Bi

模型提供商配置

接入云端模型或本机模型,并设置自动切换。

Markdown 原文Raw markdown

Bi 通过通用的模型接口与服务通信,大多数模型服务都能直接接入。

添加一个服务

在「设置」中填写:

  • 服务地址(Base URL) —— 接口地址,例如 https://api.openai.com/v1
  • API 密钥(API Key) —— 你在该服务处的密钥
  • 模型名 —— 例如 gpt-4o
  • 接口类型 —— 通常选择 OpenAI 兼容;使用 Ollama 时也可选其原生接口

可以为每个模型标注能力(视觉、工具、推理)和上下文长度,用于界面展示与筛选。

密钥保存在哪里

密钥保存在本机的 .bi 目录内。Bi 没有自己的服务器,密钥只会发送到你填写的服务地址。

本地模型

把服务地址指向本机运行的模型服务,内容就不必离开这台电脑。常见选择:

  • Ollama
  • LM Studio
  • vLLM

默认模型与自动切换

你可以固定使用某一个模型,也可以交给自动选择。自动选择会在可用模型之间挑选;某个模型暂时不可用(连接失败或超时)时,会改用其他可用模型继续本次任务,无需中断。

长会话

上下文如何被压缩与延续,见长会话的上下文延续。

Add a model

Connect a cloud model or a local model, with automatic failover.

Markdown 原文Raw markdown

Bi talks to providers through a common model interface, so most services connect directly.

Add a provider

In Settings, fill in:

  • Base URL — the endpoint, for example https://api.openai.com/v1
  • API key — your key for that provider
  • Model name — for example gpt-4o
  • API type — usually OpenAI-compatible; Ollama can also use its native API

Each model can declare its capabilities (vision, tools, reasoning) and context length, which the UI uses for display and filtering.

Where keys are stored

Keys are stored in the local .bi directory. Bi has no server of its own, so a key is only sent to the endpoint you configured.

Local models

Point the Base URL at a model service running on your machine and content need not leave it. Common choices:

  • Ollama
  • LM Studio
  • vLLM

Default model and failover

You can pin one model or let Bi choose automatically. Automatic selection picks among available models; if one is temporarily unavailable (connection failure or timeout), another available model continues the task instead of aborting it.

Long sessions

How context is compacted and continued is covered in Long conversations.