diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index 2e68245aa2..fe56fadab3 100644 --- a/.github/PULL_REQUEST_TEMPLATE.md +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -27,6 +27,9 @@ - [ ] 👀 My changes have been well-tested, **and "Verification Steps" and "Screenshots" have been provided above**. / 我的更改经过了良好的测试,**并已在上方提供了“验证步骤”和“运行截图”**。 +- [ ] 📚 I checked the affected WebUI instructions and screenshots in `docs/zh` and `docs/en` against the changed navigation, page structure, and labels, and updated them in this PR (or explained why no documentation update is needed). For renamed, moved, or merged entry points, I included an **old entry → new entry** mapping in the documentation and changelog. + / 我已对照变化后的 WebUI 入口、页面结构和术语,核对并在本 PR 中更新 `docs/zh` 和 `docs/en` 的相关操作说明与截图(或说明无需更新文档的原因)。入口改名、移动或合并时,已在文档和 changelog 中补充 **旧入口 → 新入口** 对照。 + - [ ] 🤓 I have ensured that no new dependencies are introduced, OR if new dependencies are introduced, they have been added to the appropriate locations in `requirements.txt` and `pyproject.toml`. / 我确保没有引入新依赖库,或者引入了新依赖库的同时将其添加到 `requirements.txt` 和 `pyproject.toml` 文件相应位置。 diff --git a/AGENTS.md b/AGENTS.md index 4d7ba90490..5e39048851 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -53,6 +53,7 @@ ruff check . 8. When updating the project version, keep `[project].version` in `pyproject.toml` and `__version__` in `astrbot/__init__.py` in sync. `VERSION` in `astrbot/core/config/default.py` should derive from `astrbot.__version__` instead of hardcoding a separate version string. 9. When designing WebUI dialogs, use `text-h3 pa-4 pb-0 pl-6` as the base class for dialog titles, and use `variant="text"` or `variant="tonal"` for dialog buttons. 10. Consider cross-platform compatibility (e.g., Windows, macOS, and Linux, as well as Arm64 and x86 CPU architectures) and compatibility with Python 3.10+. +11. When changing WebUI navigation, page structure, or terminology, update the affected instructions and screenshots in `docs/zh` and `docs/en` in the same PR. For renamed, moved, or merged entry points, include an old-to-new mapping in the relevant docs and changelog. Keep layout redesigns separate from feature additions where practical, and explain necessary navigation changes in the PR. See `CONTRIBUTING.md` for the review checklist. ### KISS and First Principles diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index bfdf904e03..9ebc7511d2 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -35,6 +35,14 @@ #### 代码规范 +##### WebUI 与文档同步 + +- 修改菜单入口、页面结构或界面术语时,在同一个 PR 中更新 `docs/zh` 和 `docs/en` 的相关操作说明、链接与截图。没有对应英文页面时无需为此翻译整篇文档,但应检查已有英文说明。 +- 按当前默认侧边栏、实际按钮文案和完整操作流程核对文档。重点检查配置文件、模型提供商、机器人、插件和系统设置;仅通过链接检查不能证明入口说明仍然正确。 +- 入口改名、移动或合并时,在对应文档和 `changelogs/` 中写明「旧入口 → 新入口」,并同步维护 [WebUI 入口对照](docs/zh/use/webui.md#菜单与旧入口对照)。截图若仍展示旧结构,应更新或移除,并用可独立完成操作的文字步骤替代。 +- 将布局重设计与新增功能尽量拆成独立 PR。新增功能优先沿用现有页面结构;确需调整已有入口时,在 PR 中说明原因和受影响的流程,避免连续、无关的页面重排。 +- 提交前运行 `cd docs && pnpm run docs:build`,并按更新后的步骤核对相关 WebUI 页面。在 PR 中写明核对的页面和验证结果。 + ##### Core 我们使用 Ruff 作为代码格式化和静态分析工具。在提交代码之前,请运行以下命令以确保代码符合规范: @@ -106,6 +114,14 @@ We use the `fix/` prefix for bug fixes and the `feat/` prefix for new features. #### Code Style +##### Keep WebUI and documentation in sync + +- When changing navigation, page structure, or UI labels, update the affected instructions, links, and screenshots in `docs/zh` and `docs/en` in the same PR. Check existing English instructions; translating an entire missing English page is not required. +- Verify the default sidebar, actual button labels, and complete workflows. Pay particular attention to profiles, providers, platforms, extensions, and system settings. Passing link checks does not establish that navigation instructions are correct. +- For renamed, moved, or merged entry points, include an **old entry → new entry** mapping in the relevant docs and `changelogs/`, and maintain the [WebUI navigation reference](docs/en/use/webui.md#navigation-and-previous-entry-points). Replace or remove screenshots showing outdated layouts, with text instructions sufficient to complete the task on their own. +- Keep layout redesigns and feature additions in separate PRs where practical. Prefer the existing page structure for new features. Explain necessary navigation changes and affected workflows in the PR to avoid repeated, unrelated rearrangements. +- Before submitting, run `cd docs && pnpm run docs:build` and check the affected WebUI pages against the updated steps. Include the checked pages and validation results in the PR. + ##### Core We use Ruff as our code formatter and static analysis tool. Before submitting your code, please run the following commands to ensure your code adheres to the style guidelines: diff --git a/changelogs/v4.28.0.md b/changelogs/v4.28.0.md index b06ea5ccc0..ebae234783 100644 --- a/changelogs/v4.28.0.md +++ b/changelogs/v4.28.0.md @@ -34,6 +34,18 @@ Each season brings its own beauty, and the joy is endless. - Preserved text in Lark mixed text-and-image messages. (#9841) - Displayed the create-folder button in the mobile persona manager. (#9812) +### WebUI Upgrade Notes + +| Previous entry point | New entry point | +| --- | --- | +| Providers → Add Provider → Agent Runner | Config → Select a profile → AI → `…` → Change execution mode | +| Data / Dashboard | Data & Logs → Statistics | +| Conversation Management / Conversations | Data & Logs → Conversations | +| Logs / Console | Data & Logs → Logs | +| Trace | Data & Logs → Trace | + +Third-party Agent parameters are now configured within each profile instead of creating and selecting an Agent provider ID. Changing execution mode resets its parameters to the new mode's defaults; review the confirmation and save the profile after configuration. See the [Agent Runner guide](https://docs.astrbot.app/en/use/agent-runner.html) and [current WebUI navigation reference](https://docs.astrbot.app/en/use/webui.html#navigation-and-previous-entry-points). + ## 中文 ### 主要新增 @@ -67,6 +79,18 @@ Each season brings its own beauty, and the joy is endless. - 在移动端的人格管理器中显示新建文件夹按钮。 (#9812) +### WebUI 升级提示 + +| 旧入口 | 新入口 | +| --- | --- | +| 模型提供商 → 新增提供商 → Agent 执行器 | 配置文件 → 选择配置文件 → AI 配置 → `…` → 更换执行方式 | +| 数据 / 数据统计 | 数据与日志 → 统计 | +| 对话管理 / 对话数据 | 数据与日志 → 对话 | +| 日志 / 平台日志 | 数据与日志 → 日志 | +| 追踪 | 数据与日志 → 追踪 | + +第三方 Agent 参数现在直接保存在各配置文件中,无需创建和选择 Agent 提供商 ID。切换执行方式会将参数重置为新方式的默认值,请阅读确认提示,并在配置完成后保存配置文件。详见 [Agent 执行器指南](https://docs.astrbot.app/use/agent-runner.html) 和 [当前 WebUI 入口对照](https://docs.astrbot.app/use/webui.html#菜单与旧入口对照)。 + [4.28.0-beta.1]: https://github.com/AstrBotDevs/AstrBot/compare/v4.27.4...v4.28.0-beta.1 ## Changes Since 4.28.0-beta.1 diff --git a/dashboard/README.md b/dashboard/README.md index 0cdcae80cc..d8e5972508 100644 --- a/dashboard/README.md +++ b/dashboard/README.md @@ -2,9 +2,33 @@ 基于 CodedThemes/Berry 模板开发。 -## 环境变量 +## 本地开发 -- `VITE_ASTRBOT_RELEASE_BASE_URL`(可选) - - 默认值:`https://github.com/AstrBotDevs/AstrBot/releases` - - 用途:管理面板内“更新到最新版本”外部跳转所使用的 release 基地址。集成方可按需覆盖(例如 Desktop 指向其自身发布页)。 - - 建议传入仓库的 `.../releases` 基地址(不带 `/latest`)。 +先在项目根目录启动后端: + +```bash +uv sync +uv run main.py +``` + +在另一个终端启动 WebUI: + +```bash +cd dashboard +pnpm install +pnpm dev +``` + +开发服务器默认运行在 `http://localhost:3000`,将 `/api` 请求代理到 `http://127.0.0.1:6185`。后端地址不同时,请修改 `vite.config.ts` 中的 `server.proxy`。 + +## 构建与 API 客户端 + +```bash +pnpm build +``` + +此命令检查 TypeScript 类型并生成 `dist/`。当后端 API 路由、请求/响应结构或 OpenAPI 定义发生变化时,在本目录运行 `pnpm generate:api` 重新生成前端客户端。 + +## 发布更新入口 + +WebUI 顶部的更新入口会打开更新对话框,通过后端 API 获取版本信息。`VITE_ASTRBOT_RELEASE_BASE_URL` 当前没有被前端代码读取,设置此变量不会改变更新入口。 diff --git a/docs/en/config/model-config.md b/docs/en/config/model-config.md index 5bc3d57b07..fbba00bbbc 100644 --- a/docs/en/config/model-config.md +++ b/docs/en/config/model-config.md @@ -1,12 +1,10 @@ +# Configure Custom Model Parameters -# 配置自定义的模型参数 +You can configure model parameters in the WebUI: -请手动修改位于 `data/cmd_config.json` 下的配置文件。 +1. Open `Providers` and select the provider containing your model. +2. In its configured models list, click the model name or its settings icon to open the model configuration dialog. +3. Under `Custom request body parameters` (`custom_extra_body`), add the parameters required by your model, such as `temperature`, `top_p`, or `max_tokens`. +4. Click `Save`. -找到 `provider`,并找到你想要修改的提供商的模型配置: - -![alt text](https://files.astrbot.app/docs/source/images/model-config/image-2.png) - -然后在 `model_config` 中添加新的参数即可。 - -具体的参数请参看对应的提供商的文档。 +Available fields depend on the provider. For example, Gemini exposes its own generation settings instead of the generic `custom_extra_body` field. Refer to your provider's documentation for supported parameters and values. diff --git a/docs/en/deploy/astrbot/compshare.md b/docs/en/deploy/astrbot/compshare.md index 08b07b7db6..57688e22be 100644 --- a/docs/en/deploy/astrbot/compshare.md +++ b/docs/en/deploy/astrbot/compshare.md @@ -33,8 +33,6 @@ You can find the public IP in Console -> Basic Network (Public). > It may take around 30 seconds before the page becomes reachable. -![WebUI](https://www-s.ucloud.cn/2025/07/7e9fc6edc1dfa916abc069f4cecc24cf_1753940381771.png) - Use the random password printed in startup logs for first-time login, and use the username shown in the logs (usually `astrbot`). Change it immediately after login. After logging in, you can reset your password and continue setup. @@ -50,26 +48,21 @@ The image includes Ollama. You can pull any model and host it locally on the ins 1. Choose a model from [Ollama Search](https://ollama.com/search). 2. Connect to the instance terminal via SSH (from Compshare Console -> Instance List -> Console Command and Password). 3. Run `ollama pull ` and wait for completion. -4. In AstrBot Dashboard -> Providers, edit `ollama_deepseek-r1`, update the model name, and save. - -![image](https://files.astrbot.app/docs/source/images/compshare/image-1.png) +4. Open `Providers → Chat Completion`, select the preconfigured Ollama source, click `Fetch Model List`, and click `+` beside the model you just pulled. If no source is preconfigured, click `Add`, select `Ollama`, enter the instance's Ollama URL, and click `Save and Fetch Models`. ### Use Compshare Model API AstrBot supports direct access to model APIs provided by Compshare. 1. Find the model you want at [Compshare Model Center](https://console.compshare.cn/light-gpu/model-center). -2. In AstrBot Dashboard -> Providers, click `+ Add Provider`, then choose Compshare. -If Compshare is not listed, choose OpenAI-compatible access and set API Base URL to `https://api.modelverse.cn/v1`. -Enter the model name in model configuration and save. +2. Open `Providers → Chat Completion → Add`, select `OpenAI Compatible`, enter your Compshare API key, and set API Base URL to `https://api.modelverse.cn/v1`. +3. Click `Save and Fetch Models`, then click `+` beside the model you want. If the API returns no model list, click `Save Configuration`, then `Custom Model`, and enter the exact model ID supplied by Compshare. ### Test -In AstrBot Dashboard, click `Chat` and run `/provider` to view and switch your active provider. - -Then send a normal message to test whether the model works. +Click `Test Model` on the configured model to check connectivity. Then open `Config`, select the profile used by your bot, choose the new model under `AI → Model → Chat Model`, and click `Save Configuration`. -![image](https://files.astrbot.app/docs/source/images/compshare/image-2.png) +Use the chat switch in the WebUI header or send a message to the bot on its connected messaging platform to test a reply. ## Connect to Messaging Platforms diff --git a/docs/en/deploy/astrbot/kubernetes.md b/docs/en/deploy/astrbot/kubernetes.md index 5d34fe03b4..a24370f1d9 100644 --- a/docs/en/deploy/astrbot/kubernetes.md +++ b/docs/en/deploy/astrbot/kubernetes.md @@ -73,7 +73,7 @@ kubectl apply -f k8s/astrbot_with_napcat/02-deployment.yaml Since AstrBot and NapCat are in the same Pod, they can communicate directly via `localhost`. 1. **Add a message platform in AstrBot:** - * Go to the AstrBot WebUI, select `Platform` -> `Add`. + * Go to the AstrBot WebUI, select `Platforms` -> `Add Adapter`. * **Select Message Platform Category**: `aiocqhttp` * **Bot Name**: `napcat` (or custom) * **Reverse Websocket Host**: `0.0.0.0` diff --git a/docs/en/deploy/when-deployed.md b/docs/en/deploy/when-deployed.md index d30245052f..50bbfc8b0e 100644 --- a/docs/en/deploy/when-deployed.md +++ b/docs/en/deploy/when-deployed.md @@ -12,5 +12,5 @@ AstrBot Documentation: [![wakatime](https://wakatime.com/badge/user/915e5316-99c ## Next... -If you're reading this, it means you have successfully deployed the messaging platform and sent/received your first command. Next, you can configure large language models or add plugins. Please refer to the `Configuration - Integrating LLM Services` section. +If you're reading this, it means you have successfully deployed the messaging platform and sent/received your first command. Next, add a model under `Providers`, select it in the bot's configuration profile under `Config`, or install plugins under `Extensions → Plugins → AstrBot Plugin Market`. See [Model Providers](../providers/start.md) and [Plugins](../use/plugin.md). diff --git a/docs/en/dev/astrbot-config.md b/docs/en/dev/astrbot-config.md index 499a1d0e68..cfb247a77e 100644 --- a/docs/en/dev/astrbot-config.md +++ b/docs/en/dev/astrbot-config.md @@ -10,6 +10,8 @@ AstrBot's configuration file is a JSON format file. AstrBot reads this file at s > Since AstrBot v4.0.0, we introduced the concept of [multiple configuration files](https://blog.astrbot.app/posts/what-is-changed-in-4.0.0/#%E5%A4%9A%E9%85%8D%E7%BD%AE%E6%96%87%E4%BB%B6). `data/cmd_config.json` serves as the default configuration `default`. Other configuration files you create in the WebUI are stored in the `data/config/` directory, starting with `abconf_`. +In the WebUI, manage bot and session behavior profiles under `Config`. Global runtime, logging, network, WebUI security, and text-to-image service settings are under `Settings`. Model connections and bot connections are managed under `Providers` and `Platforms`, respectively. + The default AstrBot configuration is as follows: ```jsonc @@ -548,7 +550,7 @@ Log level. Default is `INFO`. Can be set to `DEBUG`, `INFO`, `WARNING`, `ERROR`, ### `trace_enable` -Whether to enable trace recording. Default is `false`. When enabled, AstrBot records execution traces, which can be viewed under `Data` -> `Trace` in the admin panel. +Whether to enable trace recording. Default is `false`. When enabled, AstrBot records execution traces, which can be viewed under `Data & Logs → Trace` in the admin panel. ### `pip_install_arg` diff --git a/docs/en/dev/openapi.md b/docs/en/dev/openapi.md index e00ecdad97..5130494265 100644 --- a/docs/en/dev/openapi.md +++ b/docs/en/dev/openapi.md @@ -8,7 +8,7 @@ Starting from v4.18.0, AstrBot provides API Key based HTTP APIs for programmatic ## Quick Start -1. Create an API key in WebUI - Settings. +1. Open `Settings → OpenAPI` in the WebUI and click `Create API Key`. 2. Include the API key in request headers: ```http diff --git a/docs/en/dev/star/plugin-new.md b/docs/en/dev/star/plugin-new.md index d86ae7471e..1f20c6fcd3 100644 --- a/docs/en/dev/star/plugin-new.md +++ b/docs/en/dev/star/plugin-new.md @@ -86,7 +86,7 @@ your_plugin/ SKILL.md ``` -In that case, the Skill name uses the plugin directory name. Plugin-provided Skills are managed by the plugin and appear as read-only sources in the WebUI Skills page. They can be enabled or disabled, but cannot be deleted or edited from Local Skills. When the plugin is uninstalled or updated, its bundled Skills change with the plugin files. +In that case, the Skill name uses the plugin directory name. Plugin-provided Skills are managed by the plugin and appear as read-only sources under `Extensions → Skills` in the WebUI. They can be enabled or disabled, but cannot be deleted or edited from Local Skills. When the plugin is uninstalled or updated, its bundled Skills change with the plugin files. ### Declare Supported Platforms (Optional) @@ -147,9 +147,9 @@ AstrBot uses a runtime plugin injection mechanism. Therefore, when debugging plu You can use AstrBot's hot reload feature to streamline the development process. -After modifying the plugin code, you can find your plugin in the AstrBot WebUI's plugin management section, click the `...` button in the upper right corner, and select `Reload Plugin`. +After modifying the plugin code, open `Extensions → Plugins` in the AstrBot WebUI, find your plugin, and click the refresh icon (`Reload Extension`) on its card. -If the plugin fails to load due to code errors or other reasons, you can also click **"Try one-click reload fix"** in the error prompt on the admin panel to reload it. +If the plugin fails to load due to code errors or other reasons, click its `Reload` button in the `Failed to Load Plugins` list on the same page. ### Plugin Dependency Management diff --git a/docs/en/faq.md b/docs/en/faq.md index f480a76840..dae0418418 100644 --- a/docs/en/faq.md +++ b/docs/en/faq.md @@ -89,8 +89,9 @@ After restart, AstrBot will reload or download WebUI files that match the curren ### How to Let AstrBot Control My Mac / Windows / Linux Computer? -1. In AstrBot WebUI's `Config -> General Config`, find `Use Computer Capabilities`, and select `local` for the runtime environment. -2. In `Config -> Other Config`, find `Admin ID List`, and add your user ID (you can get it through the `/sid` command). +1. In the AstrBot WebUI, open `Config`, select the profile used by your bot, and go to `AI → Capabilities → Agent Computer Use`. Set `Computer Use Runtime` to `local`. This section requires the built-in AstrBot AI runner. +2. In the same profile, go to `Platform → General → Administrator IDs` and add your user ID (available through the `/sid` command). +3. Click `Save Configuration` in the bottom-right corner. > [!TIP] > For security reasons, when runtime environment is set to `local`, AstrBot only allows AstrBot administrators to use computer capabilities by default. @@ -102,7 +103,7 @@ After restart, AstrBot will reload or download WebUI files that match the curren ### No Permission to Execute Admin Commands -1. `/name, /provider, /dashboard_update, /op, /deop, /persona, /llm, /plugin, /model, /groupnew` are the default admin commands. You can use the `/sid` command to get a user's ID, then add it to the admin ID list in Settings -> Other Settings. +1. `/name, /provider, /dashboard_update, /op, /deop, /persona, /llm, /plugin, /model, /groupnew` are the default admin commands. You can use the `/sid` command to get a user's ID, then open `Config`, select the profile used by your bot, add the ID under `Platform → General → Administrator IDs`, and click `Save Configuration` in the bottom-right corner. ### Chinese Characters Garbled When Locally Rendering Markdown Images (t2i) @@ -125,7 +126,7 @@ This is because the provider's API returned empty text. Try the following steps: ### Cannot Install Plugin -1. Plugins are installed via GitHub. Access to GitHub from mainland China can indeed be unstable. You can use a proxy, then go to Other Settings -> HTTP Proxy to configure it. Alternatively, download the plugin archive directly and upload it. +1. Plugins are installed via GitHub. Access to GitHub from mainland China can indeed be unstable. Configure and save a proxy under `Settings → Network → Proxy & Dependency Sources → HTTP Proxy`. You can also set a `GitHub Proxy Address` on the same page, or download the plugin archive and install it from the Plugins page. ### Error `No module named 'xxx'` After Installing Plugin @@ -139,8 +140,8 @@ This is because the plugin's dependencies were not installed properly. Normally, Solution: -Based on the error message, refer to the plugin's README to manually install dependencies. You can install dependencies in the AstrBot WebUI under `Data` -> `Logs` -> `Install Pip Package`. +Based on the error message, refer to the plugin's README to manually install dependencies. You can install dependencies in the AstrBot WebUI under `Data & Logs → Logs → Install pip Package`. -![image](https://files.astrbot.app/docs/source/images/faq/image-1.png) +Enter the package name in the dialog, optionally specify a PyPI repository URL, and click `Install`. If you find that the plugin author did not include a `requirements.txt` file, please submit an issue in the plugin repository to remind the author to add it. diff --git a/docs/en/others/diagnostics.md b/docs/en/others/diagnostics.md index c4b34f4638..e551931c1b 100644 --- a/docs/en/others/diagnostics.md +++ b/docs/en/others/diagnostics.md @@ -12,6 +12,8 @@ This page provides a general checklist for diagnosing AstrBot issues. When somet ## Logs to Check First +When the WebUI is available, open `Data & Logs → Logs` to view live logs. To change console or file log levels, open `Settings → General → Logs` and save your changes. + Start with the main AstrBot log: ```text diff --git a/docs/en/platform/aiocqhttp.md b/docs/en/platform/aiocqhttp.md index fb8550ac5c..03a2bc7a80 100644 --- a/docs/en/platform/aiocqhttp.md +++ b/docs/en/platform/aiocqhttp.md @@ -18,8 +18,8 @@ Please refer to each implementation project's deployment documentation. ## 1. Configure OneBot v11 1. Open AstrBot's WebUI -2. Click `Bots` in the left sidebar -3. In the right panel, click `+ Create Bot` +2. Click `Platforms` in the left sidebar +3. Click `Add Adapter` above the bot list 4. Select `OneBot v11` Fill in the form: @@ -43,5 +43,5 @@ Notes: ## 3. Verify -Go to `Data` -> `Logs` in the AstrBot WebUI. If a blue log appears saying `aiocqhttp(OneBot v11) adapter connected.`, the connection is successful. +Go to `Data & Logs` -> `Logs` in the AstrBot WebUI. If a blue log appears saying `aiocqhttp(OneBot v11) adapter connected.