Skip to content

赵月辉 / fastgpt-migrated

Go to a project
Commit 0f815cc2 by DigHuang Committed by GitHub
Options

docs: update ai settings guide (#6894) 

* docs: update ai settings guide

* fix: ci pnpm version error
parent 45628a02
Showing with 544 additions and 208 deletions
document/content/guide/build/general/ai_settings.en.mdx
---
title: AI Configuration Parameters
description: FastGPT AI configuration parameters explained
title: AI Settings
description: FastGPT AI settings explained
---
import { Alert } from '@/components/docs/Alert';
The AI Chat module in FastGPT includes an advanced configuration section with various model parameters. This guide explains what each setting does.
AI settings control how AI Chat nodes behave in apps and Workflows, including model selection, response length, image recognition, response format, and reasoning display. This guide explains what each option in the settings modal means and how to choose values for common scenarios.
## Where to Find It
In the app editor, find the **AI Settings** section, select an AI model, and click the settings button on the right side of the model selector to open the AI settings modal.
In a Workflow, click the AI model configuration for the **AI Chat** node. You can open the same settings modal from the settings button on the right.
<Alert icon="🤖" context="success">
If you do not have specific requirements, selecting a suitable AI model and keeping the other settings at their defaults is usually enough.
</Alert>
| | | |
| --- | --- | --- |
| ![alt text](/imgs/image-51.png) | ![alt text](/imgs/image-52.png) | ![alt text](/imgs/image-53.png) |
## Stream Response (Workflow AI Chat only)
## Why Some Options May Be Hidden
Not every option is always shown. The modal only displays settings supported by the selected model. For example, if a model does not support image recognition, the image recognition switch is hidden. If a model does not support reasoning settings, those options are hidden as well.
## Basic Settings
### AI Model
Select the AI model used by the current app or node. Different models vary in response quality, cost, context length, and tool calling capability.
Previously called "Return AI Content," now renamed to "Stream Response."
The model section displays three types of information:
This is a toggle. When enabled, the AI Chat module streams its output to the browser (API response) in real time. When disabled, the model is called in non-streaming mode and the output is not sent to the browser. However, the generated content can still be accessed via the [AI Reply] output and connected to other modules for further use.
- **Credit cost**: A reference cost for model calls. Input content and model output are usually priced separately.
- **Max context**: The amount of content the model can reference in one request. A larger context window is better for long documents and long conversations.
- **Tool calling**: If supported, the model can use selected app tools to query data, run calculations, or call external capabilities.
### Max Context
### Max Histories
The maximum number of tokens the model can handle.
Controls how many previous conversation rounds the AI can reference when answering.
### Function Calling
Higher values make it easier for the AI to use earlier context, but they also add more content to the request, which may increase cost and slow down responses. Lower values may prevent the model from using useful prior context.
Models that support function calling are more accurate when using tools.
If you do not have a specific requirement, use the default value. Customer support and Knowledge Base Q&A apps usually only need a small number of history rounds.
### Max Tokens
Controls the maximum length of a single AI response.
When enabled, use the slider to limit response length. If the value is too low, the response may be cut off early. A higher value allows the model to generate more complete answers, but may also increase cost.
Use a lower value for concise answers. Use a higher value when generating plans, articles, or longer explanations.
### Temperature
Lower values produce more focused, deterministic responses (in practice, the difference is subtle).
Controls how stable the response is.
Lower values produce more stable responses and are better for customer support, Knowledge Base Q&A, and scenarios with clear rules. Higher values produce more varied responses and are better for writing, brainstorming, and creative content.
Common choices:
- Customer support and Knowledge Base Q&A: use a lower value.
- Copywriting, stories, and creative suggestions: use a higher value.
- If unsure: keep the default.
### Top_p
Top_p also controls response randomness, with some overlap with temperature.
In most cases, avoid adjusting temperature and Top_p at the same time. If temperature already gives the result you want, keep Top_p disabled or at its default.
### Stop
Stops the AI response when specified content appears.
Most chat scenarios do not need this setting. Use it only when the model should stop after outputting a fixed marker. Separate multiple stop strings with `|`, for example: `end|stop`.
### Response Format
Controls the format of the AI response.
