messages() — langchain Function Reference

Architecture documentation for the messages() function in test_chat.py from the langchain codebase.

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ messages() — langchain Function Reference

Dependency Diagram

graph TD
  802ac192_f451_437b_f3e4_1e062e0f992a["messages()"]
  00c8bbe0_a31c_1ac8_487a_bfd5a9d6b117["test_chat.py"]
  802ac192_f451_437b_f3e4_1e062e0f992a -->|defined in| 00c8bbe0_a31c_1ac8_487a_bfd5a9d6b117
  style 802ac192_f451_437b_f3e4_1e062e0f992a fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/tests/unit_tests/prompts/test_chat.py lines 40–72

def messages() -> list[BaseMessagePromptTemplate]:
    """Create messages."""
    system_message_prompt = SystemMessagePromptTemplate(
        prompt=PromptTemplate(
            template="Here's some context: {context}",
            input_variables=["context"],
        )
    )
    human_message_prompt = HumanMessagePromptTemplate(
        prompt=PromptTemplate(
            template="Hello {foo}, I'm {bar}. Thanks for the {context}",
            input_variables=["foo", "bar", "context"],
        )
    )
    ai_message_prompt = AIMessagePromptTemplate(
        prompt=PromptTemplate(
            template="I'm an AI. I'm {foo}. I'm {bar}.",
            input_variables=["foo", "bar"],
        )
    )
    chat_message_prompt = ChatMessagePromptTemplate(
        role="test",
        prompt=PromptTemplate(
            template="I'm a generic message. I'm {foo}. I'm {bar}.",
            input_variables=["foo", "bar"],
        ),
    )
    return [
        system_message_prompt,
        human_message_prompt,
        ai_message_prompt,
        chat_message_prompt,
    ]