`, the connection is successful. If after a few seconds you see `aiocqhttp adapter has been closed`, it means the connection timed out (failed). Please double-check your configuration. diff --git a/docs/en/platform/dingtalk.md b/docs/en/platform/dingtalk.md index a4bb53fa2a..b8ee3d5ab3 100644 --- a/docs/en/platform/dingtalk.md +++ b/docs/en/platform/dingtalk.md @@ -22,7 +22,7 @@ DingTalk supports two setup methods: one-click QR creation in AstrBot, or manual AstrBot version requirement: >= v4.25.0. -Open AstrBot Dashboard -> `Bots` -> `+ Create Bot`, then select `DingTalk`. +Open AstrBot Dashboard -> `Platforms` -> `Add Adapter`, then select `DingTalk`. Under `Creation Method`, select `One-click QR setup`, scan the QR code with the DingTalk mobile app, then create or bind a bot on the DingTalk authorization page. After creation succeeds, AstrBot automatically fills in `ClientID` and `ClientSecret`. Click `Save` to finish. @@ -48,7 +48,7 @@ Go to Credentials & Basic Information, then copy `ClientID` and `ClientSecret`. ## Connect in AstrBot -Open AstrBot Dashboard -> `Bots` -> `+ Create Bot`, then create a DingTalk adapter. +Open AstrBot Dashboard -> `Platforms` -> `Add Adapter`, then create a DingTalk adapter. If you want AstrBot to create the app for you, select `One-click QR setup` and complete the scan. If you already created the app yourself, select `Manual setup`, fill in `ClientID` and `ClientSecret`, then click Save. AstrBot will request authorization from DingTalk Open Platform automatically. diff --git a/docs/en/platform/discord.md b/docs/en/platform/discord.md index f61f049a4c..a102feeec5 100644 --- a/docs/en/platform/discord.md +++ b/docs/en/platform/discord.md @@ -2,12 +2,7 @@ ## Create AstrBot Discord Platform Adapter -Navigate to the messaging platform, click to add a new adapter, find Discord and click to enter the Discord configuration page. - -![Click to create bot, select discord type](https://files.astrbot.app/docs/source/images/discord/image.png) - -![Options from top to bottom: 1. Bot name 2. Enable 3. Bot token 4. Discord proxy address 5. Auto-register plugin commands as Discord slash commands 6. discord_guild_id_for_debug 7. Discord activity name](https://files.astrbot.app/docs/source/images/discord/image-3.png) -> For this tutorial, you only need to configure items 1, 2, 3, and 5 +Open `Platforms` in the WebUI, click `Add Adapter`, and select `Discord`. Fill in the following settings, then click `Save` after obtaining the token. - Bot Name: Customize this to easily distinguish between different adapters - Enable: Check to enable this adapter @@ -64,7 +59,7 @@ If you find this tedious, you can directly use administrator permissions, but it Discord supports the pre-acknowledgment emoji feature. When enabled, the bot will add an emoji reaction when processing a message, letting users know the bot is working on their request. -In the admin panel's "Configuration" page, find `Platform Specific -> Discord -> Pre-acknowledgment Emoji`: +Open `Config`, select the configuration profile used by the bot, click the search button, and search for `platform_specific.discord.pre_ack_emoji`. Click `Save Configuration` after editing: - **Enable Pre-acknowledgment Emoji**: When enabled, the bot will automatically add an emoji reaction upon receiving a message - **Emoji List**: Enter Unicode emoji symbols, e.g., 👍, 🤔, ⏳. You can add multiple emojis, and the bot will randomly select one to use diff --git a/docs/en/platform/kook.md b/docs/en/platform/kook.md index 96714566b2..7057b04e6f 100644 --- a/docs/en/platform/kook.md +++ b/docs/en/platform/kook.md @@ -30,8 +30,8 @@ Message receiving mode: WebSocket ## Configure in AstrBot 1. Access the AstrBot management panel. -2. Click **Bots** in the left sidebar. -3. Click `+ Create Bot` on the right side of the interface. +2. Click **Platforms** in the left sidebar. +3. Click `Add Adapter` above the bot list. 4. Select the `kook` adapter. 5. Fill in the configuration fields: - ID (id): Any name to identify this specific instance. diff --git a/docs/en/platform/lark.md b/docs/en/platform/lark.md index 293608939f..b59ef10954 100644 --- a/docs/en/platform/lark.md +++ b/docs/en/platform/lark.md @@ -26,7 +26,7 @@ Lark supports two setup methods: one-click QR creation in AstrBot, or manually c AstrBot version requirement: >= 4.25.0. -Open the AstrBot management panel, click `Bots` in the left sidebar, click `+ Create Bot`, and select `lark`. +Open the AstrBot management panel, click `Platforms` in the left sidebar, click `Add Adapter`, and select `lark`. Under `Creation Method`, select `One-click QR Creation`, choose the China or international edition as needed, then scan the QR code with the Lark mobile app and confirm. After creation succeeds, AstrBot automatically fills in the app's `app_id`, `app_secret`, and domain configuration. @@ -35,7 +35,7 @@ Under `Creation Method`, select `One-click QR Creation`, choose the China or int > > Replace `` in the URL below with your Lark app ID, then open it to jump to the permission enablement page: > -> To find the App ID, go back to AstrBot's `Bots` page, find the Lark bot you just created, click `Edit`, and check the dialog that opens. +> To find the App ID, go back to AstrBot's `Platforms` page, select the Lark bot you just created, and check `app_id` under `Connection settings`. > > ```text > https://open.feishu.cn/app//auth?q=contact:contact.base:readonly,contact:user.base:readonly,im:message.p2p_msg:readonly,im:message.group_at_msg:readonly,im:message:send,im:message,im:message:send_as_bot,im:resource:upload,im:resource,cardkit:card:write,im:message.group_at_msg:readonly,im:message.group_msg&op_from=openapi&token_type=tenant @@ -60,8 +60,8 @@ Click on "Credentials & Basic Info" to obtain your app_id and app_secret. ## Configuring AstrBot 1. Access the AstrBot management panel -2. Click on `Bots` in the left sidebar -3. In the right panel, click `+ Create Bot` +2. Click on `Platforms` in the left sidebar +3. Click `Add Adapter` above the bot list 4. Select `lark` 5. If you want AstrBot to create the app for you, select `One-click QR Creation` and complete the scan. If you already created the app yourself, select `Manual Creation` @@ -95,9 +95,7 @@ Next, click on "Events & Callbacks," select "Receive events using long connectio > [!TIP] > To make better use of this method, please refer to [Unified Webhook Mode](/en/use/unified-webhook.md#how-to-use-unified-webhook-mode) for the necessary configuration. -After clicking `Save`, the bot card will display "View Webhook URL." Click to view and copy the callback URL. - -![](https://files.astrbot.app/docs/source/images/lark/webhook.png) +After clicking `Save`, select the bot in `Platforms` and click `View Webhook URL` to copy the callback URL. Next, return to Lark's Events & Callbacks page, click "Event Configuration," select "Send events to developer server," enter the callback URL you just copied as the "Request URL," and click Save. If everything is correct, no errors will appear. diff --git a/docs/en/platform/line.md b/docs/en/platform/line.md index 884a841669..acfd0cd4b8 100644 --- a/docs/en/platform/line.md +++ b/docs/en/platform/line.md @@ -40,8 +40,8 @@ How to get them: ## Configure AstrBot 1. Open the AstrBot admin panel -2. Click `Bots` in the left sidebar -3. Click `+ Create Bot` +2. Click `Platforms` in the left sidebar +3. Click `Add Adapter` 4. Select `line` Fill in these fields: @@ -58,7 +58,7 @@ Click Save. The LINE adapter supports **unified webhook mode only**. -After saving, click `View Webhook URL` on the bot card and copy the URL. +After saving, select the bot in `Platforms` and click `View Webhook URL` to copy the URL. Then in LINE Developers Console: diff --git a/docs/en/platform/matrix.md b/docs/en/platform/matrix.md index 7d8b9bdc61..b3404dd589 100644 --- a/docs/en/platform/matrix.md +++ b/docs/en/platform/matrix.md @@ -24,9 +24,9 @@ Please refer to [Matrix Server](https://matrix.org/ecosystem/servers/) to view a ## Installing the astrbot_plugin_matrix_adapter Plugin -Go to the AstrBot WebUI plugin marketplace, search for `astrbot_plugin_matrix_adapter`, and click Install. +Go to `Extensions → Plugins → AstrBot Plugin Market` in the AstrBot WebUI, search for `astrbot_plugin_matrix_adapter`, and click Install. -After installation, navigate to Messaging Platforms (older versions: `Bot`) → Add Adapter → Select Matrix (if the option is missing, try restarting AstrBot or check the plugin installation status). +After installation, navigate to `Platforms` → `Add Adapter` → select Matrix (if the option is missing, try restarting AstrBot or check the plugin installation status). Click `Enable` in the configuration dialog that appears. diff --git a/docs/en/platform/mattermost.md b/docs/en/platform/mattermost.md index feb0716845..c3275fa46c 100644 --- a/docs/en/platform/mattermost.md +++ b/docs/en/platform/mattermost.md @@ -4,7 +4,7 @@ The Mattermost adapter connects to your Mattermost server through a Bot Token an ## Create the AstrBot Mattermost Platform Adapter -Go to the `Bots` page, click `+ Create Bot`, and choose `Mattermost`. +Go to the `Platforms` page, click `Add Adapter`, and choose `Mattermost`. On the configuration page, enable it first, then fill in: diff --git a/docs/en/platform/misskey.md b/docs/en/platform/misskey.md index 9056d14d26..23b89db08f 100644 --- a/docs/en/platform/misskey.md +++ b/docs/en/platform/misskey.md @@ -7,9 +7,7 @@ ## Create AstrBot Misskey Platform Adapter -Navigate to the messaging platform, click to add a new adapter, find Misskey and click to enter the Misskey configuration page. - -![Create Misskey Platform Adapter](https://files.astrbot.app/docs/source/images/misskey/create.png) +Open `Platforms` in the WebUI, click `Add Adapter`, select `Misskey`, and fill in the connection details described below. Click `Save` when finished. ## Configure Platform Adapter Settings @@ -21,8 +19,6 @@ Don't forget to click `Enable` before saving to activate the Misskey platform ad How to obtain the Misskey connection information is described below. -![Misskey Platform Adapter Configuration](https://files.astrbot.app/docs/source/images/misskey/config.png) - ## Misskey Instance URL This is the frontend address of the Misskey instance where your bot account is located, in standard domain format. For example, `https://misskey.example`. @@ -88,7 +84,7 @@ Enabled by default. When enabled, the bot will respond to private chat messages ## History Records -Conversation history for individual users in chats and posts appears under `Data` -> `Conversations` in the AstrBot WebUI. Chat conversations use `chat:UserID` as the session ID, while traditional posts use `note:UserID`. +Conversation history for individual users in chats and posts appears under `Data & Logs` -> `Conversations` in the AstrBot WebUI. Chat conversations use `chat:UserID` as the session ID, while traditional posts use `note:UserID`. ::: tip Where is the Misskey user's UserID? It can be found on the user's personal page in the `Raw` section. UserID is the unique key identifier for Misskey users within a single instance. diff --git a/docs/en/platform/qqofficial/webhook.md b/docs/en/platform/qqofficial/webhook.md index 48e4d6c87e..98f02d7fab 100644 --- a/docs/en/platform/qqofficial/webhook.md +++ b/docs/en/platform/qqofficial/webhook.md @@ -23,7 +23,7 @@ Proactive message push: Supported. ### Setup Flow -1. In AstrBot WebUI, click `Bots` in the left sidebar, then click `+ Create Bot`. +1. In AstrBot WebUI, click `Platforms` in the left sidebar, then click `Add Adapter`. 2. Select `QQ Official Bot (Webhook)`. 3. Under `Choose setup method`, select `One-click QR setup`, click start, then scan the QR code with mobile QQ. 4. After confirming the QR binding, click `Save`. @@ -33,9 +33,7 @@ Proactive message push: Supported. 8. Save the callback configuration, then restart AstrBot. > [!TIP] -> With `Unified Webhook Mode`, AstrBot generates a unique Webhook callback URL automatically. You can find it in the logs or on the bot card in WebUI. - -![unified_webhook](https://files.astrbot.app/docs/source/images/use/unified-webhook.png) +> With `Unified Webhook Mode`, AstrBot generates a unique Webhook callback URL automatically. You can find it under `Data & Logs → Logs`, or select the bot in `Platforms` and click `View Webhook URL`. ### Use in Group Chats @@ -93,8 +91,8 @@ Open `Development -> Development Settings`, find IP whitelist, and add your serv ### Configure in AstrBot 1. Open AstrBot Dashboard. -2. Click `Bots` in the left sidebar. -3. Click `+ Create Bot`. +2. Click `Platforms` in the left sidebar. +3. Click `Add Adapter`. 4. Select `QQ Official Bot (Webhook)`. Recommended: use `One-click QR setup`. @@ -124,7 +122,7 @@ The Webhook callback URL must be reachable from QQ Open Platform over the public Open `Development -> Callback Configuration`. -After you save the bot in AstrBot, AstrBot generates a unique Webhook callback URL. You can find it in the logs or on the bot card in WebUI. +After you save the bot in AstrBot, AstrBot generates a unique Webhook callback URL. You can find it under `Data & Logs → Logs`, or select the bot in `Platforms` and click `View Webhook URL`. Use that URL as the request URL. diff --git a/docs/en/platform/qqofficial/websockets.md b/docs/en/platform/qqofficial/websockets.md index 7aed3d3b39..7324ba8e26 100644 --- a/docs/en/platform/qqofficial/websockets.md +++ b/docs/en/platform/qqofficial/websockets.md @@ -18,7 +18,7 @@ Proactive message push: Supported. ### Setup Flow -1. In AstrBot WebUI, click `Bots` in the left sidebar, then click `+ Create Bot`. +1. In AstrBot WebUI, click `Platforms` in the left sidebar, then click `Add Adapter`. 2. Select `QQ Official Bot (WebSocket)`. 3. Under `Choose setup method`, select `One-click QR setup`, click start, then scan the QR code with mobile QQ. 4. After you confirm the QR binding, AstrBot automatically fills in `AppID` and `AppSecret`. Make sure `Enable` is checked, then click `Save`. @@ -82,8 +82,8 @@ Open `Development -> Development Settings`, find IP whitelist, and add your serv ### Configure in AstrBot 1. Open AstrBot Dashboard. -2. Click `Bots` in the left sidebar. -3. Click `+ Create Bot`. +2. Click `Platforms` in the left sidebar. +3. Click `Add Adapter`. 4. Select `qq_official`. Recommended: use `One-click QR setup`. diff --git a/docs/en/platform/satori/guide.md b/docs/en/platform/satori/guide.md index 7c9b0b044a..26895eafb2 100644 --- a/docs/en/platform/satori/guide.md +++ b/docs/en/platform/satori/guide.md @@ -17,8 +17,8 @@ Please refer to the deployment documentation of the chosen implementation projec ## 2. Configure Satori protocol in AstrBot 1. Open AstrBot WebUI. -2. Click `Bots` in the left sidebar. -3. In the right panel, click `+ Create Bot`. +2. Click `Platforms` in the left sidebar. +3. Click `Add Adapter` above the bot list. 4. Select `satori`. Fill in the form: diff --git a/docs/en/platform/satori/server-satori.md b/docs/en/platform/satori/server-satori.md index bcf5beeafd..33e37c7190 100644 --- a/docs/en/platform/satori/server-satori.md +++ b/docs/en/platform/satori/server-satori.md @@ -25,8 +25,8 @@ After enabling, `server-satori` serves Satori API under `/satori`. ## Configure Satori Adapter in AstrBot 1. Open AstrBot Dashboard. -2. Click `Bots`. -3. Click `+ Create Bot`. +2. Click `Platforms`. +3. Click `Add Adapter`. 4. Select `satori`. Fill in: diff --git a/docs/en/platform/slack.md b/docs/en/platform/slack.md index 28b6b0f883..63b245c3a5 100644 --- a/docs/en/platform/slack.md +++ b/docs/en/platform/slack.md @@ -2,7 +2,7 @@ ## Create AstrBot Slack Platform Adapter -Navigate to the `Bots` page, click `+ Create Bot`, find Slack and click to enter the Slack configuration page. +Navigate to the `Platforms` page, click `Add Adapter`, find Slack and click to enter the Slack configuration page. ![image](https://files.astrbot.app/docs/source/images/slack/image-1.png) @@ -64,9 +64,7 @@ After successfully creating the platform adapter, return to the Slack settings. If you're using Webhook mode: -- If `Unified Webhook Mode` is enabled, after clicking save, AstrBot will automatically generate a unique Webhook callback URL for you. You can find it in the logs or on the bot card in the WebUI's Bots page. Enter this URL in the `Request URL` field. - -![unified_webhook](https://files.astrbot.app/docs/source/images/use/unified-webhook.png) +- If `Unified Webhook Mode` is enabled, after clicking save, AstrBot will automatically generate a unique Webhook callback URL for you. You can find it under `Data & Logs → Logs`, or select the bot in `Platforms` and click `View Webhook URL`. Enter this URL in the `Request URL` field. - If `Unified Webhook Mode` is not enabled, enter `https://your-domain/astrbot-slack-webhook/callback` in the `Request URL` field. diff --git a/docs/en/platform/start.md b/docs/en/platform/start.md index 3dbfce9176..4226729fb5 100644 --- a/docs/en/platform/start.md +++ b/docs/en/platform/start.md @@ -2,5 +2,7 @@ AstrBot supports integration with many mainstream instant messaging platforms, so you can use AstrBot on the IM platform your team already uses. -In WebUI, click **Bots** in the left sidebar to open the messaging platform integration page. -Then click **Create Bot** in the top-right corner, choose the platform you want to connect, and follow the platform-specific guide in the left sidebar of this documentation. +In WebUI, click **Platforms** in the left sidebar to open the messaging platform integration page. +Then click **Add Adapter** above the bot list, choose the platform you want to connect, and follow the platform-specific guide in the left sidebar of this documentation. + +To edit an existing bot, select it in the list, update **Connection settings**, and click **Save changes**. Use **Conversation configuration** to choose its default configuration profile or bind profiles to specific conversations. Connection status appears in the bot list; detailed logs are under **Data & Logs → Logs**. diff --git a/docs/en/platform/telegram.md b/docs/en/platform/telegram.md index 68ae143fcd..783bd37e27 100644 --- a/docs/en/platform/telegram.md +++ b/docs/en/platform/telegram.md @@ -26,8 +26,8 @@ If you need to use the bot in group chats, you must disable the bot's [Privacy m ## 2. Configure AstrBot 1. Enter the AstrBot admin panel -2. Click `Bots` in the left sidebar -3. In the interface on the right, click `+ Create Bot` +2. Click `Platforms` in the left sidebar +3. Click `Add Adapter` above the bot list 4. Select `telegram` Fill in the configuration fields that appear: @@ -36,11 +36,11 @@ Fill in the configuration fields that appear: - Enable: Check this option. - Bot Token: Your Telegram bot's `token`. -Please ensure your network environment can access Telegram. You may need to configure a proxy using `Configuration -> Other Settings -> HTTP Proxy`. +Please ensure your network environment can access Telegram. You may need to configure a proxy using `Settings → Network → Proxy & Dependency Sources → HTTP Proxy`. ## Streaming Output -The Telegram platform supports streaming output. Enable the "Streaming Output" switch in "AI Configuration" -> "Other Settings". +The Telegram platform supports streaming output. Open `Config`, select the configuration profile used by the Telegram bot, enable `Streaming Output` under `AI → Common Settings → Message Handling`, and click `Save Configuration`. ### Private Chat Streaming diff --git a/docs/en/platform/vocechat.md b/docs/en/platform/vocechat.md index bb03266df8..277e7aeb68 100644 --- a/docs/en/platform/vocechat.md +++ b/docs/en/platform/vocechat.md @@ -14,11 +14,9 @@ See deployment methods on the [VoceChat official website](https://voce.chat/en-U ## Install `astrbot_plugin_vocechat` -In AstrBot Dashboard Plugin Market, search for `astrbot_plugin_vocechat` and install it. +In AstrBot WebUI, open `Extensions → Plugins → AstrBot Plugin Market`, search for `astrbot_plugin_vocechat` and install it. -![image](https://files.astrbot.app/docs/source/images/vocechat/image.png) - -After installation, go to `Bots` -> `+ Create Bot` -> `VoceChat`. +After installation, go to `Platforms` -> `Add Adapter` -> `VoceChat`. If VoceChat is missing, restart AstrBot or verify plugin installation. Enable the adapter in the configuration dialog. diff --git a/docs/en/platform/wecom.md b/docs/en/platform/wecom.md index 486c8fab1a..9eed121a59 100644 --- a/docs/en/platform/wecom.md +++ b/docs/en/platform/wecom.md @@ -19,8 +19,8 @@ Proactive message push: Supported for WeCom Application. Not fully tested for We ## Before You Start 1. Open AstrBot Dashboard. -2. Click `Bots` in the left sidebar. -3. Click `+ Create Bot`. +2. Click `Platforms` in the left sidebar. +3. Click `Add Adapter`. 4. Select `wecom`. A configuration dialog will appear. Keep it open and continue with the steps below. @@ -46,21 +46,19 @@ A configuration dialog will appear. Keep it open and continue with the steps bel For callback URL: -- If unified mode is enabled, AstrBot generates a unique webhook callback URL after save. Copy it from logs or bot card in WebUI. +- If unified mode is enabled, AstrBot generates a unique webhook callback URL after save. Copy it from `Data & Logs → Logs`, or select the bot in `Platforms` and click `View Webhook URL`. - If unified mode is disabled, use `http://:6195/callback/command`. -![unified_webhook](https://files.astrbot.app/docs/source/images/use/unified-webhook.png) - > If unified mode is enabled, forward external requests to AstrBot port `6185`; otherwise forward to configured adapter port (default `6195`). Back in WeCom Customer Service callback settings, click `Complete`. If successful, status shows completed. -7. In `Development Configuration`, get `Secret`, edit your WeCom adapter in AstrBot, set `secret`, then save again. +7. In `Development Configuration`, get `Secret`, select your WeCom bot in AstrBot under `Platforms`, set `secret` in `Connection settings`, and click `Save changes`. > [!TIP] > Based on [#571](https://github.com/Soulter/AstrBot/issues/571), for newly registered enterprises, `corp_id` may take about 30 minutes to become valid. -Then open `Data` -> `Logs` in AstrBot, where you should see logs asking you to open a WeChat scan link. +Then open `Data & Logs` -> `Logs` in AstrBot, where you should see logs asking you to open a WeChat scan link. ```txt Please open the following link and scan with WeChat ... @@ -93,15 +91,13 @@ Open: ![image](https://files.astrbot.app/docs/source/images/wecom/image-9.png) 5. Generate `Token` and `EncodingAESKey`, fill AstrBot `token` and `encoding_aes_key`. -6. Keep `Unified Webhook Mode (unified_webhook_mode)` enabled (recommended), then click Save in AstrBot and wait for restart. +6. Keep `Unified Webhook Mode (unified_webhook_mode)` enabled (recommended), then click `Save` in the creation dialog (or `Save changes` for an existing bot) and wait for the adapter to reload. For callback URL: -- If unified mode is enabled, use the generated unique callback URL from logs or bot card. +- If unified mode is enabled, copy the generated URL from `Data & Logs → Logs`, or select the bot in `Platforms` and click `View Webhook URL`. - If unified mode is disabled, use `http://:6195/callback/command`. -![unified_webhook](https://files.astrbot.app/docs/source/images/use/unified-webhook.png) - > If unified mode is enabled, forward to port `6185`; otherwise forward to configured adapter port (default `6195`). 7. Configure trusted enterprise IP in WeCom. @@ -112,7 +108,7 @@ Add your public IP and confirm. ![image](https://files.astrbot.app/docs/source/images/wecom/image-12.png) -After AstrBot restart, return to API receive page and click save. If you see callback verification errors, re-check all required fields. +After the adapter reloads, return to API receive page and click save. If you see callback verification errors, re-check all required fields. If save succeeds, AstrBot can receive messages from WeCom. diff --git a/docs/en/platform/wecom_ai_bot.md b/docs/en/platform/wecom_ai_bot.md index 51635b4c0a..d2b0e902b2 100644 --- a/docs/en/platform/wecom_ai_bot.md +++ b/docs/en/platform/wecom_ai_bot.md @@ -30,9 +30,7 @@ Generate `Token` and `EncodingAESKey` using random generation, but do not click ## Configure AstrBot -1. Open AstrBot Dashboard, click `Messaging Platforms`, then click `+ Add Adapter`, choose `WeCom AI Bot`. - -![Add Adapter](https://files.astrbot.app/docs/source/images/wecom_ai_bot/image-2.png) +1. Open AstrBot Dashboard, click `Platforms`, then click `+ Add Adapter`, choose `WeCom AI Bot`. 