Implementation:Cohere ai Cohere python ChatMessageV2 Types

Metadata
Source Repo	Cohere Python SDK
Domains	NLP, Chat_API, Message_Formatting
Last Updated	2026-02-15 14:00 GMT

Overview

Concrete Pydantic models for constructing typed chat messages in the Cohere V2 API.

Description

ChatMessageV2 is a discriminated union of four message types (UserChatMessageV2, AssistantChatMessageV2, SystemChatMessageV2, ToolChatMessageV2), discriminated on the role field. Each type is a Pydantic model extending UncheckedBaseModel with role-specific fields. ChatMessages is typed as List[ChatMessageV2].

Usage

Import the specific message types and construct a list to pass as the messages parameter to V2Client.chat() or V2Client.chat_stream().

Code Reference

• Source Location: Repository cohere-ai/cohere-python, File src/cohere/types/chat_message_v2.py, Lines L1-94
• Signature:

class UserChatMessageV2(UncheckedBaseModel):
    role: typing.Literal["user"] = "user"
    content: UserMessageV2Content

class AssistantChatMessageV2(UncheckedBaseModel):
    role: typing.Literal["assistant"] = "assistant"
    tool_calls: typing.Optional[typing.List[ToolCallV2]] = None
    tool_plan: typing.Optional[str] = None
    content: typing.Optional[AssistantMessageV2Content] = None
    citations: typing.Optional[typing.List[Citation]] = None

class SystemChatMessageV2(UncheckedBaseModel):
    role: typing.Literal["system"] = "system"
    content: SystemMessageV2Content

class ToolChatMessageV2(UncheckedBaseModel):
    role: typing.Literal["tool"] = "tool"
    tool_call_id: str
    content: ToolMessageV2Content

ChatMessageV2 = Annotated[
    Union[UserChatMessageV2, AssistantChatMessageV2, SystemChatMessageV2, ToolChatMessageV2],
    UnionMetadata(discriminant="role"),
]

• Import: from cohere import UserChatMessageV2, AssistantChatMessageV2, SystemChatMessageV2, ToolChatMessageV2

I/O Contract

Name	Type	Required	Description
Inputs
role	Literal string	Yes	Discriminant field ("user", "assistant", "system", "tool")
content	Varies by role	Yes (except assistant)	Message content (string or content blocks)
tool_calls	Optional[List[ToolCallV2]]	No	Only on AssistantChatMessageV2
tool_call_id	str	Yes (tool only)	Links tool result to its call
Outputs
Return value	ChatMessages (List[ChatMessageV2])	—	Message list ready for chat API

Usage Examples

from cohere import ClientV2, UserChatMessageV2, SystemChatMessageV2

messages = [
    SystemChatMessageV2(content="You are a helpful assistant."),
    UserChatMessageV2(content="What is machine learning?"),
]

client = ClientV2()
response = client.chat(model="command-a-03-2025", messages=messages)

Related Pages

• Principle:Cohere_ai_Cohere_python_Message_Construction