Learn about CAMEL’s agent types, with a focus on ChatAgent and advanced agent architectures for AI-powered automation.
BaseAgent
abstract class, which defines two essential methods:
Method | Purpose | Description |
---|---|---|
reset() | State Management | Resets the agent to its initial state |
step() | Task Execution | Performs a single step of the agent’s operation |
ChatAgent
is the primary implementation that handles conversations with language models. It supports:
Other Agent Types (When to Use)
CriticAgent
DeductiveReasonerAgent
EmbodiedAgent
KnowledgeGraphAgent
MultiHopGeneratorAgent
SearchAgent
TaskAgent
ChatAgent
supports multiple ways to specify the model:
ChatAgent
can produce structured output by leveraging Pydantic models. This feature is especially useful when you need the agent to return data in a specific format, such as JSON. By defining a Pydantic model, you can ensure that the agent’s output is predictable and easy to parse.
ChatAgent
. First, define a BaseModel
that specifies the desired output fields. You can add descriptions to each field to guide the model.Memory Management
Tool Integration
Response Handling
Model Specification