon="user">
Easily create messages for user or assistant agents:
```python
user_message = BaseMessage.make_user_message(
role_name="user_name",
content="test content for user",
)
assistant_message = BaseMessage.make_assistant_message(
role_name="assistant_name",
content="test content for assistant",
)
Methods in the BaseMessage Class
The BaseMessage class lets you:
-
Create a new instance with updated content:
new_message = message.create_new_instance("new test content") -
Convert to OpenAI message formats:
openai_message = message.to_openai_message(role_at_backend=OpenAIBackendRole.USER)
openai_system_message = message.to_openai_system_message()
openai_user_message = message.to_openai_user_message()
openai_assistant_message = message.to_openai_assistant_message() -
Convert to a Python dictionary:
message_dict = message.to_dict()
BaseMessage into the
right format for different LLM APIs and agent flows.
Using BaseMessage with ChatAgent
You can send multimodal messages (including images) to your agents:
from io import BytesIO
import requests
from PIL import Image
from camel.agents import ChatAgent
from camel.messages import BaseMessage
# Download an image
url = "https://raw.githubusercontent.com/camel-ai/camel/master/misc/logo_light.png"
img = Image.open(BytesIO(requests.get(url).content))
# Build system and user messages
sys_msg = BaseMessage.make_assistant_message(
role_name="Assistant",
content="You are a helpful assistant.",
)
user_msg = BaseMessage.make_user_message(
role_name="User", content="what's in the image?", image_list=[img]
)
# Create agent and send message
camel_agent = ChatAgent(system_message=sys_msg)
response = camel_agent.step(user_msg)
print(response.msgs[0].content)
The image features a logo for "CAMEL-AI." It includes a stylized purple camel
graphic alongside the text "CAMEL-AI," which is also in purple. The design
appears modern and is likely related to artificial intelligence.
Conclusion
TheBaseMessage class is essential for structured, clear, and
flexible communication in the CAMEL-AI ecosystem—making it simple to create,
convert, and handle messages across any workflow.
For further details, check out the key modules documentation.