2. Fill AstrBot fields with values from the WeCom AI Bot create page: @@ -46,11 +44,9 @@ Keep `Unified Webhook Mode (unified_webhook_mode)` enabled and click `Save`. 3. Return to WeCom AI Bot create page and set `URL`: -- If unified mode is enabled, AstrBot generates a unique callback URL after save. Copy it from logs or bot card in WebUI. +- If unified mode is enabled, AstrBot generates a unique callback URL after save. Copy it from `Data & Logs → Logs`, or select the bot in `Platforms` and click `View Webhook URL`. - If unified mode is disabled, use `http://IP:port/webhook/wecom-ai-bot`. -![unified_webhook](https://files.astrbot.app/docs/source/images/use/unified-webhook.png) - > It is recommended to use a domain + reverse proxy + HTTPS. You can also use [Cloudflare Tunnel](https://developers.cloudflare.com/cloudflare-one/connections/connect-apps/install-and-setup/tunnel-guide/). 4. Click `Create`. If successful, you will enter bot details page. diff --git a/docs/en/platform/weixin-official-account.md b/docs/en/platform/weixin-official-account.md index 2ca2783c14..3538736a27 100644 --- a/docs/en/platform/weixin-official-account.md +++ b/docs/en/platform/weixin-official-account.md @@ -5,8 +5,8 @@ AstrBot supports WeChat Official Account integration (version >= v3.5.8). After ## Before You Start 1. Open AstrBot Dashboard. -2. Click `Bots` in the left sidebar. -3. Click `+ Create Bot`. +2. Click `Platforms` in the left sidebar. +3. Click `Add Adapter`. 4. Select `weixin_official_account`. A configuration dialog will appear. Keep it open and continue. @@ -36,15 +36,13 @@ In server configuration, click modify. - `Token`: create any string with length 3-32, and fill the same value in AstrBot `token`. - `EncodingAESKey`: click random generate and fill AstrBot `encoding_aes_key`. -Keep `Unified Webhook Mode (unified_webhook_mode)` enabled (recommended), then save AstrBot config and wait for restart. +Keep `Unified Webhook Mode (unified_webhook_mode)` enabled (recommended), then click `Save` in the creation dialog (or `Save changes` for an existing bot) and wait for the adapter to reload. For `URL`: -- If unified mode is enabled, use the unique callback URL generated by AstrBot (from logs or bot card). +- If unified mode is enabled, copy the generated URL from `Data & Logs → Logs`, or select the bot in `Platforms` and click `View Webhook URL`. - If unified mode is disabled, use `http:///callback/command`. -![unified_webhook](https://files.astrbot.app/docs/source/images/use/unified-webhook.png) - > [!NOTE] > WeChat Official Account callback supports only ports 80 or 443. You usually need a domain and reverse proxy: > - Unified mode enabled: forward to AstrBot port `6185` diff --git a/docs/en/platform/weixin_oc.md b/docs/en/platform/weixin_oc.md index 1143e3b5bc..7015a624df 100644 --- a/docs/en/platform/weixin_oc.md +++ b/docs/en/platform/weixin_oc.md @@ -22,8 +22,8 @@ AstrBot supports connecting a personal WeChat account through the `Personal WeCh ## Create the Bot 1. Open AstrBot WebUI. -2. Click `Bots` in the left sidebar. -3. Click `+ Create Bot` in the upper-right corner. +2. Click `Platforms` in the left sidebar. +3. Click `Add Adapter` above the bot list. 4. Select `Personal WeChat`. 5. The login QR code is shown directly. Scan it with WeChat on your phone and confirm the login inside WeChat. 6. After login succeeds, click `Save`. @@ -57,7 +57,7 @@ After login succeeds and the bot is saved, AstrBot will automatically persist th After login succeeds, send a message from WeChat. If AstrBot replies normally, the integration is working. -You can also watch `Data` -> `Logs` in the WebUI to confirm that the adapter has completed login and started polling messages. +You can also watch `Data & Logs` -> `Logs` in the WebUI to confirm that the adapter has completed login and started polling messages. ## Media File Storage diff --git a/docs/en/providers/302ai.md b/docs/en/providers/302ai.md index 8685e3b055..50d7cd3024 100644 --- a/docs/en/providers/302ai.md +++ b/docs/en/providers/302ai.md @@ -12,10 +12,12 @@ If needed, visit [this link](https://dash.302.ai/charge) to top up your account ## Connect -Open the AstrBot dashboard → Service Providers page, click **Add Provider**, find and click `302.AI` (requires version >= 3.5.18). +In the AstrBot WebUI, open **Providers → Chat Completion**, click **Add**, and select `302.AI`. -Set an ID, fill in the API Key and model name in the dialog form, then click **Save** to complete the setup. +Enter the provider name and `API Key`, check the `API Base URL`, then click **Save and Fetch Models**. Click `+` beside the desired model and make sure it is enabled. Alternatively, click **Save Configuration**, then **Custom Model** and enter the exact model ID. Use **Test Model** beside the configured model to check availability. ## Usage +Open **Config**, select the profile to use, and go to **AI → Model**. Set **Chat Model** to the model you just added, then click **Save Configuration** at the bottom right. This setting is for AstrBot built-in AI. + Send the `/provider` command to the bot to switch to the 302.AI provider you just added. diff --git a/docs/en/providers/agent-runners/coze.md b/docs/en/providers/agent-runners/coze.md index 3ef4e8612f..5c0cf10ea5 100644 --- a/docs/en/providers/agent-runners/coze.md +++ b/docs/en/providers/agent-runners/coze.md @@ -48,18 +48,15 @@ We need to record the `bot_id` for later use. After completing all the preparation work, we can now configure Coze in AstrBot. -Go to AstrBot Admin Panel -> Service Provider -> Add Service Provider -> Coze to enter the configuration page. +In the WebUI, open **Config**, select the profile to edit, and open **AI**. Click **More actions** (`…`) beside the heading → **Change Execution Mode**, select **Coze**, read and check the reset acknowledgement, then click **Use This Mode**. Make sure **Enable AI** is on, then enter the connection settings on this page. Switching resets the current mode's configuration; see [Agent Runner](../../use/agent-runner.md). -![Coze Provider](https://files.astrbot.app/docs/source/images/coze/image_8.png) - -Fill in the API Key and bot_id you just created, then click Save. +Fill in the API Key and bot_id you just created, then click **Save Configuration**. > Other configuration notes: > > - API Base URL: Generally no modification is needed. If you are using the international version of Coze, change this to: "https://api.coze.com" > - Let Coze manage conversation history: As described. -## Select Agent Runner - -Go to the Configuration page in the left sidebar, click "Agent Execution Method", select "Coze", then select the ID of the Coze Agent Runner you just created in the new configuration options that appear below, and click "Save" in the bottom right corner to complete the configuration. +## Save the Configuration +When all fields are complete, click **Save Configuration** at the bottom right. This profile uses the selected execution mode and connection settings directly; no separate runner provider or provider ID selection is needed. diff --git a/docs/en/providers/agent-runners/dashscope.md b/docs/en/providers/agent-runners/dashscope.md index 6323824d6f..a71a2e67a9 100644 --- a/docs/en/providers/agent-runners/dashscope.md +++ b/docs/en/providers/agent-runners/dashscope.md @@ -14,7 +14,7 @@ Click to enter the application, click Publishing Channel -> API Call -> API KEY, ![alt text](https://files.astrbot.app/docs/source/images/dashscope/image-2.png) -In the WebUI, click "Model Provider" -> "Add Provider", select "Agent Runner", select "Alibaba Cloud Bailian Application", and enter the Alibaba Cloud Bailian Application configuration page. +In the WebUI, open **Config**, select the profile to edit, and open **AI**. Click **More actions** (`…`) beside the heading → **Change Execution Mode**, select **Alibaba Cloud Bailian**, read and check the reset acknowledgement, then click **Use This Mode**. Make sure **Enable AI** is on, then enter the connection settings on this page. Switching resets the current mode's configuration; see [Agent Runner](../../use/agent-runner.md). According to Alibaba Cloud Bailian Application, there are four application types: @@ -28,13 +28,13 @@ According to Alibaba Cloud Bailian Application, there are four application types Please ensure that the `Application Type` configured in AstrBot matches the application type created in Alibaba Cloud Bailian Application. -Then fill in the Application ID in `dashscope_app_id` and the API KEY in `dashscope_api_key`. +Then fill in the Application ID in `Application ID` and the API KEY in `API Key`. -After filling in these three items, click Save. +After filling in these three items, click **Save Configuration**. -## Select Agent Runner +## Save the Configuration -Go to the Configuration page in the left sidebar, click "Agent Execution Method", select "Alibaba Cloud Bailian Application", then select the ID of the Alibaba Cloud Bailian Application Agent Runner you just created in the new configuration options that appear below, and click "Save" in the bottom right corner to complete the configuration. +When all fields are complete, click **Save Configuration** at the bottom right. This profile uses the selected execution mode and connection settings directly; no separate runner provider or provider ID selection is needed. ## Appendix: Dynamically Set Workflow Input Variables During Chat (Optional) @@ -49,4 +49,3 @@ After setting variables, AstrBot will attach the variables you set in the next r Of course, you can use the `/unset` command to cancel the variables you set. For example, `/unset name` Variables are permanently valid in the current session. - diff --git a/docs/en/providers/agent-runners/deerflow.md b/docs/en/providers/agent-runners/deerflow.md index 04b6fc82f5..332885793a 100644 --- a/docs/en/providers/agent-runners/deerflow.md +++ b/docs/en/providers/agent-runners/deerflow.md @@ -18,30 +18,30 @@ Make sure DeerFlow is running properly and that AstrBot can reach the DeerFlow g ## Configure DeerFlow in AstrBot -In the WebUI, click "Model Provider" -> "Add Provider", select "Agent Runner", select "DeerFlow", and enter the DeerFlow configuration page. +In the WebUI, open **Config**, select the profile to edit, and open **AI**. Click **More actions** (`…`) beside the heading → **Change Execution Mode**, select **DeerFlow**, read and check the reset acknowledgement, then click **Use This Mode**. Make sure **Enable AI** is on, then enter the connection settings on this page. Switching resets the current mode's configuration; see [Agent Runner](../../use/agent-runner.md). Fill in the following fields: - `API Base URL`: DeerFlow API gateway URL. Default: `http://127.0.0.1:2026` -- `DeerFlow API Key`: Optional. Fill this if your DeerFlow gateway is protected by Bearer auth -- `Authorization Header`: Optional. Custom Authorization header value. This takes precedence over `DeerFlow API Key` +- `API Key`: Optional. Fill this if your DeerFlow gateway is protected by Bearer auth +- `Authorization Header`: Optional. Custom Authorization header value. This takes precedence over `API Key` - `Assistant ID`: Maps to LangGraph `assistant_id`. Default: `lead_agent` -- `Model name override`: Optional. Overrides the default model configured in DeerFlow -- `Enable thinking mode`: Whether to enable DeerFlow thinking mode -- `Enable plan mode`: Maps to DeerFlow `is_plan_mode` -- `Enable subagent`: Maps to DeerFlow `subagent_enabled` -- `Max concurrent subagents`: Maps to `max_concurrent_subagents`. Effective only when subagents are enabled. Default: `3` -- `Recursion limit`: Maps to LangGraph `recursion_limit`. Default: `1000` +- `Model Name Override`: Optional. Overrides the default model configured in DeerFlow +- `Enable Thinking Mode`: Whether to enable DeerFlow thinking mode +- `Enable Plan Mode`: Maps to DeerFlow `is_plan_mode` +- `Enable Subagents`: Maps to DeerFlow `subagent_enabled` +- `Maximum Concurrent Subagents`: Maps to `max_concurrent_subagents`. Effective only when subagents are enabled. Default: `3` +- `Recursion Limit`: Maps to LangGraph `recursion_limit`. Default: `1000` -After filling in the configuration, click Save. +After filling in the configuration, click **Save Configuration**. > [!TIP] -> - If DeerFlow already has a default model configured on its side, you can leave `Model name override` empty. +> - If DeerFlow already has a default model configured on its side, you can leave `Model Name Override` empty. > - Only enable `plan mode` or `subagent` related options when the corresponding DeerFlow capabilities are already configured on the DeerFlow side. -## Select Agent Runner +## Save the Configuration -Go to the Configuration page in the left sidebar, click "Agent Execution Method", select "DeerFlow", then select the ID of the DeerFlow Agent Runner you just created in the new configuration option below, and click "Save" in the bottom right corner to complete the configuration. +When all fields are complete, click **Save Configuration** at the bottom right. This profile uses the selected execution mode and connection settings directly; no separate runner provider or provider ID selection is needed. ## Common Checks diff --git a/docs/en/providers/agent-runners/dify.md b/docs/en/providers/agent-runners/dify.md index 8b17143a6b..1d2be96145 100644 --- a/docs/en/providers/agent-runners/dify.md +++ b/docs/en/providers/agent-runners/dify.md @@ -6,15 +6,14 @@ If you haven't installed Dify yet, please refer to the [Dify Installation Docume ## Configure Dify in AstrBot -In the WebUI, click "Model Provider" -> "Add Provider", select "Agent Runner", select "Dify", and enter the Dify configuration page. +In the WebUI, open **Config**, select the profile to edit, and open **AI**. Click **More actions** (`…`) beside the heading → **Change Execution Mode**, select **Dify**, read and check the reset acknowledgement, then click **Use This Mode**. Make sure **Enable AI** is on, then enter the connection settings on this page. Switching resets the current mode's configuration; see [Agent Runner](../../use/agent-runner.md). -![image](https://files.astrbot.app/docs/source/images/dify/image.png) +In Dify, one `API Key` uniquely corresponds to one Dify application. Therefore, you can configure different API keys in separate profiles to connect multiple Dify applications. -In Dify, one `API Key` uniquely corresponds to one Dify application. Therefore, you can create multiple Providers to adapt to multiple Dify applications. - -According to the current Dify project, there are three types: +AstrBot provides these **Application Type** options: - chat +- chatflow - agent - workflow @@ -22,7 +21,6 @@ According to the current Dify project, there are three types: >Please ensure that the APP type you set in AstrBot matches the application type created in Dify. >![image](https://files.astrbot.app/docs/source/images/dify/image-3.png) - ### Chat and Agent Applications Create your Dify Chat and Agent application keys as shown in the figure below: @@ -31,7 +29,7 @@ Create your Dify Chat and Agent application keys as shown in the figure below: ![image](https://files.astrbot.app/docs/source/images/dify/chat-agent-api-key-2.png) -Copy the key and paste it into the `API Key` field in the configuration, then click "Save". +Copy the key and paste it into the `API Key` field in the configuration, then click **Save Configuration**. ### Workflow Applications @@ -46,11 +44,11 @@ For Workflow applications, AstrBot will attach two variables with each request: - `astrbot_text_query`: Input variable name. This is the text content entered by the user. - `astrbot_session_id`: Session ID -You can customize the input variable name in the configuration, which is the "Prompt Input Variable Name" shown in the figure above. +You can customize the input variable name in the configuration, which is the **Prompt Input Variable** field in the Dify settings. You need to modify the input variable name of your Workflow to adapt to AstrBot's input. -Finally, the Workflow will output a result. You can customize the variable name of this result, which is the "Dify Workflow Output Variable Name" in the configuration above, with a default value of `astrbot_wf_output`. You need to configure this variable name in the output node of the Dify Workflow, otherwise AstrBot cannot parse it correctly. +Finally, the Workflow will output a result. You can customize the variable name of this result, which is the **Workflow Output Variable** field in the Dify settings, with a default value of `astrbot_wf_output`. You need to configure this variable name in the output node of the Dify Workflow, otherwise AstrBot cannot parse it correctly. #### Create API Key @@ -60,11 +58,11 @@ Click the Publish button in the upper right corner -> Access API -> click API Ke ![image](https://files.astrbot.app/docs/source/images/dify/workflow-api-key.png) -Copy the key and paste it into the `API Key` field in the configuration, then click "Save". +Copy the key and paste it into the `API Key` field in the configuration, then click **Save Configuration**. -### Select Agent Runner +## Save the Configuration -Go to the Configuration page in the left sidebar, click "Agent Execution Method", select "Dify", then select the ID of the Dify Agent Runner you just created in the new configuration options that appear below, and click "Save" in the bottom right corner to complete the configuration. +When all fields are complete, click **Save Configuration** at the bottom right. This profile uses the selected execution mode and connection settings directly; no separate runner provider or provider ID selection is needed. ## Appendix: Dynamically Set Workflow Input Variables During Chat (Optional) @@ -79,4 +77,3 @@ After setting variables, AstrBot will attach the variables you set in the next r Of course, you can use the `/unset` command to cancel the variables you set. Variables are permanently valid in the current session. - diff --git a/docs/en/providers/aihubmix.md b/docs/en/providers/aihubmix.md index 535f629298..48aa13510d 100644 --- a/docs/en/providers/aihubmix.md +++ b/docs/en/providers/aihubmix.md @@ -13,7 +13,7 @@ Fully compatible with the OpenAI API format — just change the API Base and Key ## Configure in AstrBot -Open the AstrBot dashboard , click **Providers → Add Provider → OpenAI**. +Open the AstrBot dashboard , click **Providers → Chat Completion → Add → OpenAI Compatible**. Fill in the following: @@ -22,9 +22,7 @@ Fill in the following: | API Base URL | `https://aihubmix.com/v1` | | API Key | Your AIHubMix key | -After saving, click the provider card to add models. - -![Configure in AstrBot](https://github.com/user-attachments/assets/ee2fb8ba-652c-4e97-a781-42a9082ad7eb) +Enter the provider name and `API Key`, check the `API Base URL`, then click **Save and Fetch Models**. Click `+` beside the desired model and make sure it is enabled. Alternatively, click **Save Configuration**, then **Custom Model** and enter the exact model ID. Use **Test Model** beside the configured model to check availability. ## Recommended Models @@ -58,13 +56,13 @@ AIHubMix also supports the following capabilities, all configurable in AstrBot: | Capability | AstrBot Config Location | |------------|------------------------| -| Speech-to-Text (STT) | Providers → Speech to Text | -| Text-to-Speech (TTS) | Providers → Text to Speech | -| Embedding | Providers → Embedding | -| Reranking | Providers → Rerank | +| Speech-to-Text (STT) | Providers → Speech to Text → Add | +| Text-to-Speech (TTS) | Providers → Text to Speech → Add | +| Embedding | Providers → Embedding → Add | +| Reranking | Providers → Rerank → Add | -All capabilities use the same API Key and API Base — no extra setup needed. +Add a provider and select a model separately in each capability tab. You can reuse the API key; configure the endpoint and other fields for the corresponding API. ## Set as Default -Go to **Settings → Provider Settings**, set "Default Chat Model Provider" to your AIHubMix provider, and save. +Open **Config**, select the profile to use, and go to **AI → Model**. Set **Chat Model** to the model you just added, then click **Save Configuration** at the bottom right. This setting is for AstrBot built-in AI. diff --git a/docs/en/providers/coze.md b/docs/en/providers/coze.md index 942b6c9648..418a082c2b 100644 --- a/docs/en/providers/coze.md +++ b/docs/en/providers/coze.md @@ -1 +1 @@ -This page is deprecated. Please refer to [Coze Agent Runner](../agent-runners/coze.md). +This page is deprecated. Please refer to [Coze Agent Runner](./agent-runners/coze.md). diff --git a/docs/en/providers/dashscope.md b/docs/en/providers/dashscope.md index a2d2443ca8..027cbb4eab 100644 --- a/docs/en/providers/dashscope.md +++ b/docs/en/providers/dashscope.md @@ -1 +1 @@ -This page is deprecated. Please refer to [Alibaba Cloud Bailian Application Agent Runner](../agent-runners/dashscope.md). +This page is deprecated. Please refer to [Alibaba Cloud Bailian Application Agent Runner](./agent-runners/dashscope.md). diff --git a/docs/en/providers/dify.md b/docs/en/providers/dify.md index de0f902454..4474d48761 100644 --- a/docs/en/providers/dify.md +++ b/docs/en/providers/dify.md @@ -1 +1 @@ -This page is deprecated. Please refer to [Dify Agent Runner](../agent-runners/dify.md). +This page is deprecated. Please refer to [Dify Agent Runner](./agent-runners/dify.md). diff --git a/docs/en/providers/llm.md b/docs/en/providers/llm.md index 80f1a1fc82..f6a6972425 100644 --- a/docs/en/providers/llm.md +++ b/docs/en/providers/llm.md @@ -1,13 +1,11 @@ -# 大语言模型提供商 +# Large Language Model Providers -你可在管理面板->服务提供商->+新增服务提供商 处配置各种大语言模型服务。 +In the WebUI, open **Providers → Chat Completion**, click **Add**, and select a provider type. For an OpenAI-compatible service, select `OpenAI Compatible` and enter the API Base URL and API key supplied by that service. -> [!TIP] -> 如果没有你希望接入的模型服务,你可以试着查看您希望接入的服务提供商处是否支持 兼容 OpenAI API,如果支持,那么你可以选择上面截图中的第一项 `OpenAI` 然后通过修改 API Base URL 的方式接入。 +Enter the provider name and `API Key`, check the `API Base URL`, then click **Save and Fetch Models**. Click `+` beside the desired model and make sure it is enabled. Alternatively, click **Save Configuration**, then **Custom Model** and enter the exact model ID. Use **Test Model** beside the configured model to check availability. -![image](https://files.astrbot.app/docs/source/images/llm/image.png) +Open **Config**, select the profile to use, and go to **AI → Model**. Set **Chat Model** to the model you just added, then click **Save Configuration** at the bottom right. This setting is for AstrBot built-in AI. -![image](https://files.astrbot.app/docs/source/images/llm/image-1.png) +See [Connecting Model Services](./start.md) for detailed steps. - -> 相应的配置保存在 `data/cmd_config.json` 的 `provider` 字段中。 \ No newline at end of file +> Provider connection settings are stored in `provider_sources` in `data/cmd_config.json`; individual model configurations are stored in `provider`. diff --git a/docs/en/providers/mirarouter.md b/docs/en/providers/mirarouter.md index fee9fff1ec..ceacf08223 100644 --- a/docs/en/providers/mirarouter.md +++ b/docs/en/providers/mirarouter.md @@ -9,7 +9,7 @@ ## Configure AstrBot -Open the AstrBot dashboard and go to **Providers → Add Provider → MiraRouter**. Enter the following values: +Open the AstrBot dashboard and go to **Providers → Chat Completion → Add → MiraRouter**. Enter the following values: | Field | Value | | --- | --- | @@ -19,10 +19,10 @@ Open the AstrBot dashboard and go to **Providers → Add Provider → MiraRouter AstrBot automatically adds the `X-APP-CODE: astrbot` identifier to MiraRouter requests. -Save the provider, then open its card and add the models you want to use from the [MiraRouter models and pricing](https://mirarouter.com/models) page. +Enter the provider name and `API Key`, check the `API Base URL`, then click **Save and Fetch Models**. Click `+` beside the desired model and make sure it is enabled. Alternatively, click **Save Configuration**, then **Custom Model** and enter the exact model ID. Use **Test Model** beside the configured model to check availability. ## Set as Default -Go to **Settings → Provider Settings**, select the MiraRouter model you just added as the default chat model, and save the configuration. +Open **Config**, select the profile to use, and go to **AI → Model**. Set **Chat Model** to the model you just added, then click **Save Configuration** at the bottom right. This setting is for AstrBot built-in AI. For more details, see the [MiraRouter documentation](https://docs.mirarouter.com/). diff --git a/docs/en/providers/newapi.md b/docs/en/providers/newapi.md index 2fa55e9067..fd96c824c6 100644 --- a/docs/en/providers/newapi.md +++ b/docs/en/providers/newapi.md @@ -18,23 +18,19 @@ After creation, copy the generated API key. ### 2. Configure NewAPI in AstrBot -Open AstrBot WebUI, go to `Service Providers`, and click `Add Provider`. +Open **Providers → Chat Completion** in the AstrBot WebUI and click **Add**. -NewAPI fully supports OpenAI Chat Completion and Responses APIs, so select `OpenAI` and open its provider configuration. +NewAPI fully supports OpenAI Chat Completion and Responses APIs, so select `OpenAI Compatible` (Chat Completion) or `OpenAI Responses` and open its provider settings. Set `API Base URL` to your NewAPI endpoint: - Self-hosted NewAPI example: `http://localhost:3000/v1` - Hosted service example: `https://api.example.com/v1` -Then paste your API key into `API Key` and click `Save`. - -![astrbot-provider-config](https://files.astrbot.app/docs/source/images/newapi/image-2.png) +Enter the provider name and `API Key`, check the `API Base URL`, then click **Save and Fetch Models**. Click `+` beside the desired model and make sure it is enabled. Alternatively, click **Save Configuration**, then **Custom Model** and enter the exact model ID. Use **Test Model** beside the configured model to check availability. ### 3. Apply the Provider -Go to `Configuration`, find the model section, set `Default Chat Model` to the NewAPI-based provider you just created, and click `Save`. - -![apply](https://files.astrbot.app/docs/source/images/newapi/image-3.png) +Open **Config**, select the profile to use, and go to **AI → Model**. Set **Chat Model** to the model you just added, then click **Save Configuration** at the bottom right. This setting is for AstrBot built-in AI. You have now successfully configured NewAPI as an AstrBot model provider. diff --git a/docs/en/providers/ppio.md b/docs/en/providers/ppio.md index 3812dc86b2..2330c73d1e 100644 --- a/docs/en/providers/ppio.md +++ b/docs/en/providers/ppio.md @@ -14,20 +14,14 @@ Once you find the model, click its card to expand a detail panel on the right. S ![image](https://files.astrbot.app/docs/source/images/ppio/image-3.png) -Open the AstrBot dashboard → Service Providers page, click **Add Provider**, find and click `PPIO Cloud` (requires version >= 3.5.10; older versions are also supported, see below). +In the AstrBot WebUI, open **Providers → Chat Completion**, click **Add**, and select `PPIO`. -![image](https://files.astrbot.app/docs/source/images/ppio/image.png) - -Fill in the API Key and model name in the dialog form, then click **Save** to complete the setup. - -> [!TIP] -> If you are using an older version of AstrBot (< 3.5.10), open the AstrBot dashboard → Service Providers page, click **Add Provider**, find `OpenAI`, and click to enter. -> 1. Set the ID to `ppio` (any name works) -> 2. Set `API Base URL` to `https://api.ppinfra.com/v3/openai` -> 3. Fill in the API Key and model name in the dialog form, then click **Save** to complete the setup. +Enter the provider name and `API Key`, check the `API Base URL`, then click **Save and Fetch Models**. Click `+` beside the desired model and make sure it is enabled. Alternatively, click **Save Configuration**, then **Custom Model** and enter the exact model ID. Use **Test Model** beside the configured model to check availability. ## Usage +Open **Config**, select the profile to use, and go to **AI → Model**. Set **Chat Model** to the model you just added, then click **Save Configuration** at the bottom right. This setting is for AstrBot built-in AI. + Send the `/provider` command to the bot to switch to the PPIO Cloud provider you just added. ## FAQ diff --git a/docs/en/providers/provider-lmstudio.md b/docs/en/providers/provider-lmstudio.md index 4c0d99a7c3..78761ba06f 100644 --- a/docs/en/providers/provider-lmstudio.md +++ b/docs/en/providers/provider-lmstudio.md @@ -20,7 +20,7 @@ lms get deepseek-r1-qwen-7b In AstrBot: -Go to **Configuration → Service Providers → + → OpenAI** +Open **Providers → Chat Completion**, click **Add**, and select `LM Studio`. Set `API Base URL` to `http://localhost:1234/v1` @@ -32,6 +32,8 @@ Set `API Key` to `lm-studio` If LM Studio itself is deployed in Docker, ensure port 1234 is mapped to the host. -Set the model name to the one you selected in the previous step, then save the configuration. +Enter the provider name and check the `API Base URL`. The template pre-fills `API Key` with `lmstudio`; replace it if your server requires a different key. Click **Save and Fetch Models**. Click `+` beside the desired model and make sure it is enabled. Alternatively, click **Save Configuration**, then **Custom Model** and enter the exact model ID. Use **Test Model** beside the configured model to check availability. + +Open **Config**, select the profile to use, and go to **AI → Model**. Set **Chat Model** to the model you just added, then click **Save Configuration** at the bottom right. This setting is for AstrBot built-in AI. > Run `/provider` to view the models configured in AstrBot. diff --git a/docs/en/providers/provider-ollama.md b/docs/en/providers/provider-ollama.md index b3fc172cef..dfee5fde8e 100644 --- a/docs/en/providers/provider-ollama.md +++ b/docs/en/providers/provider-ollama.md @@ -21,10 +21,11 @@ Then use `ollama run ` to run the model. ## Configure AstrBot -Open the AstrBot WebUI, locate Service Provider Management, click on Add Provider, find and click on `Ollama`. -![image](https://files.astrbot.app/docs/source/images/ollama/image.png) +Open **Providers → Chat Completion**, click **Add**, and select `Ollama`. The default API endpoint is `http://127.0.0.1:11434/v1`; adjust it to match your deployment. -Save the configuration. +Enter the provider name and check the `API Base URL`. The template pre-fills `API Key` with `ollama`; replace it if your server requires a different key. Click **Save and Fetch Models**. Click `+` beside the desired model and make sure it is enabled. Alternatively, click **Save Configuration**, then **Custom Model** and enter the exact model ID. Use **Test Model** beside the configured model to check availability. + +Open **Config**, select the profile to use, and go to **AI → Model**. Set **Chat Model** to the model you just added, then click **Save Configuration** at the bottom right. This setting is for AstrBot built-in AI. ::: tip diff --git a/docs/en/providers/shengsuanyun.md b/docs/en/providers/shengsuanyun.md index a79f95cd9f..db8f6a40a9 100644 --- a/docs/en/providers/shengsuanyun.md +++ b/docs/en/providers/shengsuanyun.md @@ -9,7 +9,7 @@ ## Configure AstrBot -Open the AstrBot dashboard and go to **Providers → Add Provider → OpenAI**. Enter the following values: +Open the AstrBot dashboard and go to **Providers → Chat Completion → Add → OpenAI Compatible**. Enter the following values: | Field | Value | | --- | --- | @@ -17,8 +17,8 @@ Open the AstrBot dashboard and go to **Providers → Add Provider → OpenAI**. | API Base URL | `https://router.shengsuanyun.com/api/v1` | | API Key | The API key created in the ShengSuanYun console | -Save the provider, then open its card and add the models you want to use from the model list in the ShengSuanYun console. +Enter the provider name and `API Key`, check the `API Base URL`, then click **Save and Fetch Models**. Click `+` beside the desired model and make sure it is enabled. Alternatively, click **Save Configuration**, then **Custom Model** and enter the exact model ID. Use **Test Model** beside the configured model to check availability. ## Set as Default -Go to **Settings → Provider Settings**, select the ShengSuanYun model you just added as the default chat model, and save the configuration. +Open **Config**, select the profile to use, and go to **AI → Model**. Set **Chat Model** to the model you just added, then click **Save Configuration** at the bottom right. This setting is for AstrBot built-in AI. diff --git a/docs/en/providers/siliconflow.md b/docs/en/providers/siliconflow.md index b986b02e35..b049e7d508 100644 --- a/docs/en/providers/siliconflow.md +++ b/docs/en/providers/siliconflow.md @@ -8,8 +8,10 @@ Navigate to the SiliconFlow [API Keys](https://cloud.siliconflow.cn/me/account/a Visit the SiliconFlow [Models page](https://cloud.siliconflow.cn/me/models) to select your desired model. Note down the model name for later use. -Open the AstrBot WebUI, click `Service Providers` in the left sidebar -> `Add Provider` -> select `SiliconFlow`. +In the AstrBot WebUI, open **Providers → Chat Completion**, click **Add**, and select `SiliconFlow`. -Paste the `API Key` and `Model Name` you obtained earlier, then click Save to complete the setup. You can click the `Refresh` button under `Service Provider Availability` to verify whether the configuration is successful. +Enter the provider name and `API Key`, check the `API Base URL`, then click **Save and Fetch Models**. Click `+` beside the desired model and make sure it is enabled. Alternatively, click **Save Configuration**, then **Custom Model** and enter the exact model ID. Use **Test Model** beside the configured model to check availability. -![Configuring Chat Model](https://files.astrbot.app/docs/source/images/siliconflow/image.png) +## Applying the Chat Model + +Open **Config**, select the profile to use, and go to **AI → Model**. Set **Chat Model** to the model you just added, then click **Save Configuration** at the bottom right. This setting is for AstrBot built-in AI. diff --git a/docs/en/providers/start.md b/docs/en/providers/start.md index 9366269618..c62b644edb 100644 --- a/docs/en/providers/start.md +++ b/docs/en/providers/start.md @@ -30,9 +30,9 @@ Using DeepSeek as an example, assuming you have registered and logged in to a De 2. Click the "API Keys" menu in the left sidebar, create a new API Key, and copy the key. 3. Click the "API Documentation" link near the bottom of the left sidebar to open the API documentation page. 4. On the API documentation page, find the section about the "OpenAI-compatible interface" and note the API Base URL, for example `https://api.deepseek.com/v1`. (If there is no `/v1`, please add `/v1`.) -5. Open the AstrBot Console -> Service Providers page, click Add Provider, find and click `OpenAI` (if the provider type you want to connect is listed, prefer clicking that type; for some providers like DeepSeek we provide optimized adapter support). Paste the API Key into the `API Key` field of the form and paste the API Base URL into the `API Base URL` field. -6. Click Get Model List, find the model you want to use, click the + button on the right, then toggle the switch that appears on the right to enable it. -7. Go to the Configuration page, find the conversational model, click the selection button on the right, choose the provider and model you just added, then click the Save Configuration button at the bottom-right of the screen. +5. Open **Providers → Chat Completion**, click **Add**, and select `DeepSeek`. For other OpenAI-compatible services, select `OpenAI Compatible`. Enter the provider name, `API Key`, and `API Base URL`. +6. Click **Save and Fetch Models**, find the desired model, click `+`, and make sure it is enabled. If the model list cannot be fetched, click **Save Configuration**, then **Custom Model** and enter the model ID. Use **Test Model** beside the model to check connectivity. +7. Open **Config**, select the profile to use, and go to **AI → Model**. Set **Chat Model** to the model you just added, then click **Save Configuration** at the bottom right. This setting is for AstrBot built-in AI. ## Using Environment Variables to Load Keys diff --git a/docs/en/providers/tokenpony.md b/docs/en/providers/tokenpony.md index 4a65ce109f..2f1081f19e 100644 --- a/docs/en/providers/tokenpony.md +++ b/docs/en/providers/tokenpony.md @@ -8,16 +8,10 @@ Navigate to the TokenPony [API Keys](https://www.tokenpony.cn/#/user/keys) page Visit the TokenPony [Models page](https://www.tokenpony.cn/#/model) to select your desired model. Note down the model name for later use. -Open the AstrBot WebUI, click `Service Providers` in the left sidebar -> `Add Provider` -> select `TokenPony` (requires version >= 4.3.3) +In the AstrBot WebUI, open **Providers → Chat Completion**, click **Add**, and select `TokenPony`. -![Configuring Chat Model](https://files.astrbot.app/docs/source/images/tokenpony/image.png) - -> If you don't see the `TokenPony` option, you can also click `Connect to OpenAI` as shown in the image and change the `API Base URL` to `https://api.tokenpony.cn/v1`. - -Paste the `API Key` and `Model Name` you obtained earlier, then click Save to complete the setup. You can click the `Refresh` button under `Service Provider Availability` to verify whether the configuration is successful. +Enter the provider name and `API Key`, check the `API Base URL`, then click **Save and Fetch Models**. Click `+` beside the desired model and make sure it is enabled. Alternatively, click **Save Configuration**, then **Custom Model** and enter the exact model ID. Use **Test Model** beside the configured model to check availability. ## Applying the Chat Model -In the AstrBot WebUI, click `Configuration` in the left sidebar, find `Default Chat Model` under AI Configuration, select the `tokenpony` (TokenPony) provider you just created, and click Save. - -![Configuring Chat Model 2](https://files.astrbot.app/docs/source/images/tokenpony/image_1.png) +Open **Config**, select the profile to use, and go to **AI → Model**. Set **Chat Model** to the model you just added, then click **Save Configuration** at the bottom right. This setting is for AstrBot built-in AI. diff --git a/docs/en/use/agent-runner.md b/docs/en/use/agent-runner.md index 95a85a92b2..83087b6f45 100644 --- a/docs/en/use/agent-runner.md +++ b/docs/en/use/agent-runner.md @@ -35,18 +35,24 @@ Platforms like Dify, Coze, Bailian Application, and DeerFlow have this loop buil ## Usage -By default, the AstrBot Built-in Agent Runner is the default runner. Using the default runner can already meet most needs, and you can use AstrBot's MCP, knowledge base, web search, and other features. +AstrBot uses its built-in AI by default. Select a chat model under **Config → AI → Model**, and configure personas, knowledge bases, and tools as needed. -If you need to use the capabilities of platforms like Dify, Coze, Bailian Application, or DeerFlow, you can create an Agent Runner and select the corresponding provider. +To connect an external application, select the execution mode and enter its connection settings directly in the current configuration profile: -## Creating an Agent Runner +1. Open **Config** in the WebUI sidebar, select the profile to edit, and open **AI**. +2. Click **More actions** (`…`) beside the AI heading, then **Change Execution Mode**. +3. Choose Dify, Coze, Alibaba Cloud Bailian, or DeerFlow, read and check the configuration reset acknowledgement, then click **Use This Mode**. +4. Make sure **Enable AI** is on. Enter the API key, application ID, API endpoint, and other settings shown for that mode. See the integration guides below for the fields. +5. Click **Save Configuration** at the bottom right to apply the changes. -![image](https://files.astrbot.app/docs/source/images/use/agent-runner/image-1.png) +> [!IMPORTANT] +> Switching modes replaces the current execution mode's settings with the new mode's defaults. Switching back requires configuring it again. To preserve the original settings, copy the profile through **Manage Configurations...** before switching. -In the WebUI, click "Model Provider" -> "Add Provider", select "Agent Runner", choose the platform or runner type you want to connect to, and fill in the relevant information. +The current WebUI does not require creating an Agent Runner under **Providers** or selecting a runner provider ID. Each profile stores its own execution mode and connection settings. Use separate profiles when different bots need different applications. -## Changing the Default Agent Runner +## Integration Guides -![image](https://files.astrbot.app/docs/source/images/use/agent-runner/image.png) - -In the WebUI, click "Configuration" -> "Agent Execution Method", change the runner type to the Agent Runner type you just created, then select `XX Agent Runner Provider ID` as the ID of the Agent Runner provider you just created, and click save. +- [Dify](../providers/agent-runners/dify.md) +- [Coze](../providers/agent-runners/coze.md) +- [Alibaba Cloud Bailian Application](../providers/agent-runners/dashscope.md) +- [DeerFlow](../providers/agent-runners/deerflow.md) diff --git a/docs/en/use/astrbot-agent-sandbox.md b/docs/en/use/astrbot-agent-sandbox.md index 31115d20de..77036813b8 100644 --- a/docs/en/use/astrbot-agent-sandbox.md +++ b/docs/en/use/astrbot-agent-sandbox.md @@ -14,7 +14,7 @@ AstrBot currently supports the following sandbox drivers: - `Shipyard Neo` (recommended) - `Shipyard` (legacy option, still supported) -In the current AstrBot console, go to **AI Settings** -> **Agent Computer Use** and select: +In the current AstrBot console, go to **Config → AI → Capabilities → Agent Computer Use** and select: - `Computer Use Runtime` = `sandbox` - `Sandbox Driver` = `Shipyard Neo` or `Shipyard` @@ -310,7 +310,7 @@ After successful deployment, Shipyard listens on `http://:8156` by de > [!TIP] > Please make sure your AstrBot version is `v4.12.0` or later. -In the AstrBot console, go to **AI Settings** -> **Agent Computer Use**. +In the AstrBot console, go to **Config → AI → Capabilities → Agent Computer Use**. 1. Set `Computer Use Runtime` to `sandbox` 2. Select `Shipyard Neo` or `Shipyard` as the sandbox driver diff --git a/docs/en/use/command.md b/docs/en/use/command.md index 10c3cc0b4a..2c8a2bd39b 100644 --- a/docs/en/use/command.md +++ b/docs/en/use/command.md @@ -46,7 +46,7 @@ In group chats, if `unique_session` is enabled, `/sid` also shows the current gr Common uses: -- Add an admin: run `/sid` to get the `UID`, then add it in WebUI under `Config -> Other Config -> Admin ID`. +- Add an admin: run `/sid` to get the `UID`, then add it in WebUI under `Config -> Platform -> General -> Administrator IDs`. - Configure allowlists: use `UMO` or group ID to control which sessions can use the bot. - Configure routing rules: use `UMO` to distinguish different platforms, groups, or private chats. @@ -137,7 +137,7 @@ With no arguments, `/provider` lists all configured Providers grouped by LLM, TT - The currently active Provider is marked with `(currently in use)` at the end. > [!NOTE] -> Reachability checks must be enabled in WebUI under `Config -> General Config -> AI Config`, expand the "More Settings" section at the bottom, and enable "Provider Reachability Check". When disabled, reachability markers are not shown and the list loads faster. +> Reachability checks must be enabled in WebUI by selecting the relevant profile in `Config`, using the search button at the top to search for `reachability_check`, enabling the setting, and saving the configuration. When disabled, reachability markers are not shown and the list loads faster. **Switching Providers:** @@ -176,4 +176,4 @@ Install or enable the `builtin_commands_extension` plugin if you need these exte Some commands require AstrBot admin permission, such as `/dashboard_update`, `/name`, `/op`, `/deop`, `/provider`, `/model`, and `/persona`. -You can use `/sid` to get a user ID, then add it in WebUI under `Config -> Other Config -> Admin ID`. +You can use `/sid` to get a user ID, then add it in WebUI under `Config -> Platform -> General -> Administrator IDs`. diff --git a/docs/en/use/computer.md b/docs/en/use/computer.md index e217e6f073..7e7d426c59 100644 --- a/docs/en/use/computer.md +++ b/docs/en/use/computer.md @@ -6,7 +6,7 @@ Computer Use controls whether an Agent can execute code, access files, run Shell In WebUI, open: -- `Config -> General Config -> Use Computer Capabilities` +- `Config -> AI -> Capabilities -> Agent Computer Use` The key option is `Computer Use Runtime`: @@ -90,7 +90,7 @@ If `Require AstrBot admin permission` is disabled, regular users behave much clo Admin IDs can be configured in: -- `Config -> Other Config -> Admin ID` +- `Config -> Platform -> General -> Administrator IDs` Users can get their own ID with `/sid`. diff --git a/docs/en/use/context-compress.md b/docs/en/use/context-compress.md index c5664e2f2c..81e5611b13 100644 --- a/docs/en/use/context-compress.md +++ b/docs/en/use/context-compress.md @@ -2,7 +2,7 @@ Starting from v4.11.0, AstrBot introduced an automatic context compression feature. -![alt text](https://files.astrbot.app/docs/source/images/context-compress/image.png) +On the `Config` page, select the profile to edit, open `AI → Advanced → Context Management Strategy`, set the compression strategy, and click `Save Configuration` at the bottom right. AstrBot automatically compresses the context when the conversation context **reaches 82% of the maximum context window length of the conversation model being used**, ensuring that as much conversation content as possible is retained without losing key information. @@ -30,11 +30,6 @@ After one round of compression, AstrBot will perform a secondary check to verify By default, when you add a model, AstrBot automatically retrieves the model's context window size from the API provided by [MODELS.DEV](https://models.dev/) based on the model's ID. However, due to the wide variety of models and the fact that some providers even modify the model IDs, AstrBot cannot automatically infer the context window size for all models you add. -You can manually set the model's context window size in the model configuration, as shown in the image below: - -![alt text](https://files.astrbot.app/docs/source/images/context-compress/image1.png) - -> [!NOTE] -> If you don't see the configuration option shown in the image above, please delete the model and re-add it. +Open `Providers → Chat Completion`, select the model's provider in the left panel, and click an added model in the model list on the right. Edit `max_context_tokens` in the model configuration and save it. When the model context window size is set to 0, AstrBot will still automatically retrieve the model's context window size from MODELS.DEV for each request. If it remains 0, context compression will not be enabled for that request. diff --git a/docs/en/use/custom-rules.md b/docs/en/use/custom-rules.md index 7545da100f..4c2850790b 100644 --- a/docs/en/use/custom-rules.md +++ b/docs/en/use/custom-rules.md @@ -7,7 +7,7 @@ Since version v4.7.0, we have refactored AstrBot's original "Session Management" You can think of custom rules as more flexible, mandatory processing rules for specified message sources, which have higher priority than configuration files. -For example, if a messaging platform originally uses the "default" configuration file, all conversations under this platform are processed according to the rules in the configuration file. If you want to apply special processing to a specific session source A, previously you would need to create a separate configuration file and bind A to it. Now, you simply need to create a custom rule in the WebUI's Custom Rules page and select message source A. You can define the following rules: +For example, if a messaging platform originally uses the "default" configuration file, all conversations under this platform are processed according to the rules in the configuration file. If you want to apply special processing to a specific session source A, previously you would need to create a separate configuration file and bind A to it. Now, you simply need to create a custom rule in the WebUI under **More Features → Custom Rules** (`/session-management`) and select message source A. You can define the following rules: 1. Whether to enable message processing for this unified message origin. If disabled, the effect is equivalent to blacklisting this unified message origin. 