ym88659208ym87991671
Agent Types | Документация для разработчиков

Agent Types

Обновлено 1 марта 2024

This categorizes all the available agents along a few dimensions.

Intended Model Type

Whether this agent is intended for Chat Models (takes in messages, outputs message) or LLMs (takes in string, outputs string). The main thing this affects is the prompting strategy used. You can use an agent with a different type of model than it is intended for, but it likely won't produce results of the same quality.

Supports Chat History

Whether or not these agent types support chat history. If it does, that means it can be used as a chatbot. If it does not, then that means it's more suited for single tasks. Supporting chat history generally requires better models, so earlier agent types aimed at worse models may not support it.

Supports Multi-Input Tools

Whether or not these agent types support tools with multiple inputs. If a tool only requires a single input, it is generally easier for an LLM to know how to invoke it. Therefore, several earlier agent types aimed at worse models may not support them.

Supports Parallel Function Calling

Having an LLM call multiple tools at the same time can greatly speed up agents whether there are tasks that are assisted by doing so. However, it is much more challenging for LLMs to do this, so some agent types do not support this.

Required Model Params

Whether this agent requires the model to support any additional parameters. Some agent types take advantage of things like OpenAI function calling, which require other model parameters. If none are required, then that means that everything is done via prompting

When to Use

Our commentary on when you should consider using this agent type.

Agent TypeIntended Model TypeSupports Chat HistorySupports Multi-Input ToolsSupports Parallel Function CallingRequired Model ParamsWhen to UseAPI
OpenAI ToolsChattoolsIf you are using a recent OpenAI model (1106 onwards)Ref
OpenAI FunctionsChatfunctionsIf you are using an OpenAI model, or an open-source model that has been finetuned for function calling and exposes the same functions parameters as OpenAIRef
XMLLLMIf you are using Anthropic models, or other models good at XMLRef
Structured ChatChatIf you need to support tools with multiple inputsRef
JSON ChatChatIf you are using a model good at JSONRef
ReActLLMIf you are using a simple modelRef
Self Ask With SearchLLMIf you are using a simple model and only have one search toolRef
ПАО Сбербанк использует cookie для персонализации сервисов и удобства пользователей.
Вы можете запретить сохранение cookie в настройках своего браузера.