For regular chat, customer support, and Knowledge Base Q&A, keep the default. Change this only when a later step needs to read the response in a fixed format.
If you select `json_schema`, you also need to provide the corresponding schema. This option is suitable when the model must return content in a fixed structure.
### Image Recognition
If the selected model supports image recognition, this setting controls whether the AI can read images.
When enabled, the AI can read user-uploaded images or image content from file links. For example, if a user uploads a screenshot, poster, or table image, the model can answer based on the image content.
If the modal shows that the selected model does not support image recognition, switch to a model that supports it.
### Hide AI Output
When enabled, AI-generated content is not shown directly to the user, but it can still be passed to downstream nodes through the AI response output. For example, the AI can first organize an internal result, and the next node can rewrite it into the final response.
## Reasoning Settings
### Max Output Tokens
Some models can generate reasoning content before the final answer. When you select one of these models, the modal shows reasoning settings.
The maximum number of tokens in the response. Note: this is the response token limit, not the context token limit.
### Reasoning Effort
Typically: max output = min(model's max output limit, max context - used context)
Controls how much reasoning the model performs.
Because of this, you generally don't set max context to the model's actual maximum — instead, reserve space for the response. For example, a 128k model might use max_context=115000.
- **Default**: Use the model's default behavior.
- **None**: Try to answer directly. This is suitable for simple questions.
- **Minimal / Low / Medium / High / Extra high**: Use stronger reasoning for more complex questions.
Reasoning effort follows OpenAI's `reasoning_effort` convention, with ai-proxy adapting it to the parameter format required by each model provider. For the full rules, see [ai-proxy reasoning compatibility](https://github.com/labring/aiproxy/blob/main/docs/REASONING_COMPATIBILITY.md).
<details>
<summary>OpenAI-Compatible Enum and Default Budget Mapping</summary>
| FastGPT option | OpenAI-compatible value | Default budget |
| --- | --- | --- |
| Default | Do not explicitly send `reasoning_effort` | Use the model default |
| None | `none` | `0` |
| Minimal | `minimal` | `1024` |
| Low | `low` | `2048` |
| Medium | `medium` | `8192` |
| High | `high` | `16384` |
| Extra high | `xhigh` | `32768` |
If an upstream provider only supports a token budget instead of discrete effort levels, ai-proxy uses the table above to convert effort to budget. When normalizing budget back to effort, `<=0` maps to `none`, `1-1024` maps to `minimal`, `1025-4096` maps to `low`, `4097-12288` maps to `medium`, `12289-24576` maps to `high`, and anything higher maps to `xhigh`.
</details>
<details>
<summary>OpenAI / OpenAI Responses</summary>
| Target format | Output field | Mapping |
| --- | --- | --- |
| OpenAI Chat / Completions | `reasoning_effort` | Writes `none/minimal/low/medium/high/xhigh` as-is |
| OpenAI Responses | `reasoning.effort` | Writes `none/minimal/low/medium/high/xhigh` as-is |
OpenAI Chat / Completions only parses `reasoning_effort`. When Gemini, Claude, or other request formats are converted to an OpenAI-compatible format, they are first normalized to this field.
</details>
<details>
<summary>Google Gemini</summary>
Gemini native requests are parsed from `generationConfig.thinkingConfig`, including `thinkingLevel`, `thinkingBudget`, and `includeThoughts`. When writing to Gemini upstreams, ai-proxy chooses either `thinkingLevel` or `thinkingBudget` based on the model family.