2. Whether to enable LLM for messages from this unified message origin. If disabled, AI capabilities will not be used. diff --git a/docs/en/use/function-calling.md b/docs/en/use/function-calling.md index 8b0fbff9b7..0ab8dc8624 100644 --- a/docs/en/use/function-calling.md +++ b/docs/en/use/function-calling.md @@ -32,7 +32,7 @@ In AstrBot, web search, todo reminders, and code interpreter tools are provided In addition to providing traditional command invocation, also offer function calling capabilities. -Tool management (enable/disable) can be done in the WebUI. +Open `Extensions → Handlers → Function Tools` (`/extension/components`) in the WebUI to view and manage tool enablement. Configure the tools available to each Persona on the `Persona` page, and manage MCP servers under `Extensions → MCP Servers`. Some models may not support function calling and will return errors such as `tool call is not supported`, `function calling is not supported`, `tool use is not supported`, etc. In most cases, AstrBot can detect these errors and automatically remove function calling tools for you. If you find that a model doesn't support function calling, you can also disable all calling tools in the WebUI and try again, or switch to a model that supports function calling. diff --git a/docs/en/use/knowledge-base.md b/docs/en/use/knowledge-base.md index 62d9b15578..1c14656176 100644 --- a/docs/en/use/knowledge-base.md +++ b/docs/en/use/knowledge-base.md @@ -8,11 +8,11 @@ ## Configuring Embedding Model -Open the service provider page, click "Add Service Provider", and select Embedding. +Open `Providers` (`/providers`), switch to the `Embedding` tab, click `Add`, and select a provider type. Currently, AstrBot supports embedding vector services compatible with OpenAI API and Gemini API. -Click on the provider card above to enter the configuration page and fill in the configuration. +Select the provider in the left panel and fill in its API endpoint, API key, model name, and other settings in the right panel. After completing the configuration, click Save. @@ -20,17 +20,15 @@ After completing the configuration, click Save. A reranker model can improve the precision of final retrieval results to some extent. -Similar to configuring the embedding model, open the service provider page, click "Add Service Provider", and select Reranker. For more information about reranker models, please refer to online resources. +Similar to configuring the embedding model, open `Providers`, switch to the `Rerank` tab, click `Add`, select a provider type, and save its configuration. ## Creating a Knowledge Base AstrBot supports multiple knowledge base management. During chat, you can **freely specify which knowledge base to use**. -Enter the knowledge base page and click "Create Knowledge Base", as shown below: +Open `Knowledge Base` (`/knowledge-base`) from the sidebar and click `Create Knowledge Base`. -![image](https://files.astrbot.app/docs/source/images/knowledge-base/image.png) - -Fill in the relevant information. In the embedding model dropdown menu, you will see the embedding model and reranker model you just created (reranker model is optional). +Fill in the name and other details. Select the embedding model under `Embedding Model` and, optionally, select a reranker in the separate `Rerank Model (Optional)` field. Then click `Create`. > [!TIP] > Once you've selected an embedding model for a knowledge base, do not modify the **model** or **vector dimension information** of that provider, as this will **seriously affect** the retrieval accuracy of the knowledge base or even **cause errors**. @@ -43,4 +41,4 @@ After creating a knowledge base, you can upload documents to it. Up to 10 files ## Using the Knowledge Base -In the configuration file, you can specify different knowledge bases for different configuration profiles. +Open `Config`, select the profile to edit, choose the knowledge bases under `AI → Capabilities → Knowledge Base`, and click `Save Configuration` at the bottom right. Each profile can use different knowledge bases. diff --git a/docs/en/use/mcp.md b/docs/en/use/mcp.md index a2b95f5622..fd6a16e283 100644 --- a/docs/en/use/mcp.md +++ b/docs/en/use/mcp.md @@ -7,17 +7,13 @@ MCP (Model Context Protocol) is a new open standard protocol for establishing se AstrBot v3.5.0 supports the MCP protocol, enabling you to add multiple MCP servers and use function tools from MCP servers. -![image](https://files.astrbot.app/docs/source/images/function-calling/image2.png) +Manage MCP servers in WebUI under `Extensions → MCP Servers` (`/extension/mcp`). ## Initial Configuration MCP servers are typically launched using `uv` or `npm`, so you need to install these two tools. -For `uv`, you can install it directly via pip. Quick installation via AstrBot WebUI: - -![image](https://files.astrbot.app/docs/en/use/image.png) - -Just enter `uv`. +For `uv`, you can install it directly via pip. In AstrBot WebUI, open `Data & Logs → Logs` (`/data/logs`), click `Install pip Package`, enter `uv`, and install it. If you're deploying AstrBot with Docker, you can also execute the following command for quick installation: @@ -90,11 +86,7 @@ If the MCP server you need requires environment variables to configure something } ``` -Configure it in the AstrBot WebUI: - -![image](https://files.astrbot.app/docs/en/use/image-2.png) - -That's it. +In AstrBot WebUI, open `Extensions → MCP Servers` and click `Add Server`. Enter a server name and paste the JSON above into `Server Configuration`. You can test the connection first; enable the option to connect after saving and click `Save` to connect. Reference links: diff --git a/docs/en/use/plugin.md b/docs/en/use/plugin.md index 194c6b4f04..9e6265385d 100644 --- a/docs/en/use/plugin.md +++ b/docs/en/use/plugin.md @@ -2,6 +2,6 @@ Starting from version `3.4.0`, AstrBot renamed plugins to `Star`. AstrBot is a highly modular project, and plugins leverage this modularity to implement various functionalities. -Use `/plugin` to view all plugins. You can also manage installed plugins in the admin panel. +Use `/plugin` to view all plugins. You can also manage installed plugins in the admin panel under `Extensions → Plugins` (`/extension/plugins`). Open `AstrBot Plugin Market` (`/extension/plugins/market`) to search for and install plugins. Skills, MCP servers, and handlers have their own tabs at the top of the Extensions workspace. If you want to develop your own plugin, see [AstrBot Plugin Development Guide](/en/dev/star/plugin-new). diff --git a/docs/en/use/proactive-agent.md b/docs/en/use/proactive-agent.md index 72ff9cb38b..9041227899 100644 --- a/docs/en/use/proactive-agent.md +++ b/docs/en/use/proactive-agent.md @@ -14,12 +14,12 @@ The Main Agent can now manage a global **Cron Job List**, setting tasks for its - **Self-Wakeup**: AstrBot automatically wakes up at the scheduled time to execute tasks. - **Task Feedback**: After execution, AstrBot reports the results back to the task creator. -- **WebUI Management**: You can view, edit, or delete scheduled tasks in the "Future Tasks" page of the WebUI. +- **WebUI Management**: You can view, edit, or delete scheduled tasks in the WebUI under **More Features → Future Tasks**. ### How to Use > [!TIP] -> First, ensure that "Proactive Capabilities" is enabled in the configuration. +> First, select the relevant profile on the `Config` page, open `AI → Capabilities → Proactive Agent`, enable the feature, and click `Save Configuration` at the bottom right. The Main Agent has the ability to manage scheduled tasks. You can tell it: - "Remind me to have a meeting at 8 AM tomorrow." @@ -28,7 +28,7 @@ The Main Agent has the ability to manage scheduled tasks. You can tell it: The Main Agent will call built-in scheduling tools to arrange these plans. -You can view and manage all future tasks by clicking **Future Tasks** in the left navigation bar of the AstrBot WebUI. +You can view and manage all future tasks by expanding **More Features** in the left navigation bar and clicking **Future Tasks** (`/cron`) of the AstrBot WebUI. ![](https://files.astrbot.app/docs/source/images/proactive-agent/image-1.png) diff --git a/docs/en/use/skills.md b/docs/en/use/skills.md index b2fc0d534e..8a6ba6fd98 100644 --- a/docs/en/use/skills.md +++ b/docs/en/use/skills.md @@ -12,9 +12,7 @@ Support for Anthropic Skills was introduced in AstrBot starting from v4.13.0, al ## Uploading Skills to AstrBot -Open the AstrBot admin panel, navigate to the `Plugins` page, and find `Skills`. - -![Skills](https://files.astrbot.app/docs/source/images/skills/image.png) +Open the AstrBot admin panel, go to `Extensions → Skills` (`/extension/skills`), and click `Upload Skills`. You can upload Skills with the following requirements: @@ -55,7 +53,7 @@ Currently, AstrBot provides two execution environments: - Local — The Agent runs in your AstrBot runtime environment. **Use with caution: this allows the Agent to execute arbitrary code in your environment, which may pose security risks.** - Sandbox — The Agent runs inside an isolated sandbox environment. **You must enable AstrBot sandbox mode first.** See: /use/astrbot-agent-sandbox. If sandbox mode is not enabled, Skills will not be passed to the Agent. -You can select the default execution environment on the `Config` page under "Computer Use". +On the `Config` page, select the profile to edit, open `AI → Capabilities → Agent Computer Use`, choose the execution environment, and click `Save Configuration` at the bottom right. > [!NOTE] > Please note: if you select `Local` as the execution environment, AstrBot currently only allows **AstrBot administrators** to request that the Agent operate on your local environment. Regular users are prohibited from doing so. The Agent will be prevented from executing code locally via Shell, Python, or other tools and will receive a permission restriction message such as `Sorry, I cannot execute code on your local environment due to permission restrictions.`. diff --git a/docs/en/use/subagent.md b/docs/en/use/subagent.md index da6e5a728f..ceff46a0ff 100644 --- a/docs/en/use/subagent.md +++ b/docs/en/use/subagent.md @@ -13,11 +13,11 @@ In traditional architectures, all tools are directly mounted on the Main Agent. 2. **Execution Errors**: With a large number of tools, the LLM may confuse tool purposes or generate incorrect parameters. 3. **Complexity**: The Main Agent is overburdened with both conversation and the organization/invocation of numerous tools. -With SubAgent Orchestration, the Main Agent is only responsible for user interaction and **task delegation**. Actual tool execution is handled by specialized SubAgents. +With SubAgent Orchestration, the Main Agent can interact with users, use its own tools, and delegate tasks to specialized SubAgents. ## How It Works -1. **Main Agent Delegation**: When SubAgent mode is enabled, the Main Agent only sees a series of delegation tools named `transfer_to_`. +1. **Main Agent Delegation**: When SubAgent mode is enabled, the Main Agent gains delegation tools named `transfer_to_` alongside its own tools. Enabling the option to deduplicate Main LLM tools hides tools that overlap with those of SubAgents. 2. **Task Handoff**: When the Main Agent determines a task needs execution, it calls the corresponding delegation tool, passing the task description to the SubAgent. 3. **SubAgent Execution**: The SubAgent receives the task, performs operations using its assigned tools, and returns the organized results to the Main Agent. 4. **Feedback**: The Main Agent receives the results and continues the conversation with the user. @@ -26,7 +26,7 @@ With SubAgent Orchestration, the Main Agent is only responsible for user interac ## Configuration -In the AstrBot WebUI, click **SubAgents** in the left navigation bar. +In the AstrBot WebUI, expand **More Features** in the left navigation bar and click **SubAgents** (`/subagent`). ### 1. Enable SubAgent Mode @@ -37,11 +37,13 @@ Toggle "Enable SubAgent Orchestration" at the top of the page. Click the "Add SubAgent" button: - **Agent Name**: Used to generate the delegation tool name (e.g., `transfer_to_weather`). Use lowercase and underscores. -- **Select Persona**: Choose a preset Persona, which defines the SubAgent's basic character, behavioral guidance, and the Tools collection it can use. You can create and manage Personas on the "Persona Settings" page. +- **Select Persona**: Choose a preset Persona, which defines the SubAgent's basic character, behavioral guidance, and the Tools collection it can use. You can create and manage Personas on the "Persona" page. - **Description for Main LLM**: This description tells the Main Agent what this SubAgent is good at, ensuring accurate delegation. -- **Assign Tools**: Select the tools this SubAgent can invoke. +- **Tools**: The SubAgent inherits its selected Persona’s tools. Edit the Persona’s tool selection on the **Persona** page. - **Provider Override (Optional)**: You can specify different model providers for specific SubAgents. For example, the Main Agent could use GPT-4o, while a simple query SubAgent uses GPT-4o-mini to save costs. +After configuring the agents, click `Save` on the page. + ## Best Practices - **Single Responsibility**: Each SubAgent should handle one category of related tasks (e.g., search, file processing, smart home control). diff --git a/docs/en/use/unified-webhook.md b/docs/en/use/unified-webhook.md index 63bdbff73a..d0c2279acc 100644 --- a/docs/en/use/unified-webhook.md +++ b/docs/en/use/unified-webhook.md @@ -17,7 +17,7 @@ Platform adapters that support Unified Webhook Mode include: 1. Have a domain (e.g., example.com) and a server with a public IP 2. Configure DNS resolution (e.g., astrbot.example.com) 3. Configure reverse proxy to forward requests from port 80 or 443 of your domain to AstrBot's WebUI port (default is 6185) -4. Go to AstrBot's `Configuration` page, click `System`, and set the `Externally Reachable Callback URL` to your configured URL (e.g., https://astrbot.example.com). Click save and wait for restart. +4. Go to AstrBot's `Settings → General → Runtime Basics` and set the `Externally Reachable Callback URL` to your configured URL (e.g., https://astrbot.example.com). Click save and wait for restart. When configuring each platform adapter afterwards, enable `Unified Webhook Mode (unified_webhook_mode)`. diff --git a/docs/en/use/websearch.md b/docs/en/use/websearch.md index 503de95df0..9125c98faa 100644 --- a/docs/en/use/websearch.md +++ b/docs/en/use/websearch.md @@ -16,9 +16,7 @@ And other prompts with search intent to trigger the model to invoke the search t AstrBot currently supports 7 web search providers: `Tavily`, `BoCha`, `Baidu AI Search`, `Brave`, `Firecrawl`, `Exa` ,and `AnySearch`. -![image](https://files.astrbot.app/docs/source/images/websearch/image.png) - -Go to `Configuration`, scroll down to find Web Search, where you can select `Tavily`, `BoCha`, `Baidu AI Search`, `Brave`, `Firecrawl`, `Exa` ,or `AnySearch`. +Open `Config`, select the profile to edit, and enable Web Search under `AI → Capabilities → Web Search`, where you can select `Tavily`, `BoCha`, `Baidu AI Search`, `Brave`, `Firecrawl`, `Exa` ,or `AnySearch`. Fill in the required settings and click `Save Configuration` at the bottom right. ### Tavily diff --git a/docs/en/use/webui.md b/docs/en/use/webui.md index 9f7435a9f2..837e43b903 100644 --- a/docs/en/use/webui.md +++ b/docs/en/use/webui.md @@ -2,7 +2,24 @@ The AstrBot admin panel features plugin management, log viewing, visual configuration, statistics viewing, and more. -![image](https://files.astrbot.app/docs/source/images/webui/image-4.png) +## Navigation and Previous Entry Points + +These paths use the current default sidebar. If you customized it, open `Settings → Appearance → Customize Sidebar` at the bottom of the sidebar to review or reset the layout. + +| Previous entry point or name | Current entry point | +| --- | --- | +| Providers → Add Provider → Agent Runner | Config → Select a profile → AI → `…` beside the AI heading → Change execution mode | +| Data / Dashboard | Data & Logs → Statistics | +| Conversation Management / Conversations | Data & Logs → Conversations | +| Logs / Console | Data & Logs → Logs | +| Trace | Data & Logs → Trace | +| Config → Normal Config | Config → Select a profile | +| Config → System Config | Settings → General, Appearance, Network, or Security, depending on the setting | +| Commands / Command Management | Extensions → Handlers → Command | +| Standalone MCP / Skills entries | Extensions → MCP Servers / Skills | +| Custom Rules / Future Tasks / SubAgents | More Features → The corresponding feature | + +Old log, trace, conversation, and statistics URLs still redirect to the corresponding tabs. Agent runners are now saved in each profile; they are no longer created as model providers. See [Agent Runners](./agent-runner.md) for the setup steps. ## Accessing the Admin Panel @@ -21,7 +38,7 @@ AstrBot WebUI supports TOTP (Time-based One-Time Password) based two-factor auth ### Enabling Two-Factor Authentication -1. In the left menu, click Config → System Config. +1. Open `Settings → Security` at the bottom of the sidebar and find `WebUI Security`. 2. Toggle on "Enable WebUI TOTP"; a setup dialog with a QR code will appear. 3. Scan the QR code using any TOTP-compatible authenticator app (e.g., Google Authenticator, etc.). 