| OpenAI-compatible value | Gemini 3+ Pro | Gemini 3+ non-Pro | gemini-2.5-pro | gemini-2.5-flash | gemini-2.5-flash-lite |
| --- | --- | --- | --- | --- | --- |
| `none` | `thinkingLevel=low` | `thinkingLevel=minimal` | `thinkingBudget=128` | `thinkingBudget=0` | `thinkingBudget=0` |
| `minimal` | `thinkingLevel=low` | `thinkingLevel=minimal` | `thinkingBudget=1024` | `thinkingBudget=1024` | `thinkingBudget=1024` |
| `low` | `thinkingLevel=low` | `thinkingLevel=low` | `thinkingBudget=2048` | `thinkingBudget=2048` | `thinkingBudget=2048` |
| `medium` | `thinkingLevel=low` | `thinkingLevel=medium` | `thinkingBudget=8192` | `thinkingBudget=8192` | `thinkingBudget=8192` |
| `high` | `thinkingLevel=high` | `thinkingLevel=high` | `thinkingBudget=16384` | `thinkingBudget=16384` | `thinkingBudget=16384` |
| `xhigh` | `thinkingLevel=high` | `thinkingLevel=high` | `thinkingBudget=32768` | `thinkingBudget=24576` | `thinkingBudget=24576` |
Gemini 2.5 models clamp the budget to the model's supported range. Some Gemini models cannot fully disable thinking, so `none` falls back to the minimum supported level or budget.
</details>
<details>
<summary>Claude / Anthropic / Bedrock / Vertex AI</summary>
Claude native requests are parsed from `thinking` and `output_config`. When writing to Anthropic, AWS Bedrock Claude, or Vertex AI Claude, the payload still follows Claude's thinking format.
| OpenAI-compatible value | Legacy / budget mode | Adaptive mode |
| --- | --- | --- |
| `none` | `thinking.type=disabled` | `thinking.type=disabled`; may be removed for some adaptive-only models |
| `minimal` | `thinking.type=enabled`, `budget_tokens=1024` | `thinking.type=adaptive`, `output_config.effort=low` |
| `low` | `thinking.type=enabled`, `budget_tokens=2048` | `thinking.type=adaptive`, `output_config.effort=low` |
| `medium` | `thinking.type=enabled`, `budget_tokens=8192` | `thinking.type=adaptive`, `output_config.effort=medium` |
| `high` | `thinking.type=enabled`, `budget_tokens=16384` | `thinking.type=adaptive`, `output_config.effort=high` |
| `xhigh` | `thinking.type=enabled`, `budget_tokens=32768` | `thinking.type=adaptive`, `output_config.effort=max` |
Budget mode ensures `budget_tokens < max_tokens` and raises too-small budgets to the minimum accepted by the upstream provider.
</details>
<details>
<summary>Ali DashScope / Qwen / QwQ / GLM / Kimi-Compatible Models</summary>
| OpenAI-compatible value | Models with `thinking_budget` support | Models without budget support |
| --- | --- | --- |
| `none` | `enable_thinking=false`; remove `thinking_budget` | `enable_thinking=false` |
| `minimal` | `enable_thinking=true`, `thinking_budget=1024` | `enable_thinking=true` |
| `low` | `enable_thinking=true`, `thinking_budget=2048` | `enable_thinking=true` |
| `medium` | `enable_thinking=true`, `thinking_budget=8192` | `enable_thinking=true` |
| `high` | `enable_thinking=true`, `thinking_budget=16384` | `enable_thinking=true` |
| `xhigh` | `enable_thinking=true`, `thinking_budget=32768` | `enable_thinking=true` |
ai-proxy currently treats `qwen3-*`, `qwq-*`, and Ali-compatible models whose names contain `glm` or `kimi` as supporting `thinking_budget`. Non-streaming `qwen3-*` requests are forced to disable thinking, while `qwq-*` requests are forced to streaming mode.
</details>
<details>
<summary>Zhipu / DeepSeek / Doubao / Moonshot Kimi</summary>
These providers currently preserve only the on/off meaning. They do not preserve budget or fine-grained effort levels.
| Provider | OpenAI-compatible value | Upstream field |
| --- | --- | --- |
| Zhipu / DeepSeek / Doubao | `none` | `thinking.type=disabled` |
| Zhipu / DeepSeek / Doubao | `minimal/low/medium/high/xhigh` | `thinking.type=enabled` |
| Moonshot / Kimi models with switch support | `none` | `thinking.type=disabled`; remove `reasoning_effort` |
| Moonshot / Kimi models with switch support | `minimal/low/medium/high/xhigh` | `thinking.type=enabled`; remove `reasoning_effort` |
| Moonshot / Kimi models without switch support | Any value | Remove `reasoning_effort` and omit `thinking` |
### System Prompt
For Moonshot / Kimi, whether `thinking.type` can be written depends on the actual upstream model name after channel mapping.