4. Enter the 6-digit verification code generated by the authenticator app to complete the verification. @@ -59,37 +76,44 @@ ChatUI supports these common workflows: ## Visual Configuration -In the admin panel, you can configure AstrBot's plugins through visual configuration. Click `Configuration` in the left sidebar to enter the configuration page. +Select `Config` in the sidebar, then choose the profile to edit from the selector at the top. Settings are grouped into sections such as `AI`, `Platform`, and `Plugin`. Use the search control at the top to find a setting. -![image](https://files.astrbot.app/docs/source/images/webui/image-3.png) +- In `AI`, built-in AI settings have `Model`, `Persona`, `Capabilities`, and `Advanced` tabs. Use `… → Change execution mode` beside the AI heading to connect a third-party agent. +- `Platform` contains administrator and message-trigger settings. +- `Plugin` selects the plugins enabled for this profile. To edit an individual plugin's parameters, open `Extensions` and click that plugin's gear icon (`Extension Config`). -After modifying the configuration, you need to click the `Save` button in the bottom right corner to successfully save the configuration. +After editing, click the disk icon labeled `Save Configuration` in the lower-right corner and check for a successful save message. -Use the first circular button in the bottom right corner to switch to `Code Edit Configuration`. In `Code Edit Configuration`, you can directly edit the configuration file. +Use the `{}` icon labeled `Edit Configuration File` to edit the current profile as JSON. Select `Apply This Configuration` to stage the changes in the visual editor, close the editor, and then select `Save Configuration`. -After editing, first click `Apply This Configuration`, which will apply the configuration to the visual configuration, then click the `Save` button in the bottom right corner to save the configuration. If you don't click `Apply This Configuration`, your modifications won't take effect. +### System Settings -![alt text](https://files.astrbot.app/docs/source/images/webui/image-5.png) +Global settings are under `Settings` at the bottom of the sidebar: -## Plugins +- `General`: timezone, external callback address, logs, and cache. +- `Appearance`: sidebar, theme, and text-to-image rendering. +- `Network`: HTTP proxy, Python package sources, and GitHub proxy. +- `Security`: WebUI HTTPS, login rate limits, and TOTP. +- `Maintenance`: backup, restore, and restart. +- `OpenAPI`: developer access keys. -In the admin panel, you can view installed plugins and install new plugins through the `Plugins` section in the left sidebar. +System configuration changes save automatically. Check for a successful save message and restart AstrBot if the page indicates that a restart is required. -Click the Plugin Market tab to browse plugins officially listed by AstrBot. +## Plugins -![image](https://files.astrbot.app/docs/source/images/webui/image-1.png) +Select `Extensions` in the sidebar. The top tabs are `Plugins`, `Skills`, `MCP Servers`, and `Handlers`. Within `Plugins`, switch between `Installed` and `AstrBot Plugin Market` to view local and market plugins. -You can also click the + button in the bottom right corner to manually install plugins via URL or file upload. +On either plugin list, you can also click `Install Plugin` (+) in the bottom right corner to manually install plugins via URL or file upload. > Due to the plugin update mechanism, the AstrBot Team cannot fully guarantee the security of plugins in the plugin market. Please carefully verify them. The AstrBot Team is not responsible for any losses caused by plugins. ### Handling Plugin Load Failures -If a plugin fails to load, the admin panel will display the error message and provide a **"Try one-click reload fix"** button. This allows you to quickly reload the plugin after fixing the environment (e.g., installing missing dependencies) or modifying the code, without having to restart the entire application. +If a plugin fails to load, the admin panel will display the error message and provide a **"Reload"** button in the failed plugins list. This allows you to quickly reload the plugin after fixing the environment (e.g., installing missing dependencies) or modifying the code, without having to restart the entire application. -## Data +## Data & Logs {#data} -Select `Data` in the left sidebar to switch between `Statistics`, `Conversations`, `Logs`, and `Trace` from the tabs at the top of one workspace. +Select `Data & Logs` in the left sidebar to switch between `Statistics`, `Conversations`, `Logs`, and `Trace` from the tabs at the top of one workspace. ### Statistics @@ -107,7 +131,7 @@ Use the `Conversations` tab to find and manage saved conversation records: ### Logs -The `Logs` tab shows AstrBot runtime logs in real time. You can filter by log level and install missing Pip packages from this page. To view DEBUG logs, first enable the console DEBUG log level under `Config -> System Config`. +The `Logs` tab shows AstrBot runtime logs in real time. You can filter by log level and install missing Pip packages from this page. To view DEBUG logs, first set `Console Log Level` to `DEBUG` under `Settings → General → Logs`. ### Trace @@ -118,7 +142,7 @@ The `Trace` tab shows AstrBot execution traces in real time and is useful for de ## Command Management -Use the `Command Management` menu on the left to centrally manage all registered commands; system plugins are hidden by default. +Use `Extensions → Handlers → Command` to centrally manage all registered commands; system plugins are hidden by default. Filter by plugin, type (command / command group / subcommand), permission, and status, and combine with the search box for quick lookup. Command group rows can expand to show subcommands, badges display the subcommand count, and subcommand rows are indented to indicate hierarchy. @@ -128,7 +152,9 @@ You can enable/disable and rename each command. When AstrBot starts, it automatically checks if the admin panel needs updating. If it does, the first log entry (in yellow) will prompt you. -Use the `/dashboard_update` command to manually update the admin panel (admin command). +In the browser WebUI, open `⋮ → Update AstrBot` in the upper-right corner, expand `Advanced settings`, and click `Download and Update` under `Update Dashboard to Latest Version Only`. The page refreshes automatically after a successful update. In the desktop app, the update entry opens the desktop application updater. + +You can also use the `/dashboard_update` command to manually update the admin panel (admin command). Admin panel files are located in the data/dist directory. If you need to manually replace them, download `dist.zip` from https://github.com/AstrBotDevs/AstrBot/releases/ and extract it to the data directory. diff --git a/docs/zh/deploy/astrbot/compshare.md b/docs/zh/deploy/astrbot/compshare.md index 664870b123..472a83f8e9 100644 --- a/docs/zh/deploy/astrbot/compshare.md +++ b/docs/zh/deploy/astrbot/compshare.md @@ -32,11 +32,8 @@ Both services started in the background. > 可能需要等待半分钟左右。 -![WebUI 界面](https://www-s.ucloud.cn/2025/07/7e9fc6edc1dfa916abc069f4cecc24cf_1753940381771.png) - 首次登录时请使用启动日志内的随机初始密码(用户名通常是 astrbot),登录后请立即修改密码。 - 登录成功后,可以重新设置密码,并进入 AstrBot 的页面。 实例默认会导入 Ollama-DeepSeek-R1-32B 模型。 @@ -50,38 +47,34 @@ Both services started in the background. 1. 在 [Ollama](https://ollama.com/search) 模型列表找到想部署的模型。 2. 通过 SSH 进入到实例的终端(进入优云智算平台的控制台页面->实例列表->控制台指令和密码) 3. 通过 `ollama pull 模型名` 拉取模型,等待拉取成功。 -4. 在 AstrBot 面板的 服务提供商页面找到 `ollama_deepseek-r1`,点击编辑,更新模型名称,点击保存。 - -![image](https://files.astrbot.app/docs/source/images/compshare/image-1.png) +4. 在 `模型提供商 → 对话` 中选择镜像预配置的 Ollama 提供商源,点击 `获取模型列表`,在刚拉取的模型旁点击 `+` 添加。如果没有预配置的源,点击 `新增`,选择 `Ollama`,填写实例中的 Ollama 地址后点击 `保存并获取模型`。 ### 使用优云智算提供的模型 API AstrBot 支持接入优云智算提供的模型 API。 1. 在 [优云智算](https://console.compshare.cn/light-gpu/model-center) 找到想要接入的模型 -2. 在 AstrBot 面板的 服务提供商页面点击「+ 新增服务提供商」,点击优云智算(如果没有,点击“接入 OpenAI”,并且修改下一步弹出窗口的 API Base URL 为 `https://api.modelverse.cn/v1`)。在模型配置-模型名称输入模型名,点击保存。 +2. 打开 `模型提供商 → 对话 → 新增`,选择 `OpenAI Compatible`,填写优云智算的 API Key,并将 API Base URL 设为 `https://api.modelverse.cn/v1`。 +3. 点击 `保存并获取模型`,在需要的模型旁点击 `+`。如果接口未返回模型列表,先 `保存配置`,再点击 `自定义模型`,填写平台提供的完整模型 ID。 ### 测试 -在 AstrBot 面板左侧点击 `聊天`,输入 `/provider`,可以查看和切换您当前接入的提供商。 - -您可以直接聊天来测试模型是否正常。 - -![image](https://files.astrbot.app/docs/source/images/compshare/image-2.png) +在已配置的模型上点击 `测试模型`,确认连接成功。然后进入 `配置文件`,选择机器人使用的配置文件,在 `AI → 模型 → 对话模型` 中选择刚添加的模型,点击 `保存配置`。 +通过 WebUI 顶部的聊天切换按钮进入聊天,或直接向已接入消息平台的机器人发送消息,测试实际回复。 ## 接入到消息平台 -- 飞书:[接入到飞书](https://docs.astrbot.app/deploy/platform/lark.html) -- LINE:[接入到 LINE](https://docs.astrbot.app/deploy/platform/line.html) -- 钉钉:[接入到钉钉](https://docs.astrbot.app/deploy/platform/dingtalk.html) -- 企业微信:[接入到企业微信应用](https://docs.astrbot.app/deploy/platform/wecom.html) -- 微信客服:[接入到微信客服](https://docs.astrbot.app/deploy/platform/wecom.html) -- 微信公众平台:[接入到微信公众平台](https://docs.astrbot.app/deploy/platform/weixin-official-account.html) -- QQ 官方机器人平台:[接入到 QQ 机器人](https://docs.astrbot.app/deploy/platform/qqofficial/webhook.html) -- KOOK:[接入到 KOOK](https://docs.astrbot.app/deploy/platform/kook.html) -- Slack:[接入到 Slack](https://docs.astrbot.app/deploy/platform/slack.html) -- Discord:[接入到 Discord](https://docs.astrbot.app/deploy/platform/discord.html) +- 飞书:[接入到飞书](https://docs.astrbot.app/platform/lark.html) +- LINE:[接入到 LINE](https://docs.astrbot.app/platform/line.html) +- 钉钉:[接入到钉钉](https://docs.astrbot.app/platform/dingtalk.html) +- 企业微信:[接入到企业微信应用](https://docs.astrbot.app/platform/wecom.html) +- 微信客服:[接入到微信客服](https://docs.astrbot.app/platform/wecom.html) +- 微信公众平台:[接入到微信公众平台](https://docs.astrbot.app/platform/weixin-official-account.html) +- QQ 官方机器人平台:[接入到 QQ 机器人](https://docs.astrbot.app/platform/qqofficial/webhook.html) +- KOOK:[接入到 KOOK](https://docs.astrbot.app/platform/kook.html) +- Slack:[接入到 Slack](https://docs.astrbot.app/platform/slack.html) +- Discord:[接入到 Discord](https://docs.astrbot.app/platform/discord.html) - 更多接入方式参考 [AstrBot 官方文档](https://docs.astrbot.app/what-is-astrbot.html) ## 更多功能 diff --git a/docs/zh/deploy/astrbot/kubernetes.md b/docs/zh/deploy/astrbot/kubernetes.md index 6d2ed52888..2d54d2196d 100644 --- a/docs/zh/deploy/astrbot/kubernetes.md +++ b/docs/zh/deploy/astrbot/kubernetes.md @@ -73,7 +73,7 @@ kubectl apply -f k8s/astrbot_with_napcat/02-deployment.yaml 由于 AstrBot 和 NapCat 在同一个 Pod 中,它们可以通过 `localhost` 直接通信。 1. **在 AstrBot 中添加消息平台:** - * 进入 AstrBot WebUI,选择 `机器人` -> `添加`。 + * 进入 AstrBot WebUI,选择 `机器人` -> `创建机器人`。 * **选择消息平台类别**: `aiocqhttp` * **机器人名称**: `napcat` (或自定义) * **反向 Websocket 主机**: `0.0.0.0` diff --git a/docs/zh/deploy/when-deployed.md b/docs/zh/deploy/when-deployed.md index b4a17958a8..68e2afb6c7 100644 --- a/docs/zh/deploy/when-deployed.md +++ b/docs/zh/deploy/when-deployed.md @@ -21,4 +21,4 @@ AstrBot 文档:[![wakatime](https://wakatime.com/badge/user/915e5316-99c6-4563 ## 正文 -当你看到这里,说明已经成功部署好消息平台并且实现了第一条指令的收发。接下来,你可以配置大语言模型,或者添加插件。请参看 `配置-接入大模型服务` 一节。 +当你看到这里,说明已经成功部署好消息平台并且实现了第一条指令的收发。接下来,可以在 WebUI 的 `模型提供商` 中接入模型,在 `配置文件` 中选择机器人使用的对话模型,或到 `插件 → 插件市场` 安装插件。请参看[接入模型服务](../providers/start.md)和[插件](../use/plugin.md)。 diff --git a/docs/zh/dev/astrbot-config.md b/docs/zh/dev/astrbot-config.md index 4b61c00b45..d3de28775a 100644 --- a/docs/zh/dev/astrbot-config.md +++ b/docs/zh/dev/astrbot-config.md @@ -10,6 +10,8 @@ AstrBot 的配置文件是一个 JSON 格式的文件。AstrBot 会在启动时 > 在 AstrBot v4.0.0 版本及之后,我们引入了[多配置文件](https://blog.astrbot.app/posts/what-is-changed-in-4.0.0/#%E5%A4%9A%E9%85%8D%E7%BD%AE%E6%96%87%E4%BB%B6)的概念。`data/cmd_config.json` 作为默认配置文件 `default`。其他您在 WebUI 新建的配置文件会存储在 `data/config/` 目录下,以 `abconf_` 开头。 +WebUI 中,按机器人或会话使用的行为配置在 `配置文件` 页面管理;全局运行、日志、网络、WebUI 安全和文本转图像服务等配置在 `设置` 页面管理。模型连接和机器人连接分别在 `模型提供商` 和 `机器人` 页面管理。 + AstrBot 默认配置如下: ```jsonc @@ -548,7 +550,7 @@ AstrBot WebUI 配置。 ### `trace_enable` -是否启用追踪记录。默认为 `false`。启用后,AstrBot 会记录运行追踪信息,可以在管理面板的 `数据` -> `追踪` 页面查看。 +是否启用追踪记录。默认为 `false`。启用后,AstrBot 会记录运行追踪信息,可以在管理面板的 `数据与日志 → 追踪` 页面查看。 ### `pip_install_arg` diff --git a/docs/zh/dev/openapi.md b/docs/zh/dev/openapi.md index 28ded27b22..780a5669f9 100644 --- a/docs/zh/dev/openapi.md +++ b/docs/zh/dev/openapi.md @@ -8,7 +8,7 @@ outline: deep ## 快速开始 -1. 在 WebUI - 设置中创建 API Key。 +1. 在 WebUI 的 `设置 → OpenAPI` 中点击 `创建 API Key`。 2. 在请求头中携带 API Key: ```http diff --git a/docs/zh/dev/star/plugin-new.md b/docs/zh/dev/star/plugin-new.md index 690d024988..c4b09d3f57 100644 --- a/docs/zh/dev/star/plugin-new.md +++ b/docs/zh/dev/star/plugin-new.md @@ -88,7 +88,7 @@ your_plugin/ SKILL.md ``` -这种情况下 Skill 名称会使用插件目录名。插件提供的 Skill 由插件管理,在 WebUI 的 Skills 页面中作为只读来源展示;可以启用或禁用,但不能从本地 Skills 页面删除或编辑。插件卸载或更新后,对应 Skill 会随插件文件变化。 +这种情况下 Skill 名称会使用插件目录名。插件提供的 Skill 由插件管理,在 WebUI 的 `插件 → 技能` 页面中作为只读来源展示;可以启用或禁用,但不能从本地 Skills 页面删除或编辑。插件卸载或更新后,对应 Skill 会随插件文件变化。 ### 声明支持平台(Optional) @@ -149,9 +149,9 @@ AstrBot 采用在运行时注入插件的机制。因此,在调试插件时, 您可以使用 AstrBot 的热重载功能简化开发流程。 -插件的代码修改后,可以在 AstrBot WebUI 的插件管理处找到自己的插件,点击右上角 `...` 按钮,选择 `重载插件`。 +插件的代码修改后,在 AstrBot WebUI 的 `插件` 页找到自己的插件,点击插件卡片上的刷新图标(`重载插件`)。 -如果插件因为代码错误等原因加载失败,你也可以在管理面板的错误提示中点击 **“尝试一键重载修复”** 来重新加载。 +如果插件因为代码错误等原因加载失败,可以在同一页面的 `加载失败插件` 列表中点击对应插件的 `重载` 按钮。 ### 插件依赖管理 diff --git a/docs/zh/dev/star/plugin.md b/docs/zh/dev/star/plugin.md index 2be7740b8a..e4c5ef30d0 100644 --- a/docs/zh/dev/star/plugin.md +++ b/docs/zh/dev/star/plugin.md @@ -50,7 +50,7 @@ git clone 插件仓库地址 AstrBot 采用在运行时注入插件的机制。因此,在调试插件时,需要启动 AstrBot 本体。 -插件的代码修改后,可以在 AstrBot WebUI 的插件管理处找到自己的插件,点击 `管理`,点击 `重载插件` 即可。 +插件的代码修改后,在 AstrBot WebUI 的 `插件` 页找到自己的插件,点击插件卡片上的刷新图标(`重载插件`)。如果插件加载失败,可在同一页面的 `加载失败插件` 列表中点击对应插件的 `重载` 按钮。 ### 插件依赖管理 @@ -266,7 +266,7 @@ your_plugin/ SKILL.md ``` -这种情况下 Skill 名称会使用插件目录名。插件提供的 Skill 由插件管理,在 WebUI 的 Skills 页面中作为只读来源展示;可以启用或禁用,但不能从本地 Skills 页面删除或编辑。插件卸载或更新后,对应 Skill 会随插件文件变化。 +这种情况下 Skill 名称会使用插件目录名。插件提供的 Skill 由插件管理,在 WebUI 的 `插件 → 技能` 页面中作为只读来源展示;可以启用或禁用,但不能从本地 Skills 页面删除或编辑。插件卸载或更新后,对应 Skill 会随插件文件变化。 ### 声明支持平台(Optional) diff --git a/docs/zh/faq.md b/docs/zh/faq.md index d510653ceb..ecb242f79e 100644 --- a/docs/zh/faq.md +++ b/docs/zh/faq.md @@ -90,9 +90,9 @@ Set dashboard.host in data/cmd_config.json to enable remote access. ### 如何让 AstrBot 控制我的 Mac / Windows / Linux 电脑? -1. 在 AstrBot WebUI 的 `配置 -> 普通配置` 中,找到 `使用电脑能力`,运行环境选择 `local`。 -2. 在 `配置 -> 其他配置` 中,找到 `管理员 ID 列表`,添加你的用户 ID(可以通过 `/sid` 指令获取)。 -3. 右下角保存配置 +1. 在 AstrBot WebUI 的 `配置文件` 中选择机器人使用的配置文件,进入 `AI 配置 → 能力 → 使用电脑能力`,将 `运行环境` 设为 `local`。此处需要使用 AstrBot 内置 AI。 +2. 在同一配置文件的 `平台配置 → 基本 → 管理员 ID` 中添加你的用户 ID(可以通过 `/sid` 指令获取)。 +3. 点击右下角的 `保存配置` 按钮。 > [!TIP] > AstrBot 为了安全起见,运行环境选择 `local` 时,默认仅允许 AstrBot 管理员使用电脑能力。 @@ -120,7 +120,7 @@ Set dashboard.host in data/cmd_config.json to enable remote access. ### 没有权限操作管理员指令 -1. `/name, /provider, /dashboard_update, /op, /deop, /persona, /llm, /plugin, /model, /groupnew` 等是默认的管理员指令。可以通过 `/sid` 指令得到用户的 ID,然后在 `配置` -> `其他配置` 中添加到管理员 ID 名单中。 +1. `/name, /provider, /dashboard_update, /op, /deop, /persona, /llm, /plugin, /model, /groupnew` 等是默认的管理员指令。可以通过 `/sid` 指令得到用户的 ID,然后在 `配置文件` 中选择机器人使用的配置文件,在 `平台配置 → 基本 → 管理员 ID` 中添加该 ID,并点击右下角的 `保存配置`。 ### 本地渲染 Markdown 图片(t2i)时中文乱码 @@ -143,7 +143,7 @@ Set dashboard.host in data/cmd_config.json to enable remote access. ### 插件安装不上 -1. 插件通过 GitHub 安装,在国内访问 GitHub 确实有时候连不上。可以挂代理,然后进入 `其他配置` -> `HTTP 代理` 设置代理,或者直接下载插件压缩包后上传。 +1. 插件通过 GitHub 安装,在国内访问 GitHub 确实有时候连不上。可以在 `设置 → 网络 → 代理与依赖源 → HTTP 代理` 中配置代理并保存;也可以在同一页面设置 `GitHub 加速地址`,或直接下载插件压缩包后在插件页安装。 ### 安装插件后报错 `No module named 'xxx'` @@ -157,9 +157,9 @@ Set dashboard.host in data/cmd_config.json to enable remote access. 解决方法: -结合报错信息,参考插件的 README 手动安装依赖库。你可以在 AstrBot WebUI 的 `数据` -> `日志` -> `安装 Pip 库` 中安装依赖库。 +结合报错信息,参考插件的 README 手动安装依赖库。你可以在 AstrBot WebUI 的 `数据与日志 → 日志 → 安装 pip 库` 中安装依赖库。 -![image](https://files.astrbot.app/docs/source/images/faq/image-1.png) +在弹窗中填写库名,按需填写 PyPI 软件仓库链接,然后点击 `安装`。 如果发现插件作者没有填写 `requirements.txt` 文件,请在插件仓库提交 Issue,提醒作者补充。 diff --git a/docs/zh/others/diagnostics.md b/docs/zh/others/diagnostics.md index ab9a2c65bd..92082db63c 100644 --- a/docs/zh/others/diagnostics.md +++ b/docs/zh/others/diagnostics.md @@ -12,6 +12,8 @@ ## 先看哪些日志 +WebUI 可访问时,进入 `数据与日志 → 日志` 查看实时日志。需要调整控制台或文件日志级别时,进入 `设置 → 常规 → 日志`,修改后保存。 + 优先查看 AstrBot 主日志: ```text diff --git a/docs/zh/others/github-proxy.md b/docs/zh/others/github-proxy.md index 88daea179e..1faa7fd752 100644 --- a/docs/zh/others/github-proxy.md +++ b/docs/zh/others/github-proxy.md @@ -25,7 +25,7 @@ 8. **获取服务地址**: 部署成功后,页面会显示你的服务地址,格式为 `https://<第6步设置的项目名>.deno.dev`。复制这个地址。 9. **配置 AstrBot**: * 回到你的 AstrBot WebUI。 - * 进入 **设置 (Settings)** 页面。 + * 进入 **设置 → 网络** 页面。 * 找到 **GitHub 加速地址 (GitHub Proxy)** * 将**第 8 步**复制的 Deno 服务地址完整粘贴进去。 diff --git a/docs/zh/platform/aiocqhttp.md b/docs/zh/platform/aiocqhttp.md index 402e07f1b2..bcb7084d55 100644 --- a/docs/zh/platform/aiocqhttp.md +++ b/docs/zh/platform/aiocqhttp.md @@ -21,7 +21,7 @@ AstrBot 支持接入所有适配了 OneBotv11 反向 Websockets(AstrBot 做服 1. 进入 AstrBot 的 WebUI 2. 点击左边栏 `机器人` -3. 然后在右边的界面中,点击 `+ 创建机器人` +3. 点击机器人列表上方的 `创建机器人` 4. 选择 `OneBot v11` 在出现的表单中,填写: @@ -45,7 +45,7 @@ AstrBot 支持接入所有适配了 OneBotv11 反向 Websockets(AstrBot 做服 ## 3. 验证 -前往 AstrBot WebUI 的 `数据` -> `日志`,如果出现 ` aiocqhttp(OneBot v11) 适配器已连接。` 蓝色的日志,说明连接成功。如果没有,若干秒后出现` aiocqhttp 适配器已被关闭` 则为连接超时(失败),请检查配置是否正确。 +前往 AstrBot WebUI 的 `数据与日志` -> `日志`,如果出现 ` aiocqhttp(OneBot v11) 适配器已连接。` 蓝色的日志,说明连接成功。如果没有,若干秒后出现` aiocqhttp 适配器已被关闭` 则为连接超时(失败),请检查配置是否正确。 ## 附录:部署 Napcat @@ -81,6 +81,6 @@ NAPCAT_UID=$(id -u) NAPCAT_GID=$(id -g) docker compose -f ./astrbot.yml up -d ``` 部署完毕之后,可以去 Napcat 的 WebUI(默认端口 6099)中新增 OneBot 连接实例:点击`网络配置->新建->WebSockets客户端`,在新弹出的窗口中:勾选`启用`, -URL 填写 `ws://宿主机IP:端口/ws`。如 `ws://127.0.0.1:6199/ws`。如果采用上面的 Docker Compose 部署,可以填写 `ws://astrbot:6199/ws`(参考本文档的 Docker 脚本)。心跳间隔和重连间隔可以改为 `1000`(1 秒)。点击保存,然后前往 AstrBot WebUI 的 `数据` -> `日志` 检查是否连接成功,出现 `aiocqhttp(OneBot v11) 适配器已连接` 日志即代表成功。 +URL 填写 `ws://宿主机IP:端口/ws`。如 `ws://127.0.0.1:6199/ws`。如果采用上面的 Docker Compose 部署,可以填写 `ws://astrbot:6199/ws`(参考本文档的 Docker 脚本)。心跳间隔和重连间隔可以改为 `1000`(1 秒)。点击保存,然后前往 AstrBot WebUI 的 `数据与日志` -> `日志` 检查是否连接成功,出现 `aiocqhttp(OneBot v11) 适配器已连接` 日志即代表成功。 如果您对部署、网络配置不了解,请千万不要在公网暴露 Napcat 的端口。 diff --git a/docs/zh/platform/discord.md b/docs/zh/platform/discord.md index 89c198a928..8c41b410d5 100644 --- a/docs/zh/platform/discord.md +++ b/docs/zh/platform/discord.md @@ -2,12 +2,7 @@ ## 创建 AstrBot Discord 平台适配器 -进入机器人,点击新增适配器,找到 Discord 并点击进入 Discord 配置页。 -> 旧版本`机器人`为`消息平台` -![点击创建机器人,选择discord类型](https://files.astrbot.app/docs/source/images/discord/image.png) - -![选项从上到下依次是 1.机器人名称 2. 启用 3. Bot token 4. Discord 代理地址 5. 是否自动将插件指令注册为 Discord 斜杠指令 6. discord_guild_id_for_debug 7.Discord 活动名称](https://files.astrbot.app/docs/source/images/discord/image-3.png) -> 本次教程只用管1,2,3,5项 +进入 WebUI 的 `机器人` 页,点击 `创建机器人`,选择 `Discord`。填写以下配置,获取 Token 后点击 `保存`。 - 机器人名称:自定义,方便区分不同适配器 - 启用:勾选后启用该适配器 @@ -62,7 +57,7 @@ Discord 支持预回应表情功能。启用后,机器人在处理消息时会先添加一个表情反应,让用户知道机器人正在处理消息。 -在管理面板的「配置」页面中,找到 `平台特定配置 -> Discord -> 预回应表情`: +进入 `配置文件`,选择该机器人使用的配置文件,点击搜索按钮并搜索 `platform_specific.discord.pre_ack_emoji`。修改后点击 `保存配置`: - **启用预回应表情**:开启后,机器人收到消息时会自动添加表情反应 - **表情列表**:填写 Unicode 表情符号,例如:👍、🤔、⏳。可填写多个,机器人会随机选择一个使用 diff --git a/docs/zh/platform/kook.md b/docs/zh/platform/kook.md index b585ab870c..b080a14254 100644 --- a/docs/zh/platform/kook.md +++ b/docs/zh/platform/kook.md @@ -32,7 +32,7 @@ 1. 进入 AstrBot 的管理面板 2. 点击左边栏 `机器人` -3. 然后在右边的界面中,点击 `+ 创建机器人` +3. 点击机器人列表上方的 `创建机器人` 4. 选择 `kook` 适配器 5. 弹出的配置项填写: diff --git a/docs/zh/platform/lark.md b/docs/zh/platform/lark.md index a788a80e7f..92f0d49085 100644 --- a/docs/zh/platform/lark.md +++ b/docs/zh/platform/lark.md @@ -35,7 +35,7 @@ > > 可以将下面链接中的 `` 替换为你的飞书应用 App ID 后打开,一键进入权限开通页: > -> App ID 获取方式:回到 AstrBot 的 `机器人` 页,找到刚刚创建的飞书机器人,点击 `编辑`,弹出的对话框中可以看到 App ID。 +> App ID 获取方式:回到 AstrBot 的 `机器人` 页,选中刚刚创建的飞书机器人,在 `接入设置` 中查看 `app_id`。 > > ```text > https://open.feishu.cn/app//auth?q=contact:contact.base:readonly,contact:user.base:readonly,im:message.p2p_msg:readonly,im:message.group_at_msg:readonly,im:message:send,im:message,im:message:send_as_bot,im:resource:upload,im:resource,cardkit:card:write,im:message.group_at_msg:readonly,im:message.group_msg&op_from=openapi&token_type=tenant @@ -61,7 +61,7 @@ 1. 进入 AstrBot 的管理面板 2. 点击左边栏 `机器人` -3. 然后在右边的界面中,点击 `+ 创建机器人` +3. 点击机器人列表上方的 `创建机器人` 4. 选择 `lark(飞书)` 5. 如果使用扫码一键创建,选择 `扫码一键创建` 并完成扫码;如果使用自己创建的企业自建应用,选择 `手动创建` @@ -95,9 +95,7 @@ > [!TIP] > 为了更好地使用这种方式,请先参考 [统一 Webhook 模式](/use/unified-webhook.html) 做好相关配置。 -在点击 `保存` 后,机器人卡片会显示「查看 Webhook 链接」,点击查看,复制回调 URL。 - -![](https://files.astrbot.app/docs/source/images/lark/webhook.png) +点击 `保存` 后,在 `机器人` 页选中刚创建的机器人,点击 `查看 Webhook 链接`,复制回调 URL。 接下来,回到飞书的事件与回调页,点击「事件配置」,选择「将事件发送至开发者服务器」,将“请求地址”填写为刚刚复制的回调 URL,点击保存。如果一切无误将不会报错。 diff --git a/docs/zh/platform/line.md b/docs/zh/platform/line.md index 32b7dedcb0..f1a7f5013a 100644 --- a/docs/zh/platform/line.md +++ b/docs/zh/platform/line.md @@ -57,7 +57,7 @@ LINE 适配器仅支持 AstrBot 统一 Webhook 模式。 -保存后,在机器人卡片里点击「查看 Webhook 链接」,复制 URL。 +保存后,在 `机器人` 页选中刚创建的机器人,点击 `查看 Webhook 链接`,复制 URL。 然后到 LINE Developers Console: diff --git a/docs/zh/platform/matrix.md b/docs/zh/platform/matrix.md index db1d056f27..53acadd4b5 100644 --- a/docs/zh/platform/matrix.md +++ b/docs/zh/platform/matrix.md @@ -9,11 +9,8 @@ Matrix 是一个 IM 协议,有着丰富的服务端实现。 请在 [Matrix Server](https://matrix.org/ecosystem/servers/)查看可用的服务端。 - - ## 支持的基本消息类型 - | 消息类型 | 是否支持接收 | 是否支持发送 | 备注 | | ------------ | ------------ | ------------ | ---------------------------------------------- | | 文本 | 是 | 是 | | @@ -27,9 +24,9 @@ Matrix 是一个 IM 协议,有着丰富的服务端实现。 ## 安装 astrbot_plugin_matrix_adapter 插件 -进入 AstrBot WebUI 的插件市场,搜索 `astrbot_plugin_matrix_adapter`,点击安装。 +进入 AstrBot WebUI 的 `插件 → 插件市场`,搜索 `astrbot_plugin_matrix_adapter`,点击安装。 -安装完成后,前往 机器人(旧版本为 `消息平台`) → 新增适配器 → 选择 Matrix(若选项缺失,尝试重启 AstrBot 或检查插件安装状态)。 +安装完成后,前往 `机器人` → `创建机器人` → 选择 Matrix(若选项缺失,尝试重启 AstrBot 或检查插件安装状态)。 在弹出的配置对话框中点击 `启用`。 diff --git a/docs/zh/platform/misskey.md b/docs/zh/platform/misskey.md index 1afc854d27..932eef74a8 100644 --- a/docs/zh/platform/misskey.md +++ b/docs/zh/platform/misskey.md @@ -6,9 +6,7 @@ ## 创建 AstrBot Misskey 平台适配器 -进入消息平台,点击新增适配器,找到 Misskey 并单击进入 Misskey 配置页。 - -![创建 Misskey 平台适配器](https://files.astrbot.app/docs/source/images/misskey/create.png) +进入 WebUI 的 `机器人` 页,点击 `创建机器人`,选择 `Misskey`,填写下文介绍的接入信息并点击 `保存`。 ## 配置平台适配器设置 @@ -20,8 +18,6 @@ 获取 Misskey 接入信息的方式见下文介绍。 -![Misskey 平台适配器配置](https://files.astrbot.app/docs/source/images/misskey/config.png) - ## Misskey 实例 URL 就是你的 Bot 所处账号的 Misskey 实例前端地址,格式为标准域名。例如`https://misskey.example`。 @@ -87,7 +83,7 @@ Misskey 在`v2025.4.0`及以后的版本中为加入“聊天”组件支持, ## 历史记录 -聊天和贴文单个用户的对话历史会显示在 AstrBot WebUI 的 `数据` -> `对话` 中,并以 `chat:UserID` 作为会话 ID;传统贴文则以 `note:UserID` 作为会话 ID。 +聊天和贴文单个用户的对话历史会显示在 AstrBot WebUI 的 `数据与日志` -> `对话` 中,并以 `chat:UserID` 作为会话 ID;传统贴文则以 `note:UserID` 作为会话 ID。 ::: tip Misskey 用户的 UserID 在哪里? 位于用户个人页面部分的`Raw`页面内可以查询,UserID 是单个实例中 Misskey 用户唯一的关键身份标识。 diff --git a/docs/zh/platform/qqofficial/webhook.md b/docs/zh/platform/qqofficial/webhook.md index b07facc30a..d69a7a6e13 100644 --- a/docs/zh/platform/qqofficial/webhook.md +++ b/docs/zh/platform/qqofficial/webhook.md @@ -34,9 +34,7 @@ 8. 保存回调配置后,重启 AstrBot。 > [!TIP] -> 使用 `统一 Webhook 模式` 时,AstrBot 会自动生成唯一的 Webhook 回调链接。你可以在日志中,或者 WebUI 的机器人卡片上找到该链接。 - -![unified_webhook](https://files.astrbot.app/docs/source/images/use/unified-webhook.png) +> 使用 `统一 Webhook 模式` 时,AstrBot 会自动生成唯一的 Webhook 回调链接。你可以在 `数据与日志 → 日志` 中查看,或在 `机器人` 页选中该机器人,点击 `查看 Webhook 链接`。 ### 在群聊中使用 @@ -97,7 +95,7 @@ Webhook 模式还需要在 QQ 开放平台的回调配置中勾选群事件 `GRO 1. 进入 AstrBot 的管理面板 2. 点击左边栏 `机器人` -3. 然后在右边的界面中,点击 `+ 创建机器人` +3. 点击机器人列表上方的 `创建机器人` 4. 选择 `QQ 官方机器人(Webhook)` 推荐使用 `扫码一键创建`: @@ -127,7 +125,7 @@ Webhook 回调地址必须可以被 QQ 开放平台公网访问,并且需要 在 `开发 -> 回调配置` 处,配置回调地址。 -上一步点击保存之后,AstrBot 将会自动为你生成唯一的 Webhook 回调链接,你可以在日志中或者 WebUI 的机器人页的卡片上找到。 +上一步点击保存之后,AstrBot 将会自动为你生成唯一的 Webhook 回调链接,你可以在 `数据与日志 → 日志` 中查看,或在 `机器人` 页选中该机器人,点击 `查看 Webhook 链接`。 将请求地址填写为该地址。 diff --git a/docs/zh/platform/qqofficial/websockets.md b/docs/zh/platform/qqofficial/websockets.md index da1705df18..3ebc807cf1 100644 --- a/docs/zh/platform/qqofficial/websockets.md +++ b/docs/zh/platform/qqofficial/websockets.md @@ -87,7 +87,7 @@ 1. 进入 AstrBot 的管理面板 2. 点击左边栏 `机器人` -3. 然后在右边的界面中,点击 `+ 创建机器人` +3. 点击机器人列表上方的 `创建机器人` 4. 选择 `QQ 官方机器人(WebSocket)` 推荐使用 `扫码一键创建`: diff --git a/docs/zh/platform/satori/guide.md b/docs/zh/platform/satori/guide.md index c60380de9b..8fa5100ff1 100644 --- a/docs/zh/platform/satori/guide.md +++ b/docs/zh/platform/satori/guide.md @@ -18,7 +18,7 @@ Satori 的开发团队长期从事聊天机器人开发,熟悉各种聊天平 1. 进入 AstrBot 的 WebUI 2. 点击左边栏 `机器人` -3. 然后在右边的界面中,点击 `+ 创建机器人` +3. 点击机器人列表上方的 `创建机器人` 4. 选择 `Satori` 弹出的配置项填写: diff --git a/docs/zh/platform/satori/server-satori.md b/docs/zh/platform/satori/server-satori.md index b957bd0eb6..70b1a348a7 100644 --- a/docs/zh/platform/satori/server-satori.md +++ b/docs/zh/platform/satori/server-satori.md @@ -25,7 +25,7 @@ 1. 进入 AstrBot 的管理面板 2. 点击左边栏 `机器人` -3. 然后在右边的界面中,点击 `+ 创建机器人` +3. 点击机器人列表上方的 `创建机器人` 4. 选择 `satori` 弹出的配置项填写: diff --git a/docs/zh/platform/slack.md b/docs/zh/platform/slack.md index de5b31c3f3..3135905580 100644 --- a/docs/zh/platform/slack.md +++ b/docs/zh/platform/slack.md @@ -63,9 +63,7 @@ Slack 支持两种接入方式:`Webhook` 与 `Socket`。如果您没有公网 如果您使用的是 Webhook 模式: -- 如果开启了 `统一 Webhook 模式`,点击保存之后,AstrBot 将会自动为你生成唯一的 Webhook 回调链接,你可以在日志中或者 WebUI 的机器人页的卡片上找到,将该链接填入 `Request URL` 输入框中。 - -![unified_webhook](https://files.astrbot.app/docs/source/images/use/unified-webhook.png) +- 如果开启了 `统一 Webhook 模式`,点击保存之后,AstrBot 将会自动为你生成唯一的 Webhook 回调链接,你可以在 `数据与日志 → 日志` 中查看,或在 `机器人` 页选中该机器人,点击 `查看 Webhook 链接`,将该链接填入 `Request URL` 输入框中。 - 如果没有开启 `统一 Webhook 模式`,请在 `Request URL` 输入框中输入 `https://您的域名/astrbot-slack-webhook/callback`。 diff --git a/docs/zh/platform/start.md b/docs/zh/platform/start.md index 6e48d5ddd8..e596401283 100644 --- a/docs/zh/platform/start.md +++ b/docs/zh/platform/start.md @@ -2,7 +2,9 @@ AstrBot 支持接入众多主流即时通讯软件平台,帮助您在自己喜欢的 IM 平台上使用 AstrBot 的强大功能。 -在 WebUI 中,点击侧边栏的**机器人**,即可进入消息平台接入界面。点击右上角的**创建机器人**,选择您想要接入的平台,按照本文档左侧提供的接入指南进行操作,即可完成接入。 +在 WebUI 中,点击侧边栏的**机器人**,即可进入消息平台接入界面。点击机器人列表上方的 **创建机器人**,选择您想要接入的平台,按照本文档左侧提供的接入指南进行操作,即可完成接入。 > [!TIP] -> 建议在部署前预先安装 `ffmpeg`(并确保支持 `amr`),否则媒体类文件可能无法正常收发。对于微信类平台接入,强烈建议安装。 \ No newline at end of file +> 建议在部署前预先安装 `ffmpeg`(并确保支持 `amr`),否则媒体类文件可能无法正常收发。对于微信类平台接入,强烈建议安装。 + +创建后,从机器人列表中选择实例,在 **接入设置** 中修改连接参数,点击 **保存更改** 生效。**会话配置** 可为机器人选择默认配置文件,或为特定会话单独绑定配置。连接状态显示在机器人列表中,详细日志位于 **数据与日志 → 日志**。 diff --git a/docs/zh/platform/telegram.md b/docs/zh/platform/telegram.md index 0156b668df..bbe10c676a 100644 --- a/docs/zh/platform/telegram.md +++ b/docs/zh/platform/telegram.md @@ -13,7 +13,6 @@ | 视频 | 是 | 是 | | | 文件 | 是 | 是 | | - 主动消息推送:支持。 ## 1. 创建 Telegram Bot @@ -28,7 +27,7 @@ 1. 进入 AstrBot 的管理面板 2. 点击左边栏 `机器人` -3. 然后在右边的界面中,点击 `+ 创建机器人` +3. 点击机器人列表上方的 `创建机器人` 4. 选择 `telegram` 弹出的配置项填写: @@ -37,11 +36,11 @@ - 启用(enable): 勾选。 - Bot Token: 你的 Telegram 机器人的 `token`。 -请确保你的网络环境可以访问 Telegram。你可能需要使用 `配置页->其他配置->HTTP 代理` 来设置代理。 +请确保你的网络环境可以访问 Telegram。你可能需要使用 `设置 → 网络 → 代理与依赖源 → HTTP 代理` 来设置代理。 ## 流式输出 -Telegram 平台支持流式输出。需要在「AI 配置」->「其他配置」中开启「流式输出」开关。 +Telegram 平台支持流式输出。需要进入 `配置文件`,选择 Telegram 机器人使用的配置文件,在 `AI → 通用设置 → 消息处理` 中开启 `流式输出`,再点击 `保存配置`。 ### 私聊流式输出 diff --git a/docs/zh/platform/vocechat.md b/docs/zh/platform/vocechat.md index 67bd7e2229..91cdac5cc9 100644 --- a/docs/zh/platform/vocechat.md +++ b/docs/zh/platform/vocechat.md @@ -15,9 +15,7 @@ VoceChat 是一个开源的支持多平台、搭建简单的即时通讯平台 ## 安装 astrbot_plugin_vocechat 插件 -进入 AstrBot 仪表盘的插件市场,搜索 `astrbot_plugin_vocechat`,点击安装。 - -![image](https://files.astrbot.app/docs/source/images/vocechat/image.png) +进入 AstrBot WebUI 的 `插件 → 插件市场`,搜索 `astrbot_plugin_vocechat`,点击安装。 安装完成后,前往 `机器人` → `+ 创建机器人` → 选择 VoceChat(若选项缺失,尝试重启 AstrBot 或检查插件安装状态)。 diff --git a/docs/zh/platform/wecom.md b/docs/zh/platform/wecom.md index a15d4468d1..3d1096fc56 100644 --- a/docs/zh/platform/wecom.md +++ b/docs/zh/platform/wecom.md @@ -22,7 +22,7 @@ AstrBot 支持接入企业微信应用和微信客服。 1. 进入 AstrBot 的管理面板 2. 点击左边栏 `机器人` -3. 然后在右边的界面中,点击 `+ 创建机器人` +3. 点击机器人列表上方的 `创建机器人` 4. 选择 `wecom` 这将弹出一个对话框。接下来,不要关闭页面,转移到下一步。 @@ -50,9 +50,7 @@ AstrBot 支持接入企业微信应用和微信客服。 回调 URL 填写: -- 如果开启了 `统一 Webhook 模式`,点击保存之后,AstrBot 将会自动为你生成唯一的 Webhook 回调链接,你可以在日志中或者 WebUI 的机器人页的卡片上找到,将该链接填入回调 URL 处。 - -![unified_webhook](https://files.astrbot.app/docs/source/images/use/unified-webhook.png) +- 如果开启了 `统一 Webhook 模式`,点击保存之后,AstrBot 将会自动为你生成唯一的 Webhook 回调链接,你可以在 `数据与日志 → 日志` 中查看,或在 `机器人` 页选中该机器人,点击 `查看 Webhook 链接`,将该链接填入回调 URL 处。 - 如果没有开启 `统一 Webhook 模式`,填写 `http://你的带公网地址的服务器ip:6195/callback/command`。 @@ -60,12 +58,12 @@ AstrBot 支持接入企业微信应用和微信客服。 回到微信客服 `回调配置`,点击 `完成`。如果一切无误,将会显示 `已完成`(否则会显示类似 `openapi 回调不通过` 类似的文本)。 -1. **获取 Secret。** 之后,在 `开发配置` 中得到 Secret,找到复制到刚刚创建的企业微信适配器,点击编辑,然后修改配置中的 `secret`。然后再次保存配置,等待适配器加载完成。 +1. **获取 Secret。** 之后,在 `开发配置` 中得到 Secret,回到 AstrBot 的 `机器人` 页,选中刚刚创建的企业微信机器人,在 `接入设置` 中填写 `secret`。点击 `保存更改`,等待适配器加载完成。 > [!TIP] > 根据 [#571](https://github.com/Soulter/AstrBot/issues/571) 的反馈,对于新注册的企业,`corp_id` 可能要注册一段时间后才生效(前后大概过了半个小时)。 -然后,打开 `数据` -> `日志`,你应该会看到如下日志: +然后,打开 `数据与日志` -> `日志`,你应该会看到如下日志: ```txt 请打开以下链接,在微信扫码以获取客服微信 ... @@ -100,13 +98,11 @@ AstrBot 支持接入企业微信应用和微信客服。 并且点击下方的两个随机获取,得到 `Token` 和 `EncodingAESKey`,复制到 AstrBot 配置的 `token` 和 `encoding_aes_key` 处。建议保持 `统一 Webhook 模式 (unified_webhook_mode)` 为开启状态。 -现在应该已经填完 AstrBot 连接到企业微信的所有配置项。点击 AstrBot 配置页右下角保存,等待 AstrBot 重启。 +现在应该已经填完 AstrBot 连接到企业微信的所有配置项。点击创建弹窗中的 `保存`(修改已有机器人时点击 `保存更改`),等待适配器重新加载。 在 URL 处填入回调地址: -- 如果开启了 `统一 Webhook 模式`,点击保存之后,AstrBot 将会自动为你生成唯一的 Webhook 回调链接,你可以在日志中或者 WebUI 的机器人页的卡片上找到,将该链接填入 URL 处。 - -![unified_webhook](https://files.astrbot.app/docs/source/images/use/unified-webhook.png) +- 如果开启了 `统一 Webhook 模式`,点击保存之后,AstrBot 将会自动为你生成唯一的 Webhook 回调链接,你可以在 `数据与日志 → 日志` 中查看,或在 `机器人` 页选中该机器人,点击 `查看 Webhook 链接`,将该链接填入 URL 处。 - 如果没有开启 `统一 Webhook 模式`,填入 `http://你的带公网地址的服务器ip:6195/callback/command`。 @@ -119,7 +115,7 @@ AstrBot 支持接入企业微信应用和微信客服。 将你的 公网 IP 地址填写到此处,点击确定。 -重启成功后,回到API 接收页面,点击下面的保存,看是否能够保存成功。如果出现 `openapi 请求回调地址不通过` 说明配置有问题,请检查四个配置项是否填写正确。 +适配器加载完成后,回到 API 接收页面,点击下面的保存,看是否能够保存成功。如果出现 `openapi 请求回调地址不通过` 说明配置有问题,请检查四个配置项是否填写正确。 如果能够保存成功,AstrBot 就已经能够接收信息。 @@ -145,4 +141,4 @@ linux 用户可以使用 `apt install ffmpeg` 安装。 windows 用户可以在 [ffmpeg 官网](https://ffmpeg.org/download.html) 下载安装。 -mac 用户可以使用 `brew install ffmpeg` 安装。 +mac 用户可以使用 `brew install ffmpeg` 安装。 diff --git a/docs/zh/platform/wecom_ai_bot.md b/docs/zh/platform/wecom_ai_bot.md index 55aca1b016..17e6347d17 100644 --- a/docs/zh/platform/wecom_ai_bot.md +++ b/docs/zh/platform/wecom_ai_bot.md @@ -30,17 +30,13 @@ ## 配置 AstrBot -1. 进入 AstrBot 的管理面板,点击左侧栏 `机器人`(旧版本为 `消息平台`),然后在右侧的界面中,点击 `+ 新增适配器`,选择 `企业微信智能机器人`,进入配置页面。 - -![新增适配器](https://files.astrbot.app/docs/source/images/wecom_ai_bot/image-2.png) +1. 进入 AstrBot 的管理面板,点击左侧栏 `机器人`,点击机器人列表上方的 `创建机器人`,选择 `企业微信智能机器人`,进入配置页面。 2. 在弹出的配置项中将 `企业微信智能机器人的名字`、`token`、`encoding_aes_key` 从上一步创建智能机器人时填写的值复制粘贴到对应的输入框中。ID 可以随意填写,用于区分不同的消息平台实例。`port` 默认为 `6198`,可以根据需要修改,但请确保该端口未被占用。请保持 `统一 Webhook 模式 (unified_webhook_mode)` 为开启状态。点击 `保存`。 3. 回到企业微信智能机器人创建页面,填写 `URL`: - - 如果开启了 `统一 Webhook 模式`,点击保存之后,AstrBot 将会自动为你生成唯一的 Webhook 回调链接,你可以在日志中或者 WebUI 的机器人页的卡片上找到,将该链接填入 `URL` 处。 - - ![unified_webhook](https://files.astrbot.app/docs/source/images/use/unified-webhook.png) + - 如果开启了 `统一 Webhook 模式`,点击保存之后,AstrBot 将会自动为你生成唯一的 Webhook 回调链接,你可以在 `数据与日志 → 日志` 中查看,或在 `机器人` 页选中该机器人,点击 `查看 Webhook 链接`,将该链接填入 `URL` 处。 - 如果没有开启 `统一 Webhook 模式`,填写 `http://IP:port/webhook/wecom-ai-bot`,其中 `IP` 替换为你的 AstrBot 服务器的公网 IP 地址,`port` 替换为上一步填写的端口号。 diff --git a/docs/zh/platform/weixin-official-account.md b/docs/zh/platform/weixin-official-account.md index 90c4fc1d4a..0815ae9dc1 100644 --- a/docs/zh/platform/weixin-official-account.md +++ b/docs/zh/platform/weixin-official-account.md @@ -8,7 +8,7 @@ AstrBot 支持接入微信公众平台(版本 >= v3.5.8),并以微信公 1. 进入 AstrBot 的管理面板 2. 点击左边栏 `机器人` -3. 然后在右边的界面中,点击 `+ 创建机器人` +3. 点击机器人列表上方的 `创建机器人` 4. 选择 `weixin_official_account(微信公众平台)` 这将弹出一个对话框。接下来,不要关闭页面,转移到下一步。 @@ -39,13 +39,11 @@ AstrBot 支持接入微信公众平台(版本 >= v3.5.8),并以微信公 建议保持 `统一 Webhook 模式 (unified_webhook_mode)` 为开启状态。 -现在应该已经填完 AstrBot 连接到微信公众平台的所有配置项。点击 AstrBot 配置页右下角保存,等待 AstrBot 重启。 +现在应该已经填完 AstrBot 连接到微信公众平台的所有配置项。点击创建弹窗中的 `保存`(修改已有机器人时点击 `保存更改`),等待适配器重新加载。 `URL` 填写: -- 如果开启了 `统一 Webhook 模式`,点击保存之后,AstrBot 将会自动为你生成唯一的 Webhook 回调链接,你可以在日志中或者 WebUI 的机器人页的卡片上找到,将该链接填入 URL 处。 - -![unified_webhook](https://files.astrbot.app/docs/source/images/use/unified-webhook.png) +- 如果开启了 `统一 Webhook 模式`,点击保存之后,AstrBot 将会自动为你生成唯一的 Webhook 回调链接,你可以在 `数据与日志 → 日志` 中查看,或在 `机器人` 页选中该机器人,点击 `查看 Webhook 链接`,将该链接填入 URL 处。 - 如果没有开启 `统一 Webhook 模式`,请填入 `http://你的域名/callback/command`。 diff --git a/docs/zh/platform/weixin_oc.md b/docs/zh/platform/weixin_oc.md index b1403dac11..c5e4fa0b7e 100644 --- a/docs/zh/platform/weixin_oc.md +++ b/docs/zh/platform/weixin_oc.md @@ -21,7 +21,7 @@ AstrBot 支持通过 `个人微信` 适配器接入微信个人号。该适配 1. 进入 AstrBot WebUI。 2. 点击左侧栏 `机器人`。 -3. 点击右上角 `+ 创建机器人`。 +3. 点击机器人列表上方的 `创建机器人`。 4. 选择 `个人微信`。 5. 页面会直接显示登录二维码,使用手机微信扫码,并在微信内确认登录。 6. 登录成功后点击 `保存`。 @@ -55,7 +55,7 @@ AstrBot 支持通过 `个人微信` 适配器接入微信个人号。该适配 登录成功后,用微信发送一条消息。如果 AstrBot 能正常回复,说明接入成功。 -也可以在 WebUI 的 `数据` -> `日志` 中观察日志,确认适配器已经完成登录并开始轮询消息。 +也可以在 WebUI 的 `数据与日志` -> `日志` 中观察日志,确认适配器已经完成登录并开始轮询消息。 ## 修改头像和备注名 diff --git a/docs/zh/providers/302ai.md b/docs/zh/providers/302ai.md index 50a3abe775..34ba288234 100644 --- a/docs/zh/providers/302ai.md +++ b/docs/zh/providers/302ai.md @@ -12,10 +12,12 @@ ## 接入 -打开 AstrBot 控制台 -> 服务提供商页面,点击新增提供商,找到并点击 `302.AI`(需要版本 >= 3.5.18) +进入 AstrBot WebUI 的「模型提供商」→「对话」,点击「新增」,选择 `302.AI`。 -修改 ID,并将 API Key 和模型名称填入对话框表单,点击保存,即可完成创建。 +填写提供商名称和 `API Key`,确认 `API Base URL`,点击「保存并获取模型」。在模型列表中点击所需模型右侧的 `+`,确认模型已启用;也可先「保存配置」,再通过「自定义模型」填写准确的模型 ID。点击已配置模型旁的「测试模型」按钮可检查是否可用。 ## 使用 +进入「配置文件」,选择要使用的配置文件,在「AI 配置」→「模型」中将「对话模型」设为刚添加的模型,点击右下角「保存配置」。此项用于 AstrBot 内置 AI。 + 对机器人输入 `/provider` 指令,将提供商切换到刚刚添加的 302.AI 提供商,即可使用。 diff --git a/docs/zh/providers/agent-runners/coze.md b/docs/zh/providers/agent-runners/coze.md index 80c673b61a..21c72753cd 100644 --- a/docs/zh/providers/agent-runners/coze.md +++ b/docs/zh/providers/agent-runners/coze.md @@ -48,17 +48,15 @@ AstrBot v4.2.1 之后的版本, 支持接入 [Coze](https://www.coze.cn/) 的 Ag 完成了所有预备工作, 现在我们就可以在 AstrBot 中配置 Coze 了。 -进入 AstrBot 管理面板 -> 服务提供商 -> 新增服务提供商 -> Coze, 进入配置页面。 +在 WebUI 中打开「配置文件」,选择要修改的配置文件,进入「AI 配置」。点击标题右侧「更多操作」(`…`)→「更换执行方式」,选择「Coze」,阅读并勾选配置重置提示后点击「使用此方式」。确保「启用 AI」已打开,然后在本页填写连接参数。切换会重置当前执行方式的配置,详情见 [Agent 执行器](../../use/agent-runner.md)。 -![Coze 供应商](https://files.astrbot.app/docs/source/images/coze/image_8.png) - -填入刚刚创建的 API Key 和 bot_id, 然后点击保存。 +填入刚刚创建的 API Key 和 bot_id, 然后点击右下角「保存配置」。 > 其他配置说明: > > - API Base URL: 一般不需要修改, 如果你使用的是 Coze 国际版, 这里修改为: "https://api.coze.com" > - 由 Coze 管理对话记录: 如描述所示。 -## 选择 Agent 执行器 +## 保存配置 -进入左边栏配置页面,点击「Agent 执行方式」,选择「Coze」,然后在下方出现的新的配置项中选择你刚刚创建的 Coze Agent 执行器的 ID,点击右下角「保存」,即可完成配置。 +填写完成后,点击右下角「保存配置」。该配置文件将直接使用上述执行方式和连接参数,无需另外创建或选择执行器提供商 ID。 diff --git a/docs/zh/providers/agent-runners/dashscope.md b/docs/zh/providers/agent-runners/dashscope.md index 46811c32ee..60b4b85b56 100644 --- a/docs/zh/providers/agent-runners/dashscope.md +++ b/docs/zh/providers/agent-runners/dashscope.md @@ -14,7 +14,7 @@ ![alt text](https://files.astrbot.app/docs/source/images/dashscope/image-2.png) -在 WebUI 中,点击「模型提供商」->「新增提供商」,选择「Agent 执行器」,选择「阿里云百炼应用」,进入阿里云百炼应用的配置页面。 +在 WebUI 中打开「配置文件」,选择要修改的配置文件,进入「AI 配置」。点击标题右侧「更多操作」(`…`)→「更换执行方式」,选择「阿里云百炼」,阅读并勾选配置重置提示后点击「使用此方式」。确保「启用 AI」已打开,然后在本页填写连接参数。切换会重置当前执行方式的配置,详情见 [Agent 执行器](../../use/agent-runner.md)。 根据阿里云百炼应用,一共有四种应用类型,分别是 @@ -28,13 +28,13 @@ 请保证 AstrBot 里配置的 `应用类型` 和阿里云百炼应用里创建的应用类型一致。 -然后将应用 ID 填写到 `dashscope_app_id`,API KEY 填写到 `dashscope_api_key`。 +然后将应用 ID 填写到 `应用 ID`,API KEY 填写到 `API Key`。 -填写完这三项之后点击保存。 +填写完这三项之后点击右下角「保存配置」。 -## 选择 Agent 执行器 +## 保存配置 -进入左边栏配置页面,点击「Agent 执行方式」,选择「阿里云百炼应用」,然后在下方出现的新的配置项中选择你刚刚创建的阿里云百炼应用 Agent 执行器的 ID,点击右下角「保存」,即可完成配置。 +填写完成后,点击右下角「保存配置」。该配置文件将直接使用上述执行方式和连接参数,无需另外创建或选择执行器提供商 ID。 ## 附录:在聊天时动态设置 Workflow 输入变量(可选) diff --git a/docs/zh/providers/agent-runners/deerflow.md b/docs/zh/providers/agent-runners/deerflow.md index 46dd2169de..9d34ee9869 100644 --- a/docs/zh/providers/agent-runners/deerflow.md +++ b/docs/zh/providers/agent-runners/deerflow.md @@ -20,13 +20,13 @@ ## 在 AstrBot 中配置 DeerFlow -在 WebUI 中,点击「模型提供商」->「新增提供商」,选择「Agent 执行器」,选择「DeerFlow」,进入 DeerFlow 的配置页面。 +在 WebUI 中打开「配置文件」,选择要修改的配置文件,进入「AI 配置」。点击标题右侧「更多操作」(`…`)→「更换执行方式」,选择「DeerFlow」,阅读并勾选配置重置提示后点击「使用此方式」。确保「启用 AI」已打开,然后在本页填写连接参数。切换会重置当前执行方式的配置,详情见 [Agent 执行器](../../use/agent-runner.md)。 填写以下配置项: - `API Base URL`:DeerFlow API 网关地址,默认为 `http://127.0.0.1:2026` -- `DeerFlow API Key`:可选。若你的 DeerFlow 网关使用 Bearer 鉴权,可在此填写 -- `Authorization Header`:可选。自定义 Authorization 请求头,优先级高于 `DeerFlow API Key` +- `API Key`:可选。若你的 DeerFlow 网关使用 Bearer 鉴权,可在此填写 +- `Authorization Header`:可选。自定义 Authorization 请求头,优先级高于 `API Key` - `Assistant ID`:对应 DeerFlow 2.0 LangGraph 的 `assistant_id`,默认为 `lead_agent` - `模型名称覆盖`:可选。覆盖 DeerFlow 默认模型 - `启用思考模式`:是否启用 DeerFlow 的思考模式 @@ -35,16 +35,16 @@ - `子智能体最大并发数`:对应 DeerFlow 2.0 运行时 `config.configurable.max_concurrent_subagents`,仅在启用子智能体时生效,默认 `3` - `递归深度上限`:对应 LangGraph 的 `recursion_limit`,默认 `1000` -填写完成后点击「保存」。 +填写完成后点击「保存配置」。 > [!TIP] > - 如果 DeerFlow 侧已经配置了默认模型,可以将 `模型名称覆盖` 留空。 > - 只有在 DeerFlow 侧已经启用了相应能力时,才建议开启 `计划模式` 或 `子智能体` 相关选项。 > - AstrBot 会同时发送 DeerFlow 2.0 推荐的 `config.configurable` 运行时参数,并保留兼容字段,便于对接上游近期版本。 -## 选择 Agent 执行器 +## 保存配置 -进入左边栏配置页面,点击「Agent 执行方式」,选择「DeerFlow」,然后在下方出现的新的配置项中选择你刚刚创建的 DeerFlow Agent 执行器提供商 ID,点击右下角「保存」,即可完成配置。 +填写完成后,点击右下角「保存配置」。该配置文件将直接使用上述执行方式和连接参数,无需另外创建或选择执行器提供商 ID。 ## 常见检查项 diff --git a/docs/zh/providers/agent-runners/dify.md b/docs/zh/providers/agent-runners/dify.md index ef27613cc9..a5bfc214c5 100644 --- a/docs/zh/providers/agent-runners/dify.md +++ b/docs/zh/providers/agent-runners/dify.md @@ -6,15 +6,14 @@ ## 在 AstrBot 中配置 Dify -在 WebUI 中,点击「模型提供商」->「新增提供商」,选择「Agent 执行器」,选择「Dify」,进入 Dify 的配置页面。 +在 WebUI 中打开「配置文件」,选择要修改的配置文件,进入「AI 配置」。点击标题右侧「更多操作」(`…`)→「更换执行方式」,选择「Dify」,阅读并勾选配置重置提示后点击「使用此方式」。确保「启用 AI」已打开,然后在本页填写连接参数。切换会重置当前执行方式的配置,详情见 [Agent 执行器](../../use/agent-runner.md)。 -![image](https://files.astrbot.app/docs/source/images/dify/image.png) +在 Dify 中,一个 `API Key` 唯一对应一个 Dify 应用。因此,您可以为不同配置文件填写不同的 API Key 来连接多个 Dify 应用。 -在 Dify 中,一个 `API Key` 唯一对应一个 Dify 应用。因此,您可以创建多个 Provider 以适配多个 Dify 应用。 - -根据目前的 Dify 项目,一共有三种类型,分别是: +AstrBot 的「应用类型」选项包括: - chat +- chatflow - agent - workflow @@ -22,7 +21,6 @@ >请确保你在 AstrBot 里设置的 APP 类型和 Dify 里面创建的应用的类型一致。 >![image](https://files.astrbot.app/docs/source/images/dify/image-3.png) - ### Chat 和 Agent 应用 按下图所示创建你的 Dify Chat 和 Agent 应用的密钥: @@ -31,7 +29,7 @@ ![image](https://files.astrbot.app/docs/source/images/dify/chat-agent-api-key-2.png) -复制密钥并粘贴到配置中的 `API Key` 字段中,点击「保存」。 +复制密钥并粘贴到配置中的 `API Key` 字段中,点击「保存配置」。 ### Workflow 应用 @@ -46,11 +44,11 @@ Workflow 应用接收输入变量,然后执行工作流,最后输出结果 - `astrbot_text_query`: 输入变量名。即用户输入的文本内容。 - `astrbot_session_id`: 会话 ID -你可以在配置中自定义输入变量名,即上图配置中的 “Prompt 输入变量名”。 +你可以在配置中自定义输入变量名,即当前 Dify 设置中的「Prompt 输入变量名」。 您需要修改您的 Workflow 的输入的变量名以适配 AstrBot 的输入。 -最终,Workflow 会输出一个结果,您可以自定义这个结果的变量名,即上图配置中的 “Dify Workflow 输出变量名”,默认为 `astrbot_wf_output`。你需要在 Dify 的 Workflow 的输出节点中配置这个变量名,否则 AstrBot 无法正确解析。 +最终,Workflow 会输出一个结果,您可以自定义这个结果的变量名,即当前 Dify 设置中的「Workflow 输出变量名」,默认为 `astrbot_wf_output`。你需要在 Dify 的 Workflow 的输出节点中配置这个变量名,否则 AstrBot 无法正确解析。 #### 创建 API Key @@ -60,11 +58,11 @@ Workflow 应用接收输入变量,然后执行工作流,最后输出结果 ![image](https://files.astrbot.app/docs/source/images/dify/workflow-api-key.png) -复制密钥并粘贴到配置中的 `API Key` 字段中,点击「保存」。 +复制密钥并粘贴到配置中的 `API Key` 字段中,点击「保存配置」。 -### 选择 Agent 执行器 +## 保存配置 -进入左边栏配置页面,点击「Agent 执行方式」,选择「Dify」,然后在下方出现的新的配置项中选择你刚刚创建的 Dify Agent 执行器的 ID,点击右下角「保存」,即可完成配置。 +填写完成后,点击右下角「保存配置」。该配置文件将直接使用上述执行方式和连接参数,无需另外创建或选择执行器提供商 ID。 ## 附录:在聊天时动态设置输入 Workflow 变量(可选) @@ -78,4 +76,4 @@ Workflow 应用接收输入变量,然后执行工作流,最后输出结果 当然,可以使用 `/unset` 指令来取消设置的变量。 -变量在当前会话永久有效。 \ No newline at end of file +变量在当前会话永久有效。 diff --git a/docs/zh/providers/aihubmix.md b/docs/zh/providers/aihubmix.md index 676e7bf0c3..ad0282aaa1 100644 --- a/docs/zh/providers/aihubmix.md +++ b/docs/zh/providers/aihubmix.md @@ -12,7 +12,7 @@ API 格式完全兼容 OpenAI,只需修改 API Base 和 Key 即可接入。** ## 在 AstrBot 中配置 -进入 AstrBot 管理面板,点击左栏 **服务提供商 → 新增提供商 → OpenAI**。 +进入 AstrBot 管理面板,点击左栏 **模型提供商 → 对话 → 新增 → OpenAI Compatible**。 填写以下信息: @@ -21,8 +21,7 @@ API 格式完全兼容 OpenAI,只需修改 API Base 和 Key 即可接入。** | API Base URL | `https://aihubmix.com/v1` | | API Key | 你在 AIHubMix 获取的 Key | -保存后,点击该 provider 卡片,添加你需要的模型。 -![在 AstrBot 中配置](https://github.com/user-attachments/assets/ee2fb8ba-652c-4e97-a781-42a9082ad7eb) +填写提供商名称和 `API Key`,确认 `API Base URL`,点击「保存并获取模型」。在模型列表中点击所需模型右侧的 `+`,确认模型已启用;也可先「保存配置」,再通过「自定义模型」填写准确的模型 ID。点击已配置模型旁的「测试模型」按钮可检查是否可用。 ## 推荐模型 @@ -56,13 +55,13 @@ AIHubMix 同时支持以下能力,均可在 AstrBot 中配置: | 能力 | AstrBot 配置位置 | |------|-----------------| -| 语音转文字 (STT) | 服务提供商 → 语音转文字 | -| 文字转语音 (TTS) | 服务提供商 → 文字转语音 | -| 嵌入 (Embedding) | 服务提供商 → 嵌入 | -| 重排序 (Rerank) | 服务提供商 → 重排序 | +| 语音转文字 (STT) | 模型提供商 → 语音转文字 → 新增 | +| 文字转语音 (TTS) | 模型提供商 → 文字转语音 → 新增 | +| 嵌入 (Embedding) | 模型提供商 → 嵌入 → 新增 | +| 重排序 (Rerank) | 模型提供商 → 重排序 → 新增 | -所有能力使用同一个 API Key 和 API Base,无需额外配置。 +各能力需要在对应分类中分别新增提供商并选择模型。API Key 可复用,API 地址及其他字段请按对应接口填写。 ## 设为默认 -前往 **配置 → 提供商设置**,将「默认聊天模型提供商」改为刚创建的 AIHubMix 提供商,保存即可。 +进入「配置文件」,选择要使用的配置文件,在「AI 配置」→「模型」中将「对话模型」设为刚添加的模型,点击右下角「保存配置」。此项用于 AstrBot 内置 AI。 diff --git a/docs/zh/providers/coze.md b/docs/zh/providers/coze.md index ed527969d2..ec16fecb11 100644 --- a/docs/zh/providers/coze.md +++ b/docs/zh/providers/coze.md @@ -1 +1 @@ -本页面已弃用,请参考 [Coze Agent 执行器](../agent-runners/coze.md)。 \ No newline at end of file +本页面已弃用,请参考 [Coze Agent 执行器](./agent-runners/coze.md)。 diff --git a/docs/zh/providers/dashscope.md b/docs/zh/providers/dashscope.md index 1d2d577732..3bf070422f 100644 --- a/docs/zh/providers/dashscope.md +++ b/docs/zh/providers/dashscope.md @@ -1 +1 @@ -本页面已弃用,请参考 [阿里云百炼应用 Agent 执行器](../agent-runners/dashscope.md)。 \ No newline at end of file +本页面已弃用,请参考 [阿里云百炼应用 Agent 执行器](./agent-runners/dashscope.md)。 diff --git a/docs/zh/providers/dify.md b/docs/zh/providers/dify.md index 76897c8f59..2e9efd0858 100644 --- a/docs/zh/providers/dify.md +++ b/docs/zh/providers/dify.md @@ -1 +1 @@ -本页面已弃用,请参考 [Dify Agent 执行器](../agent-runners/dify.md)。 \ No newline at end of file +本页面已弃用,请参考 [Dify Agent 执行器](./agent-runners/dify.md)。 diff --git a/docs/zh/providers/llm.md b/docs/zh/providers/llm.md index 80f1a1fc82..9886519c95 100644 --- a/docs/zh/providers/llm.md +++ b/docs/zh/providers/llm.md @@ -1,13 +1,11 @@ # 大语言模型提供商 -你可在管理面板->服务提供商->+新增服务提供商 处配置各种大语言模型服务。 +在 WebUI 的「模型提供商」→「对话」中点击「新增」,选择模型服务类型。兼容 OpenAI API 的服务可选择 `OpenAI Compatible`,并填写服务商提供的 API Base URL 和 API Key。 -> [!TIP] -> 如果没有你希望接入的模型服务,你可以试着查看您希望接入的服务提供商处是否支持 兼容 OpenAI API,如果支持,那么你可以选择上面截图中的第一项 `OpenAI` 然后通过修改 API Base URL 的方式接入。 +填写提供商名称和 `API Key`,确认 `API Base URL`,点击「保存并获取模型」。在模型列表中点击所需模型右侧的 `+`,确认模型已启用;也可先「保存配置」,再通过「自定义模型」填写准确的模型 ID。点击已配置模型旁的「测试模型」按钮可检查是否可用。 -![image](https://files.astrbot.app/docs/source/images/llm/image.png) +进入「配置文件」,选择要使用的配置文件,在「AI 配置」→「模型」中将「对话模型」设为刚添加的模型,点击右下角「保存配置」。此项用于 AstrBot 内置 AI。 -![image](https://files.astrbot.app/docs/source/images/llm/image-1.png) +详细步骤见 [接入模型服务](./start.md)。 - -> 相应的配置保存在 `data/cmd_config.json` 的 `provider` 字段中。 \ No newline at end of file +> 提供商连接配置保存在 `data/cmd_config.json` 的 `provider_sources` 字段,具体模型配置保存在 `provider` 字段。 diff --git a/docs/zh/providers/mirarouter.md b/docs/zh/providers/mirarouter.md index 89c3320e11..5c6ec274ae 100644 --- a/docs/zh/providers/mirarouter.md +++ b/docs/zh/providers/mirarouter.md @@ -9,7 +9,7 @@ ## 在 AstrBot 中配置 -打开 AstrBot 管理面板,进入 **服务提供商 → 新增提供商 → MiraRouter**,填写以下信息: +打开 AstrBot 管理面板,进入 **模型提供商 → 对话 → 新增 → MiraRouter**,填写以下信息: | 配置项 | 值 | | --- | --- | @@ -19,10 +19,10 @@ AstrBot 会自动为 MiraRouter 请求添加 `X-APP-CODE: astrbot` 标识。 -保存后,点击该提供商卡片,根据 [MiraRouter 模型与价格](https://mirarouter.com/models) 页面中的模型列表添加需要使用的模型。 +填写提供商名称和 `API Key`,确认 `API Base URL`,点击「保存并获取模型」。在模型列表中点击所需模型右侧的 `+`,确认模型已启用;也可先「保存配置」,再通过「自定义模型」填写准确的模型 ID。点击已配置模型旁的「测试模型」按钮可检查是否可用。 ## 设为默认模型 -进入 **配置文件 → 提供商设置**,将「默认聊天模型」设置为刚刚添加的 MiraRouter 模型,然后保存配置。 +进入「配置文件」,选择要使用的配置文件,在「AI 配置」→「模型」中将「对话模型」设为刚添加的模型,点击右下角「保存配置」。此项用于 AstrBot 内置 AI。 更多接入说明请参阅 [MiraRouter 文档](https://docs.mirarouter.com/)。 diff --git a/docs/zh/providers/newapi.md b/docs/zh/providers/newapi.md index 3dea474d75..264a9ad5e0 100644 --- a/docs/zh/providers/newapi.md +++ b/docs/zh/providers/newapi.md @@ -17,22 +17,16 @@ AstrBot 支持接入 NewAPI 作为模型提供商,用户可以通过 NewAPI ![copy-api-key](https://files.astrbot.app/docs/source/images/newapi/image-1.png) ### 在 AstrBot 中配置 NewAPI 服务提供商 -打开 AstrBot 管理面板,进入「模型提供商」页面,然后,点击「新增模型提供商」按钮。 +打开 AstrBot 管理面板,进入「模型提供商」→「对话」,点击「新增」。 -NewAPI 完美地支持了 OpenAI Chat Completion 和 Responses 接口,我们点击 「OpenAI」,进入 OpenAI 提供商的配置页面。 +NewAPI 完美地支持了 OpenAI Chat Completion 和 Responses 接口,选择 `OpenAI Compatible`(Chat Completion)或 `OpenAI Responses`,进入相应的提供商设置。 在弹出的对话框中,将 API Base URL 设置为 NewAPI 的接口地址。如果您本地部署了 NewAPI,则填写本地地址,例如 `http://localhost:3000/v1`,如果您使用第三方服务商提供的 NewAPI 服务,则填写相应的 URL 地址,例如 `https://api.example.com/v1`。 -然后,将 API Key 填入「API Key」字段中,点击「保存」按钮。 - -![astrbot-provider-config](https://files.astrbot.app/docs/source/images/newapi/image-2.png) - -然后点击保存,完成 NewAPI 提供商的配置。 +填写提供商名称和 `API Key`,确认 `API Base URL`,点击「保存并获取模型」。在模型列表中点击所需模型右侧的 `+`,确认模型已启用;也可先「保存配置」,再通过「自定义模型」填写准确的模型 ID。点击已配置模型旁的「测试模型」按钮可检查是否可用。 ### 应用服务提供商 -进入「配置文件」页面,找到模型一节,将「默认聊天模型」修改为刚刚创建的 NewAPI 提供商,点击「保存」按钮。 - -![apply](https://files.astrbot.app/docs/source/images/newapi/image-3.png) +进入「配置文件」,选择要使用的配置文件,在「AI 配置」→「模型」中将「对话模型」设为刚添加的模型,点击右下角「保存配置」。此项用于 AstrBot 内置 AI。 至此,您已经成功配置了 NewAPI 作为 AstrBot 的模型提供商。现在,您可以通过 AstrBot 来访问和使用 NewAPI 提供的各种 AI 模型服务了。 diff --git a/docs/zh/providers/ppio.md b/docs/zh/providers/ppio.md index 24027c21fe..531ab6132a 100644 --- a/docs/zh/providers/ppio.md +++ b/docs/zh/providers/ppio.md @@ -14,21 +14,14 @@ PPIO 派欧云是中国领先的独立分布式云计算服务商,您可以在 ![image](https://files.astrbot.app/docs/source/images/ppio/image-3.png) -打开 AstrBot 控制台 -> 服务提供商页面,点击新增提供商,找到并点击 `PPIO派欧云`(需要版本 >= 3.5.10,旧版本也可使用,见下文)。 - -![image](https://files.astrbot.app/docs/source/images/ppio/image.png) - -将 API Key 和模型名称填入对话框表单,点击保存,即可完成创建。 - -> [!TIP] -> 如果您是 AstrBot 旧版本(< 3.5.10)的用户,请打开 AstrBot 控制台 -> 服务提供商页面,点击新增提供商,找到 `OpenAI`,点击进入。 -> 1. 将 ID 命名为 `ppio`(随意) -> 2. 然后将 `API Base URL` 设置为 `https://api.ppinfra.com/v3/openai` -> 3. 然后将 API Key 和模型名称填入对话框表单,点击保存,即可完成创建。 +进入 AstrBot WebUI 的「模型提供商」→「对话」,点击「新增」,选择 `PPIO`。 +填写提供商名称和 `API Key`,确认 `API Base URL`,点击「保存并获取模型」。在模型列表中点击所需模型右侧的 `+`,确认模型已启用;也可先「保存配置」,再通过「自定义模型」填写准确的模型 ID。点击已配置模型旁的「测试模型」按钮可检查是否可用。 ## 使用 +进入「配置文件」,选择要使用的配置文件,在「AI 配置」→「模型」中将「对话模型」设为刚添加的模型,点击右下角「保存配置」。此项用于 AstrBot 内置 AI。 + 对机器人输入 `/provider` 指令,将提供商切换到刚刚添加的 PPIO 派欧云提供商,即可使用。 ## 常见问题 @@ -39,5 +32,4 @@ PPIO 派欧云是中国领先的独立分布式云计算服务商,您可以在 Error code: 400 - {'code': 400, 'message': '"auto" tool choice requires --enable-auto-tool-choice and --tool-call-parser to be set', 'type': 'BadRequestError'} ``` - 请在 WebUI 中关闭所有调用工具后即可使用,或者换用其他模型。 diff --git a/docs/zh/providers/provider-lmstudio.md b/docs/zh/providers/provider-lmstudio.md index 8c0046f73a..da97901f09 100644 --- a/docs/zh/providers/provider-lmstudio.md +++ b/docs/zh/providers/provider-lmstudio.md @@ -20,7 +20,7 @@ lms get deepseek-r1-qwen-7b 在 AstrBot 上: -点击 配置->服务提供商配置->加号->openai +打开「模型提供商」→「对话」,点击「新增」,选择 `LM Studio`。 API Base URL 填写 `http://localhost:1234/v1` @@ -31,8 +31,8 @@ API Key 填写 `lm-studio` 如果 LM Studio 使用了 Docker 部署,请确保 1234 端口已经映射到宿主机。 -模型名填写上一步选好的 +填写提供商名称并确认 `API Base URL`。模板已预填 `API Key` 为 `lmstudio`;如果服务端另有认证要求,请改为实际密钥。点击「保存并获取模型」。在模型列表中点击所需模型右侧的 `+`,确认模型已启用;也可先「保存配置」,再通过「自定义模型」填写准确的模型 ID。点击已配置模型旁的「测试模型」按钮可检查是否可用。 -保存配置即可。 +进入「配置文件」,选择要使用的配置文件,在「AI 配置」→「模型」中将「对话模型」设为刚添加的模型,点击右下角「保存配置」。此项用于 AstrBot 内置 AI。 > 输入 /provider 查看 AstrBot 配置的模型 diff --git a/docs/zh/providers/provider-ollama.md b/docs/zh/providers/provider-ollama.md index d1b08c92ed..a3be97272c 100644 --- a/docs/zh/providers/provider-ollama.md +++ b/docs/zh/providers/provider-ollama.md @@ -22,10 +22,11 @@ model_name 格式:`:`。如 `deepseek-r1:8b`。 ## 配置 AstrBot -打开 AstrBot 控制台 -> 服务提供商页面,点击新增模型提供商,找到并点击 `Ollama`。 -![image](https://files.astrbot.app/docs/source/images/ollama/image.png) +打开「模型提供商」→「对话」,点击「新增」,选择 `Ollama`。默认 API 地址为 `http://127.0.0.1:11434/v1`,请按实际部署位置调整。 -保存配置即可。 +填写提供商名称并确认 `API Base URL`。模板已预填 `API Key` 为 `ollama`;如果服务端另有认证要求,请改为实际密钥。点击「保存并获取模型」。在模型列表中点击所需模型右侧的 `+`,确认模型已启用;也可先「保存配置」,再通过「自定义模型」填写准确的模型 ID。点击已配置模型旁的「测试模型」按钮可检查是否可用。 + +进入「配置文件」,选择要使用的配置文件,在「AI 配置」→「模型」中将「对话模型」设为刚添加的模型,点击右下角「保存配置」。此项用于 AstrBot 内置 AI。 ::: tip @@ -35,7 +36,6 @@ model_name 格式:`:`。如 `deepseek-r1:8b`。 ::: - ## FAQ 报错: diff --git a/docs/zh/providers/shengsuanyun.md b/docs/zh/providers/shengsuanyun.md index cf98c51f9f..b5cc123c25 100644 --- a/docs/zh/providers/shengsuanyun.md +++ b/docs/zh/providers/shengsuanyun.md @@ -9,7 +9,7 @@ ## 在 AstrBot 中配置 -打开 AstrBot 管理面板,进入 **服务提供商 → 新增提供商 → OpenAI**,填写以下信息: +打开 AstrBot 管理面板,进入 **模型提供商 → 对话 → 新增 → OpenAI Compatible**,填写以下信息: | 配置项 | 值 | | --- | --- | @@ -17,8 +17,8 @@ | API Base URL | `https://router.shengsuanyun.com/api/v1` | | API Key | 在胜算云控制台创建的 API Key | -保存后,点击该提供商卡片,根据胜算云控制台中的模型列表添加需要使用的模型。 +填写提供商名称和 `API Key`,确认 `API Base URL`,点击「保存并获取模型」。在模型列表中点击所需模型右侧的 `+`,确认模型已启用;也可先「保存配置」,再通过「自定义模型」填写准确的模型 ID。点击已配置模型旁的「测试模型」按钮可检查是否可用。 ## 设为默认模型 -进入 **配置文件 → 提供商设置**,将「默认聊天模型」设置为刚刚添加的胜算云模型,然后保存配置。 +进入「配置文件」,选择要使用的配置文件,在「AI 配置」→「模型」中将「对话模型」设为刚添加的模型,点击右下角「保存配置」。此项用于 AstrBot 内置 AI。 diff --git a/docs/zh/providers/siliconflow.md b/docs/zh/providers/siliconflow.md index 7a207410dd..2181f62a02 100644 --- a/docs/zh/providers/siliconflow.md +++ b/docs/zh/providers/siliconflow.md @@ -10,12 +10,10 @@ 在硅基流动[模型页面](https://cloud.siliconflow.cn/me/models)选择需要使用的模型,留存模型名称备用。 -进入 AstrBot WebUI,点击左栏 `服务提供商` -> `新增提供商` -> 选择 `硅基流动`。 +进入 AstrBot WebUI 的「模型提供商」→「对话」,点击「新增」,选择 `SiliconFlow`。 -粘贴上面创建和选择的 `API Key` 和 `模型名称`,点击保存,完成创建。您可以点击下方 `服务提供商可用性` 的 `刷新` 按钮测试配置是否成功。 - -![配置对话模型_1](https://files.astrbot.app/docs/source/images/siliconflow/image.png) +填写提供商名称和 `API Key`,确认 `API Base URL`,点击「保存并获取模型」。在模型列表中点击所需模型右侧的 `+`,确认模型已启用;也可先「保存配置」,再通过「自定义模型」填写准确的模型 ID。点击已配置模型旁的「测试模型」按钮可检查是否可用。 ## 应用对话模型 -在 AstrBot WebUI,点击左栏 `配置文件`,找到 AI 配置中的 `默认聊天模型`,选择刚刚创建的 `siliconflow`(硅基流动) 提供商,点击保存。 \ No newline at end of file +进入「配置文件」,选择要使用的配置文件,在「AI 配置」→「模型」中将「对话模型」设为刚添加的模型,点击右下角「保存配置」。此项用于 AstrBot 内置 AI。 diff --git a/docs/zh/providers/start.md b/docs/zh/providers/start.md index d1cea9181b..6026c5e47e 100644 --- a/docs/zh/providers/start.md +++ b/docs/zh/providers/start.md @@ -30,9 +30,9 @@ AstrBot 适配了 OpenAI、Google GenAI、Anthropic 三种原生 API 格式。 - 点击左侧导航栏的 “API Keys” 菜单,创建一个新的 API Key,并复制该 Key。 - 点击左侧导航栏下方的 “接口文档” 链接,进入 API 文档页面。 - 在 API 文档页面中,找到 “OpenAI 兼容接口” 相关的内容,记下 API Base URL,例如 `https://api.deepseek.com/v1`。(如果没有 /v1,就请加上 /v1)。 -- 打开 AstrBot 控制台 -> 服务提供商页面,点击新增提供商,找到并点击 `OpenAI`(如果其中有您想要接入的提供商的类型,请优先点击那些类型,如 DeepSeek,我们会针对部分提供商做适配优化)。将 API Key 填入对话框表单的 `API Key` 处,将 API Base URL 填入 `API Base URL` 处。 -- 点击获取模型列表,找到您想要使用的模型名称,点击右侧 + 号,然后将右侧的出现的开关打开。 -- 进入配置文件页面,找到对话模型,点击右侧的选择按钮,选择刚刚添加的提供商和模型,点击屏幕右下角的保存配置按钮即可。 +- 打开「模型提供商」→「对话」,点击「新增」,选择 `DeepSeek`。其他兼容 OpenAI API 的服务可选择 `OpenAI Compatible`。填写提供商名称、`API Key` 和 `API Base URL`。 +- 点击「保存并获取模型」,找到想使用的模型,点击右侧 `+` 并确认模型已启用。如果无法获取模型列表,可先「保存配置」,再点击「自定义模型」并填写模型 ID。可通过模型旁的「测试模型」检查连通性。 +- 进入「配置文件」,选择要使用的配置文件,在「AI 配置」→「模型」中将「对话模型」设为刚添加的模型,点击右下角「保存配置」。此项用于 AstrBot 内置 AI。 ## 使用环境变量加载 Key diff --git a/docs/zh/providers/tokenpony.md b/docs/zh/providers/tokenpony.md index 5001614310..6c1c6721db 100644 --- a/docs/zh/providers/tokenpony.md +++ b/docs/zh/providers/tokenpony.md @@ -8,16 +8,10 @@ 在小马算力[模型页面](https://www.tokenpony.cn/#/model)选择需要使用的模型,留存模型名称备用。 -进入 AstrBot WebUI,点击左栏 `服务提供商` -> `新增提供商` -> 选择 `小马算力` (需要版本 >= 4.3.3) +进入 AstrBot WebUI 的「模型提供商」→「对话」,点击「新增」,选择 `TokenPony`。 -![配置对话模型_1](https://files.astrbot.app/docs/source/images/tokenpony/image.png) - -> 如果没有看到 `小马算力` 选项,您也可以直接点击图中的 `接入 OpenAI`,并将 `API Base URL` 修改为 `https://api.tokenpony.cn/v1`。 - -粘贴上面创建和选择的 `API Key` 和 `模型名称`,点击保存,完成创建。您可以点击下方 `服务提供商可用性` 的 `刷新` 按钮测试配置是否成功。 +填写提供商名称和 `API Key`,确认 `API Base URL`,点击「保存并获取模型」。在模型列表中点击所需模型右侧的 `+`,确认模型已启用;也可先「保存配置」,再通过「自定义模型」填写准确的模型 ID。点击已配置模型旁的「测试模型」按钮可检查是否可用。 ## 应用对话模型 -在 AstrBot WebUI,点击左栏 `配置文件`,找到 AI 配置中的 `默认聊天模型`,选择刚刚创建的 `tokenpony`(小马算力) 提供商,点击保存。 - -![配置对话模型_2](https://files.astrbot.app/docs/source/images/tokenpony/image_1.png) \ No newline at end of file +进入「配置文件」,选择要使用的配置文件,在「AI 配置」→「模型」中将「对话模型」设为刚添加的模型,点击右下角「保存配置」。此项用于 AstrBot 内置 AI。 diff --git a/docs/zh/use/agent-runner.md b/docs/zh/use/agent-runner.md index 95a4d27e01..6e3ff2c352 100644 --- a/docs/zh/use/agent-runner.md +++ b/docs/zh/use/agent-runner.md @@ -35,18 +35,24 @@ Dify、Coze、百炼应用、DeerFlow 等平台已经内置了这个循环,如 ## 使用 -默认情况下,AstrBot 内置 Agent 执行器为默认执行器。使用默认执行器已经可以满足大部分需求,并且可以使用 AstrBot 的 MCP、知识库、网页搜索等功能。 +默认使用 AstrBot 内置 AI,可在「配置文件」→「AI 配置」→「模型」中选择对话模型,并配置人格、知识库和工具能力。 -如果你需要使用 Dify、Coze、百炼应用、DeerFlow 等平台的能力,可以创建一个 Agent 执行器,并选择相应的提供商。 +接入第三方应用时,在当前配置文件内直接选择执行方式并填写连接参数: -## 创建 Agent 执行器 +1. 打开 WebUI 左侧「配置文件」,选择要修改的配置文件,进入「AI 配置」。 +2. 点击 AI 标题右侧的「更多操作」(`…`),选择「更换执行方式」。 +3. 选择 Dify、Coze、阿里云百炼或 DeerFlow,阅读并勾选配置重置提示,然后点击「使用此方式」。 +4. 确保「启用 AI」已打开,在出现的执行方式设置中填写 API Key、应用 ID、API 地址等参数,具体字段见下方接入指南。 +5. 点击右下角「保存配置」使更改生效。 -![image](https://files.astrbot.app/docs/source/images/use/agent-runner/image-1.png) +> [!IMPORTANT] +> 切换执行方式会将配置重置为新执行方式的默认值,当前执行方式的配置不会保留。再次切回时需要重新配置;如需保留原配置,请先通过「管理配置文件」复制配置文件。 -在 WebUI 中,点击「模型提供商」->「新增提供商」,选择「Agent 执行器」,选择你想接入的平台或执行器类型,填写相关信息即可。 +当前 WebUI 无需在「模型提供商」中新建 Agent 执行器,也无需选择执行器提供商 ID。每个配置文件保存自己的执行方式和连接参数;多个机器人需要连接不同应用时,可分别使用不同配置文件。 -## 更换默认 Agent 执行器 +## 接入指南 -![image](https://files.astrbot.app/docs/source/images/use/agent-runner/image.png) - -在 WebUI 中,点击「配置」->「Agent 执行方式」,将执行器类型更换为你刚刚创建的 Agent 执行器类型,然后选择 `XX Agent 执行器提供商 ID` 为你刚刚创建的 Agent 执行器提供商的 ID,点击保存即可。 +- [Dify](../providers/agent-runners/dify.md) +- [Coze](../providers/agent-runners/coze.md) +- [阿里云百炼应用](../providers/agent-runners/dashscope.md) +- [DeerFlow](../providers/agent-runners/deerflow.md) diff --git a/docs/zh/use/astrbot-agent-sandbox.md b/docs/zh/use/astrbot-agent-sandbox.md index fd80691411..6c7a59fcff 100644 --- a/docs/zh/use/astrbot-agent-sandbox.md +++ b/docs/zh/use/astrbot-agent-sandbox.md @@ -15,7 +15,7 @@ - `Shipyard`(旧方案,仍可继续使用) - `CUA`(本地或云端电脑使用沙盒,适合需要桌面操作的场景) -在当前版本的 AstrBot 控制台中,可在“AI 配置” -> “Agent Computer Use”中选择: +在当前版本的 AstrBot 控制台中,可在“配置文件” -> “AI 配置” -> “能力” -> “使用电脑能力”中选择: - `Computer Use Runtime` = `sandbox` - `沙箱环境驱动器` = `Shipyard Neo`、`Shipyard` 或 `CUA` @@ -75,7 +75,7 @@ CUA 本身还依赖具体运行方式: 进入 WebUI: -- `配置 -> 普通配置 -> 使用电脑能力` +- `配置文件 -> AI 配置 -> 能力 -> 使用电脑能力` 然后设置: @@ -415,7 +415,7 @@ docker pull soulter/shipyard-ship:latest > [!TIP] > 请确保您的 AstrBot 版本在 `v4.12.0` 及之后。 -在 AstrBot 控制台,进入 “AI 配置” -> “Agent Computer Use”。 +在 AstrBot 控制台,进入 “配置文件” -> “AI 配置” -> “能力” -> “使用电脑能力”。 1. 将 `Computer Use Runtime` 设为 `sandbox` 2. 在 `沙箱环境驱动器` 中选择 `Shipyard Neo` 或 `Shipyard` diff --git a/docs/zh/use/command.md b/docs/zh/use/command.md index aa91d434d0..1bb6d81d85 100644 --- a/docs/zh/use/command.md +++ b/docs/zh/use/command.md @@ -40,7 +40,7 @@ AstrBot 的指令通过插件机制注册。为了保持主程序轻量,当前 常见用途: -- 添加管理员:先发送 `/sid` 获取 `UID`,再在 WebUI 的 `配置 -> 其他配置 -> 管理员 ID` 中添加。 +- 添加管理员:先发送 `/sid` 获取 `UID`,再在 WebUI 的 `配置文件 -> 平台配置 -> 基本 -> 管理员 ID` 中添加。 - 配置白名单:使用 `UMO` 或群 ID 控制哪些会话可以使用机器人。 - 配置路由规则:使用 `UMO` 区分不同平台、群聊或私聊来源。 @@ -86,7 +86,7 @@ DeerFlow 还会尝试删除旧的远端 thread;第三方路径不保证保留 - 私聊中默认普通用户可使用。 - 群聊默认「跟随对话隔离」:开启「隔离对话」且渠道实际完成隔离时,所有人可使用;关闭时仅 AstrBot 管理员可使用。管理员指配置的管理员 ID,不是自动识别的群管理员。不支持隔离的渠道仍按共享群聊限制权限。 -- 在 WebUI「管理行为 → 指令」中勾选「显示系统插件指令」,可以分别调整 `new` 和 `reset` 的权限:「所有人」「仅管理员」「仅群聊限管理员」「跟随对话隔离」。权限选择对所有配置文件生效;「跟随对话隔离」按消息所属配置文件的隔离设置判断,其他三项不随隔离设置变化。 +- 在 WebUI「插件 → 管理行为 → 指令」中勾选「显示系统插件指令」,可以分别调整 `new` 和 `reset` 的权限:「所有人」「仅管理员」「仅群聊限管理员」「跟随对话隔离」。权限选择对所有配置文件生效;「跟随对话隔离」按消息所属配置文件的隔离设置判断,其他三项不随隔离设置变化。 - 「仅管理员」同时限制私聊和群聊;「仅群聊限管理员」允许所有人私聊,群聊仅限管理员。 - 关闭「隔离对话」时,新建对话影响整个群;开启且生效时,只影响自己的对话。若要允许共享群聊的普通成员使用,可以将对应指令设为「所有人」。 - 指令的禁用、重命名仍由指令管理统一处理。 @@ -131,7 +131,7 @@ DeerFlow 还会尝试删除旧的远端 thread;第三方路径不保证保留 - 当前正在使用的 Provider 末尾会标注 `(当前使用)`。 > [!NOTE] -> 可达性检测需要在 WebUI 的 `配置 -> 普通配置 -> AI 配置` 中,展开底部的「更多配置」,开启「提供商可达性检测」后才会生效。关闭后不显示可达性标记,列表加载更快。 +> 可达性检测需要在 WebUI 的 `配置文件` 中选择对应配置文件,通过顶部搜索按钮搜索 `reachability_check`,开启「提供商可达性检测」并保存配置后才会生效。关闭后不显示可达性标记,列表加载更快。 **切换 Provider:** @@ -172,4 +172,4 @@ DeerFlow 还会尝试删除旧的远端 thread;第三方路径不保证保留 部分指令需要 AstrBot 管理员权限,例如 `/dashboard_update`、`/name`、`/op`、`/deop`、`/provider`、`/model`、`/persona` 等。 -可以通过 `/sid` 获取用户 ID,然后在 WebUI 的 `配置 -> 其他配置 -> 管理员 ID` 中添加管理员。 +可以通过 `/sid` 获取用户 ID,然后在 WebUI 的 `配置文件 -> 平台配置 -> 基本 -> 管理员 ID` 中添加管理员。 diff --git a/docs/zh/use/computer.md b/docs/zh/use/computer.md index 7da8dd5d17..2a63d5eedb 100644 --- a/docs/zh/use/computer.md +++ b/docs/zh/use/computer.md @@ -6,7 +6,7 @@ 在 WebUI 中进入: -- `配置 -> 普通配置 -> 使用电脑能力` +- `配置文件 -> AI 配置 -> 能力 -> 使用电脑能力` 核心配置项是 `Computer Use Runtime`: @@ -88,7 +88,7 @@ data/workspaces/{normalized_umo}/notes/todo.txt 管理员 ID 可在: -- `配置 -> 其他配置 -> 管理员 ID` +- `配置文件 -> 平台配置 -> 基本 -> 管理员 ID` 中配置。用户可通过 `/sid` 获取自己的 ID。 @@ -98,7 +98,7 @@ data/workspaces/{normalized_umo}/notes/todo.txt 在沙盒中,Agent 仍然可以使用 Shell、Python、文件系统工具;如果所选沙盒 profile 支持 `browser` capability,还会挂载浏览器自动化工具。 -沙盒环境驱动器可在 `配置 -> 普通配置 -> 使用电脑能力` 的沙箱配置中选择。当前常用选项包括: +沙盒环境驱动器可在 `配置文件 -> AI 配置 -> 能力 -> 使用电脑能力` 的沙箱配置中选择。当前常用选项包括: - `Shipyard Neo`:AstrBot 推荐的远程/独立部署沙盒服务,适合长期运行和多人使用。 - `CUA`:基于 [CUA](https://github.com/trycua/cua) 的本地或云端电脑使用沙盒,可提供桌面截图、鼠标、键盘、Shell、Python 和文件系统能力。 diff --git a/docs/zh/use/context-compress.md b/docs/zh/use/context-compress.md index 1dc33bb7ee..3fbd15de56 100644 --- a/docs/zh/use/context-compress.md +++ b/docs/zh/use/context-compress.md @@ -2,7 +2,7 @@ 在 v4.11.0 之后,AstrBot 引入了自动上下文压缩功能。 -![alt text](https://files.astrbot.app/docs/source/images/context-compress/image.png) +在 `配置文件` 中选择要修改的配置文件,进入 `AI 配置 → 高级 → 上下文管理策略` 设置压缩策略,然后点击右下角的 `保存配置`。 AstrBot 会在对话上下文达到**使用的对话模型上下文窗口的最大长度的 82% 时**,自动对上下文进行压缩,以确保在不丢失关键信息的情况下,尽可能多地保留对话内容。 @@ -30,12 +30,6 @@ Based on our full conversation history, produce a concise summary of key takeawa 默认情况下,当您添加模型时,AstrBot 会自动根据模型的 id,从 [MODELS.DEV](https://models.dev/) 提供的接口中获取模型的上下文窗口大小。但由于模型种类繁多,部分提供商甚至会修改模型的 id,因此 AstrBot 不能自动推断出您所添加的模型的上下文窗口大小。 -您可以手动在模型配置中设置模型的上下文窗口大小,参考下图: - -![alt text](https://files.astrbot.app/docs/source/images/context-compress/image1.png) - -> [!NOTE] -> 如果没有看到上图中的配置项,请您删除该模型,然后重新添加模型即可。 +打开 `模型提供商 → 对话`,在左侧选择模型所属的提供商,在右侧模型列表中点击已添加的模型,编辑上下文窗口大小(`max_context_tokens`)并保存。 当模型上下文窗口大小被设置为 0 时,在每次请求时,AstrBot 仍会自动从 MODELS.DEV 获取模型的上下文窗口大小。如果仍为 0,则这次请求不会启用上下文压缩功能。 - diff --git a/docs/zh/use/custom-rules.md b/docs/zh/use/custom-rules.md index 20ff30f3e4..aa435f29b0 100644 --- a/docs/zh/use/custom-rules.md +++ b/docs/zh/use/custom-rules.md @@ -7,7 +7,7 @@ 你可以把自定义规则理解为对指定消息来源更加灵活的自定义强制处理规则,其优先级高于配置文件。 -例如,原本一个消息平台使用配置文件 “default”,这个消息平台下的所有会话都按照配置文件中的规则进行处理。如果你希望对某个会话来源 A 进行特殊处理,在原来,你需要单独创建一个配置文件,然后将 A 绑定到这个配置文件中。而现在,你只需要在 WebUI 的自定义规则页中创建一个自定义规则,然后选择消息来源 A 即可。你可以定义如下规则: +例如,原本一个消息平台使用配置文件 “default”,这个消息平台下的所有会话都按照配置文件中的规则进行处理。如果你希望对某个会话来源 A 进行特殊处理,在原来,你需要单独创建一个配置文件,然后将 A 绑定到这个配置文件中。而现在,你只需要在 WebUI 的“更多功能 → 自定义规则”页(`/session-management`)中创建一个自定义规则,然后选择消息来源 A 即可。你可以定义如下规则: 1. 是否启用该消息会话来源的消息处理。如果不启用,其效果相当于将该消息会话来源拉入黑名单。 2. 是否对该消息会话来源的消息启用 LLM。如果不启用,则不会使用 AI 能力。 diff --git a/docs/zh/use/function-calling.md b/docs/zh/use/function-calling.md index 5984ae30c8..9709f46915 100644 --- a/docs/zh/use/function-calling.md +++ b/docs/zh/use/function-calling.md @@ -30,7 +30,7 @@ outline: deep 等在提供传统的指令调用的基础上,也提供了函数调用的功能。 -相关操作请在 WebUI 中管理工具的开启和关闭。 +打开 WebUI 的 `插件 → 管理行为 → 函数工具`(`/extension/components`)查看和管理工具的启用状态。人格可使用的工具范围在 `人格设定` 中配置;MCP 服务器在 `插件 → MCP` 中管理。 某些模型可能不支持函数调用,会返回诸如 `tool call is not supported`, `function calling is not supported`, `tool use is not supported` 等错误。在大多数情况下,AstrBot 能够检测到这种错误并自动帮您去除函数调用工具。如果你发现某个模型不支持函数调用,也可在 WebUI 中关闭所有调用工具,然后再次尝试。或者更换为支持函数调用的模型。 diff --git a/docs/zh/use/knowledge-base-old.md b/docs/zh/use/knowledge-base-old.md index d2bfa7c787..7015a41b68 100644 --- a/docs/zh/use/knowledge-base-old.md +++ b/docs/zh/use/knowledge-base-old.md @@ -1,4 +1,7 @@ -# AstrBot 知识库 +# AstrBot 旧版知识库 + +> [!WARNING] +> 本页保留旧版知识库的操作说明和界面截图,导航名称不适用于当前 WebUI。当前版本请参考[知识库使用文档](/use/knowledge-base)。如需访问保留的旧版界面,可在当前 `知识库` 页面点击 `切换到旧版知识库`(`/alkaid/knowledge-base`)。 ![知识库预览](https://files.astrbot.app/docs/zh/use/image-3.png) diff --git a/docs/zh/use/knowledge-base.md b/docs/zh/use/knowledge-base.md index 383c89078c..6e05f870b3 100644 --- a/docs/zh/use/knowledge-base.md +++ b/docs/zh/use/knowledge-base.md @@ -9,11 +9,11 @@ ## 配置嵌入模型 -打开服务提供商页面,点击新增服务提供商,选择 Embedding。 +打开 `模型提供商`(`/providers`),切换到 `嵌入` 标签,点击 `新增`,选择所需的提供商类型。 目前 AstrBot 支持兼容 OpenAI API 和 Gemini API 的嵌入向量服务。 -点击上面的提供商卡片进入配置页面,填写配置。 +在左侧选择提供商,在右侧填写 API 地址、API Key、模型名称等配置。 配置完成后,点击保存。 @@ -21,17 +21,15 @@ 重排序模型可以一定程度上提高最终召回结果的精度。 -和嵌入模型的配置类似,打开服务提供商页面,点击新增服务提供商,选择重排序。有关重排序模型的更多信息请参考网络。 +和嵌入模型的配置类似,打开 `模型提供商`,切换到 `重排序` 标签,点击 `新增`,选择所需的提供商类型并保存配置。 ## 创建知识库 AstrBot 支持多知识库管理。在聊天时,您可以**自由指定知识库**。 -进入知识库页面,点击创建知识库,如下图所示: +打开侧边栏的 `知识库`(`/knowledge-base`),点击 `创建知识库`。 -![image](https://files.astrbot.app/docs/source/images/knowledge-base/image.png) - -填写相关信息。在嵌入模型下拉菜单中您将看到刚刚创建好的嵌入模型和重排序模型(重排序模型可选)。 +填写名称等信息,在 `嵌入模型` 中选择刚创建的嵌入模型;如需重排序,在单独的 `重排序模型(可选)` 中选择模型,然后点击 `创建`。 > [!TIP] > 一旦选择了一个知识库的嵌入模型,请不要再修改该提供商的**模型**或者**向量维度信息**,否则将**严重影响**该知识库的召回率甚至**报错**。 @@ -44,7 +42,7 @@ AstrBot 支持多知识库管理。在聊天时,您可以**自由指定知识 ## 使用知识库 -在配置文件中,可以为不同的配置文件指定不同的知识库。 +打开 `配置文件`,选择要修改的配置文件,在 `AI 配置 → 能力 → 知识库` 中选择要使用的知识库,点击右下角的 `保存配置`。不同配置文件可以使用不同的知识库。 ## 附录:高性价比的嵌入模型申请 diff --git a/docs/zh/use/mcp.md b/docs/zh/use/mcp.md index 79e3757fda..570b75abf0 100644 --- a/docs/zh/use/mcp.md +++ b/docs/zh/use/mcp.md @@ -6,17 +6,13 @@ MCP(Model Context Protocol,模型上下文协议) 是一种新的开放标准 AstrBot v3.5.0 支持 MCP 协议,可以添加多个 MCP 服务器、使用 MCP 服务器的函数工具。 -![image](https://files.astrbot.app/docs/source/images/function-calling/image2.png) +MCP 服务器在 WebUI 的 `插件 → MCP`(`/extension/mcp`)中管理。 ## 初始状态配置 MCP 服务器一般使用 `uv` 或者 `npm` 来启动,因此您需要安装这两个工具。 -对于 `uv`,您可以直接通过 pip 来安装。可在 AstrBot WebUI 快捷安装: - -![image](https://files.astrbot.app/docs/zh/use/image.png) - -输入 `uv` 即可。 +对于 `uv`,您可以直接通过 pip 来安装。在 AstrBot WebUI 打开 `数据与日志 → 日志`(`/data/logs`),点击 `安装 pip 库`,输入 `uv` 并安装。 如果您使用 Docker 部署 AstrBot,也可以执行以下指令快捷安装。 @@ -89,11 +85,7 @@ npx -v } ``` -在 AstrBot WebUI 中设置: - -![image](https://files.astrbot.app/docs/zh/use/image-2.png) - -即可。 +在 AstrBot WebUI 打开 `插件 → MCP`,点击 `新增服务器`,填写服务器名称,将上面的 JSON 粘贴到 `服务器配置` 中。可先点击 `测试连接`;勾选 `保存后连接服务器` 后点击 `保存`,即可连接服务器。 参考链接: diff --git a/docs/zh/use/plugin.md b/docs/zh/use/plugin.md index 77f30eeba9..9ea89d8ebe 100644 --- a/docs/zh/use/plugin.md +++ b/docs/zh/use/plugin.md @@ -2,6 +2,6 @@ 在 `3.4.0` 版本之后,AstrBot 将插件命名为 `Star`。AstrBot 是一个高度模块化的项目,通过插件可以发挥这种模块化的能力,实现各种功能。 -使用 `/plugin` 可以看到所有插件。在管理面板中也可管理已经安装的插件。 +使用 `/plugin` 可以看到所有插件。在管理面板的 `插件 → 插件`(`/extension/plugins`)中可管理已安装的插件,打开 `插件市场`(`/extension/plugins/market`)可搜索和安装插件。MCP、技能和管理行为分别位于插件工作区顶部的标签页中。 如果想自己开发插件,详见 [几行代码实现一个插件](/dev/star/plugin)。 \ No newline at end of file diff --git a/docs/zh/use/proactive-agent.md b/docs/zh/use/proactive-agent.md index 61fc64b4f8..0f60f23ffa 100644 --- a/docs/zh/use/proactive-agent.md +++ b/docs/zh/use/proactive-agent.md @@ -14,12 +14,12 @@ AstrBot 引入了主动 Agent(Proactive Agent)系统,使 AstrBot 不仅能 - **自我唤醒**:AstrBot 会在预定时间自动唤醒并执行任务。 - **任务反馈**:执行完成后,AstrBot 会将结果告知任务布置方。 -- **WebUI 管理**:你可以在 WebUI 的“定时任务”页面查看、编辑或删除已设置的任务。 +- **WebUI 管理**:你可以在 WebUI 的“更多功能 → 未来任务”页面查看、编辑或删除已设置的任务。 ### 如何使用 > [!TIP] -> 首先,确保配置中 “主动型能力” 已启用。 +> 首先,在 `配置文件` 页面选择对应配置文件,进入 `AI 配置 → 能力 → 主动型能力`,启用后点击右下角的 `保存配置`。 主 Agent 拥有管理定时任务的能力。你可以直接对它说: - “明天早上 8 点提醒我开会” @@ -28,7 +28,7 @@ AstrBot 引入了主动 Agent(Proactive Agent)系统,使 AstrBot 不仅能 主 Agent 会调用内置的定时任务工具来安排这些计划。 -你可以在 AstrBot WebUI 左侧导航栏中点击 **未来任务** 来查看和管理所有未来任务。 +你可以在 AstrBot WebUI 左侧导航栏中展开 **更多功能**,点击 **未来任务**(`/cron`) 来查看和管理所有未来任务。 ![](https://files.astrbot.app/docs/source/images/proactive-agent/image-1.png) diff --git a/docs/zh/use/skills.md b/docs/zh/use/skills.md index c9d7d4f25c..31890e8ee7 100644 --- a/docs/zh/use/skills.md +++ b/docs/zh/use/skills.md @@ -12,9 +12,7 @@ AstrBot 在 v4.13.0 之后引入了对 Anthropic Skills 的支持,使得用户 ## 上传 Skills 到 AstrBot -进入 AstrBot 管理面板,导航到 `插件` 页面,找到 `Skills`。 - -![Skills](https://files.astrbot.app/docs/source/images/skills/image.png) +进入 AstrBot 管理面板,打开 `插件 → 技能`(`/extension/skills`),点击 `上传技能`。 你可以上传 Skills,上传格式要求如下: @@ -55,7 +53,7 @@ Skills 提供了 Agent 操作说明书,并且内容通常包含 Python 代码 - Local(Agent 将在你的 AstrBot 运行环境中运行。**请谨慎使用,因为这会允许 Agent 在你的环境执行任意代码,可能带来安全风险**) - Sandbox (Agent 在隔离化的沙盒环境中运行。**需要先启动 AstrBot 沙盒模式**,请参考:[沙盒模式](/use/astrbot-agent-sandbox),如果这个模式下不启动沙盒模式,将不会将 Skills 传给 Agent) -你可以在 `配置` 页面 - 使用电脑能力 中选择默认的执行环境。 +在 `配置文件` 页面选择要修改的配置文件,进入 `AI 配置 → 能力 → 使用电脑能力`,设置执行环境后点击右下角的 `保存配置`。 > [!NOTE] > 需要说明的是,如果您使用 Local 作为执行环境,AstrBot 目前仅允许 **AstrBot 管理员**请求时才真正让 Agent 操作你的本地环境,普通用户将会被禁止,Agent 将无法通过 Shell、Python 等 Tool 在本地环境执行代码,会收到相应的权限限制提示,如 `Sorry, I cannot execute code on your local environment due to permission restrictions.`。 diff --git a/docs/zh/use/subagent.md b/docs/zh/use/subagent.md index 5c2a20d727..1166b4ee71 100644 --- a/docs/zh/use/subagent.md +++ b/docs/zh/use/subagent.md @@ -13,11 +13,11 @@ SubAgent 编排是 AstrBot 提供的一种高级 Agent 组织方式。它允许 2. **调用失误**:面对大量工具,LLM 容易混淆工具用途或产生错误的调用参数。 3. **逻辑复杂**:主 Agent 既要负责对话,又要负责组织和调用大量工具,负担过重。 -通过 SubAgent 编排,主 Agent 仅负责与用户对话以及**任务委派**。具体的工具调用由专门的 SubAgent 负责。 +通过子代理编排,主 Agent 可以与用户对话、使用自身工具,也可以将任务委派给专门的 SubAgent。 ## 工作原理 -1. **主 Agent 委派**:开启 SubAgent 模式后,主 Agent 只能看到一系列名为 `transfer_to_` 的委派工具。 +1. **主 Agent 委派**:开启子代理编排后,主 Agent 会获得名为 `transfer_to_` 的委派工具,同时仍可使用自身工具。开启“主 LLM 去重重复工具”后,与子代理重叠的工具会从主 Agent 的工具列表中隐藏。 2. **任务移交**:当主 Agent 认为需要执行某项任务时,它会调用对应的委派工具,将任务描述传递给 SubAgent。 3. **子 Agent 执行**:SubAgent 接收到任务后,使用其挂载的工具进行操作,并将结果整理后回传给主 Agent。 4. **结果反馈**:主 Agent 收到 SubAgent 的执行结果,继续与用户对话。 @@ -26,22 +26,24 @@ SubAgent 编排是 AstrBot 提供的一种高级 Agent 组织方式。它允许 ## 配置方法 -在 AstrBot WebUI 中,点击左侧导航栏的 **SubAgent 编排**。 +在 AstrBot WebUI 中,展开左侧导航栏的 **更多功能**,点击 **子代理编排**(`/subagent`)。 ### 1. 启用 SubAgent 模式 -在页面顶部开启“启用 SubAgent 编排”。 +在页面顶部开启“启用子代理编排”。 ### 2. 创建 SubAgent -点击“新增 SubAgent”按钮: +点击“新增子代理”按钮: - **Agent 名称**:用于生成委派工具名(如 `transfer_to_weather`)。建议使用英文小写和下划线。 - **选择 Persona**:选择一个预设的 Persona,即人格,作为该子 Agent 的基础性格、行为指导和可以使用的 Tools 集合。你可以在“人格设定”页面创建和管理 Persona。 - **对主 LLM 的描述**:这段描述会告诉主 Agent 这个子 Agent 擅长做什么,以便主 Agent 准确委派。 -- **分配工具**:选择该子 Agent 可以调用的工具。 +- **工具**:子代理继承所选人格的工具;请到“人格设定”页面编辑该人格的工具范围。 - **Provider 覆盖(可选)**:你可以为特定的子 Agent 指定不同的模型提供商。例如,主 Agent 使用 GPT-4o,而负责简单查询的子 Agent 使用 GPT-4o-mini 以节省成本。 +完成设置后,点击页面上的 `保存`。 + ## 最佳实践 - **职责单一**:每个 SubAgent 应该只负责一类相关的任务(如:搜索、文件处理、智能家居控制)。 diff --git a/docs/zh/use/unified-webhook.md b/docs/zh/use/unified-webhook.md index 25e22d06e4..aa91cec721 100644 --- a/docs/zh/use/unified-webhook.md +++ b/docs/zh/use/unified-webhook.md @@ -17,7 +17,7 @@ 1. 拥有一个域名(如 example.com)和公网 IP 服务器 2. 配置 DNS 解析(如 astrbot.example.com) 3. 配置反向代理,将域名的 80 或 443 端口请求转发到 AstrBot 的 WebUI 端口(默认为 6185) -4. 前往 AstrBot `配置文件` 页,点击 `系统`,将 `对外可达的回调接口地址` 填写为配置的 URL 地址。(如 https://astrbot.example.com),点击保存,等待重启。 +4. 前往 AstrBot `设置 → 常规 → 基础运行`,将 `对外可达的回调接口地址` 填写为配置的 URL 地址。(如 https://astrbot.example.com),点击保存,等待重启。 在之后配置各个平台适配器时,选择开启 `统一 Webhook 模式 (unified_webhook_mode)`。 diff --git a/docs/zh/use/websearch.md b/docs/zh/use/websearch.md index 342da22967..d631fd1503 100644 --- a/docs/zh/use/websearch.md +++ b/docs/zh/use/websearch.md @@ -15,9 +15,7 @@ AstrBot 内置的网页搜索功能依赖大模型提供 `函数调用` 能力 AstrBot 当前支持 7 种网页搜索源接入方式:`Tavily`、`BoCha`、`百度 AI 搜索`、`Brave`、`Firecrawl`、`Exa`、`AnySearch`。 -![image](https://files.astrbot.app/docs/source/images/websearch/image.png) - -进入 `配置`,下拉找到网页搜索,您可选择 `Tavily`、`BoCha`、`百度 AI 搜索`、`Brave`、`Firecrawl` 、`Exa` 或`AnySearch`。 +进入 `配置文件`,选择要修改的配置文件,在 `AI 配置 → 能力 → 网页搜索` 中启用网页搜索,您可选择 `Tavily`、`BoCha`、`百度 AI 搜索`、`Brave`、`Firecrawl` 、`Exa` 或`AnySearch`。填写所需参数后,点击右下角的 `保存配置`。 ### Tavily diff --git a/docs/zh/use/webui.md b/docs/zh/use/webui.md index 43400dd2ea..b5d38e1242 100644 --- a/docs/zh/use/webui.md +++ b/docs/zh/use/webui.md @@ -2,7 +2,24 @@ AstrBot 管理面板具有管理插件、查看日志、可视化配置、查看统计信息等功能。 -![image](https://files.astrbot.app/docs/source/images/webui/image-4.png) +## 菜单与旧入口对照 + +以下入口对应当前 WebUI 的默认侧边栏。若你调整过侧边栏,可在左下角 `设置 → 外观 → 自定义侧边栏` 中查看或恢复默认布局。 + +| 旧入口或称呼 | 当前入口 | +| --- | --- | +| 模型提供商 → 新增提供商 → Agent 执行器 | 配置文件 → 选择配置文件 → AI 配置 → AI 标题旁的 `…` → 更换执行方式 | +| 数据 / 数据统计 | 数据与日志 → 统计 | +| 对话管理 / 对话数据 | 数据与日志 → 对话 | +| 日志 / 平台日志 | 数据与日志 → 日志 | +| 追踪 | 数据与日志 → 追踪 | +| 配置 → 普通配置 | 配置文件 → 选择配置文件 | +| 配置文件 → 系统配置 | 左下角设置 → 常规、外观、网络或安全,按配置用途选择 | +| 指令管理 | 插件 → 管理行为 → 指令 | +| 独立 MCP / 技能入口 | 插件 → MCP / 技能 | +| 自定义规则 / 未来任务 / 子代理编排 | 更多功能 → 对应功能 | + +旧日志、追踪、对话和统计页面地址仍会跳转到对应的新标签页。Agent 执行器现在随配置文件保存,不再通过新增模型提供商创建;操作步骤见 [Agent 执行器](./agent-runner.md)。 ## 管理面板的访问 @@ -21,7 +38,7 @@ AstrBot WebUI支持基于 TOTP(Time-based One-Time Password)的双因素认 ### 开启双因素认证 -1. 在左侧菜单中依次点击 配置文件 → 系统配置。 +1. 点击左下角 `设置 → 安全`,找到 `WebUI 安全`。 2. 打开“启用 WebUI TOTP 双因素认证”开关,WebUI将显示二维码。 3. 使用任意支持 TOTP 的验证器应用(如 Google Authenticator 等)扫描二维码。 4. 输入验证器应用生成的 6 位验证码完成验证。 @@ -59,37 +76,44 @@ ChatUI 支持以下常用能力: ## 可视化配置 -在管理面板中,你可以通过可视化配置来配置 AstrBot 的插件。点击左栏 `配置` 即可进入配置页面。 +点击左栏 `配置文件`,先从页面顶部选择要修改的配置文件。可视化配置按 `AI 配置`、`平台配置`、`插件配置` 等分区展示,也可以使用顶部搜索定位配置项。 -![image](https://files.astrbot.app/docs/source/images/webui/image-3.png) +- `AI 配置` 中,内置 AI 的设置分为 `模型`、`人格`、`能力`、`高级`;AI 标题旁的 `… → 更换执行方式` 用于接入第三方 Agent。 +- `平台配置` 中设置管理员、消息触发方式等行为。 +- `插件配置` 中选择该配置文件启用的插件集合。单个插件的参数请在 `插件` 页面中点击对应插件的齿轮图标(`插件配置`)修改。 -当修改完配置后,你需要点击右下角 `保存` 按钮才能成功保存配置。 +修改完成后,点击右下角磁盘图标的 `保存配置` 按钮,确认保存成功提示。 -使用右下角第一个圆形按钮可以切换至 `代码编辑配置`。在 `代码编辑配置` 中,你可以直接编辑配置文件。 +点击右下角 `{}` 图标的 `编辑配置文件` 按钮,可直接编辑当前配置文件的 JSON。编辑后先点击 `应用此配置`,将内容暂存到可视化编辑器,再关闭编辑窗口并点击 `保存配置`。 -编辑完后首先点击`应用此配置`,此时配置将应用到可视化配置中,然后再点击右下角`保存`按钮来保存配置。如果你不点击`应用此配置`,那么你的修改将不会生效。 +### 系统设置 -![alt text](https://files.astrbot.app/docs/source/images/webui/image-5.png) +全局设置位于左下角 `设置`,不在配置文件选择器中: -## 插件 +- `常规`:时区、外部回调地址、日志和缓存。 +- `外观`:侧边栏、主题和文本转图像。 +- `网络`:HTTP 代理、Python 依赖源和 GitHub 加速地址。 +- `安全`:WebUI HTTPS、登录限速和 TOTP。 +- `维护`:备份、恢复和重启。 +- `OpenAPI`:开发者访问密钥。 -在管理面板中,你可以通过左栏的 `插件` 来查看已安装的插件,以及安装新插件。 +系统配置修改后自动保存,请确认保存成功提示;如果页面提示需要重启,再按提示重启 AstrBot。 -点击插件市场标签栏,你可以浏览由 AstrBot 官方上架的插件。 +## 插件 -![image](https://files.astrbot.app/docs/source/images/webui/image-1.png) +点击左栏 `插件`,顶部可切换 `插件`、`技能`、`MCP` 和 `管理行为`。在 `插件` 标签内,通过 `已安装` 与 `插件市场` 切换查看本地插件和市场插件。 -你也可以点击右下角 + 按钮,以 URL / 文件上传的方式手动安装插件。 +在已安装或插件市场页面,也可以点击右下角 `安装插件`(+)按钮,以 URL / 文件上传的方式手动安装插件。 > 由于插件更新机制,AstrBot Team 无法完全保证插件市场中插件的安全性,请您仔细甄别。因为插件原因造成损失的,AstrBot Team 不予负责。 ### 插件加载失败处理 -如果插件加载失败,管理面板会显示错误信息,并提供 **“尝试一键重载修复”** 按钮。这允许你在修复环境(如安装缺失依赖)或修改代码后,无需重启整个程序即可快速重新加载插件。 +如果插件加载失败,管理面板会显示错误信息,并在 `加载失败插件` 列表中提供 **“重载”** 按钮。这允许你在修复环境(如安装缺失依赖)或修改代码后,无需重启整个程序即可快速重新加载插件。 -## 数据 +## 数据与日志 {#数据} -点击管理面板左侧的 `数据`,可以在同一页面通过顶部标签切换 `统计`、`对话`、`日志` 和 `追踪`。 +点击管理面板左侧的 `数据与日志`,可以在同一页面通过顶部标签切换 `统计`、`对话`、`日志` 和 `追踪`。 ### 统计 @@ -107,7 +131,7 @@ ChatUI 支持以下常用能力: ### 日志 -`日志` 页面显示 AstrBot 的实时运行日志,可以按日志级别筛选,也可以从页面中安装缺失的 Pip 库。需要查看 DEBUG 日志时,请先在 `配置文件 -> 系统配置` 中开启控制台 DEBUG 日志级别。 +`日志` 页面显示 AstrBot 的实时运行日志,可以按日志级别筛选,也可以从页面中安装缺失的 Pip 库。需要查看 DEBUG 日志时,请先在 `设置 → 常规 → 日志` 中将 `控制台日志级别` 设为 `DEBUG`。 ### 追踪 @@ -118,7 +142,7 @@ ChatUI 支持以下常用能力: ## 指令管理 -通过左侧菜单 `指令管理`,可以集中管理所有已注册的指令,默认不显示系统插件。 +通过 `插件 → 管理行为 → 指令`,可以集中管理所有已注册的指令,默认不显示系统插件。 支持按插件、类型(指令 / 指令组 / 子指令)、权限与状态过滤,配合搜索框快速定位。指令组行可展开查看子指令,徽章显示子指令数量,子指令行会缩进区分层级。 @@ -128,7 +152,9 @@ ChatUI 支持以下常用能力: 在 AstrBot 启动时,会自动检查管理面板是否需要更新,如果需要,第一条日志(黄色)会进行提示。 -使用 `/dashboard_update` 命令可以手动更新管理面板(管理员指令)。 +使用浏览器版 WebUI 时,打开右上角 `⋮ → 更新 AstrBot`,展开 `高级设置`,在 `单独更新管理面板到最新版本` 中点击 `下载并更新`。更新成功后页面会自动刷新。桌面端的更新入口会打开桌面应用更新对话框。 + +也可以使用 `/dashboard_update` 命令手动更新管理面板(管理员指令)。 管理面板文件在 data/dist 目录下。如果需要手动替换,请在 https://github.com/AstrBotDevs/AstrBot/releases/ 下载 `dist.zip` 然后解压到 data 目录下。