Placed at the beginning of the context array with role `system` to guide the model's behavior.
</details>
### Memory Rounds (Basic Mode only)
Some models may not fully support every reasoning option. If an error occurs after switching the option, change it back to Default.
Configures how many conversation rounds the model retains. If the context exceeds the model's limit, the system automatically truncates to stay within bounds.
### Hide AI Reasoning
So even if you set 30 rounds, the actual number at runtime may be fewer.
\ No newline at end of file
When enabled, users only see the final answer and do not see the AI's reasoning process. During app debugging, you can temporarily disable this option to inspect the model's intermediate reasoning.
document/content/guide/build/general/ai_settings.mdx
---
title: AI 相关参数配置说明
description: FastGPT AI 相关参数配置说明
title: AI 配置说明
description: FastGPT AI 配置说明
---
import { Alert } from '@/components/docs/Alert';
在 FastGPT 的 AI 对话模块中，有一个 AI 高级配置，里面包含了 AI 模型的参数配置，本文详细介绍这些配置的含义。
AI 配置用于调整应用或工作流中 AI 对话节点的模型、回复长度、图片识别、回复格式和思考展示等行为。本文主要介绍配置弹窗中的各项含义，以及常见场景下的选择方式。
## 配置入口
在应用编辑页中，找到 **AI 配置** 区域，选择 AI 模型后，点击模型选择框右侧的设置按钮，即可打开 AI 配置弹窗。
在工作流中，点击 **AI 对话** 节点的 AI 模型配置项，也可以通过右侧设置按钮打开同一个配置弹窗。
<Alert icon="🤖" context="success">
如果暂时没有特殊要求，通常只需要选择合适的 AI 模型，其他参数保持默认即可。
</Alert>
| | | |
| --- | --- | --- |
| ![alt text](/imgs/image-51.png) | ![alt text](/imgs/image-52.png) | ![alt text](/imgs/image-53.png) |
## 流响应（高级编排 AI 对话 特有）
## 配置会不会都显示？
旧版名字叫做：返回 AI 内容；新版改名：流响应。
不会。弹窗会根据当前模型的能力显示可用配置。例如，模型不支持图片识别时，不会提供图片识别开关；模型不支持思考配置时，也不会显示对应选项。
这是一个开关，打开的时候，当 AI 对话模块运行时，会将其输出的内容返回到浏览器（API响应）；
如果关闭，会强制使用非流模式调用模型，并且 AI 输出的内容不会返回到浏览器，但是生成的内容仍可以通过【AI回复】进行输出。你可以将【AI回复】连接到其他模块中进行二次使用。
## 基础配置
### 最大上下文
### AI 模型
代表模型最多容纳的文字数量。
用于选择当前应用或节点使用的 AI 模型。不同模型在回答能力、价格、可处理内容长度、工具调用能力等方面会有差异。
### 函数调用
模型下面会显示三类信息：
支持函数调用的模型，在使用工具时更加准确。
- **积分价格**：模型调用时的积分消耗参考，通常会区分输入内容和模型回复。
- **最大上下文**：模型单次请求可参考的内容长度。数值越大，越适合长文档、长对话等场景。
- **工具调用**：如果显示支持，说明该模型可以配合应用中选择的工具完成查询、计算或外部能力调用。
### 温度
### 记忆轮数
越低回答越严谨，少废话（实测下来，感觉差别不大）
控制 AI 回答时最多参考前面多少轮聊天。
数值越大，AI 越容易参考更早的对话，但也会带入更多内容，可能增加消耗并影响响应速度。数值过小，则可能无法利用前文信息。
如果没有明确需求，建议先使用默认值。客服、知识库问答类应用通常保留少量历史轮数即可。
### 回复上限
最大回复 token 数量。注意，是回复的Tokens！不是上下文 tokens。
控制 AI 一次最多回答多长。
打开后，可以通过滑块限制模型回复长度。设置过低时，回复可能被提前截断；设置较高时，模型可以生成更完整的内容，但也可能增加消耗。
如果希望回答简短，可以适当调低；如果需要生成方案、文章或较长说明，可以适当调高。
### 温度
控制回答的稳定程度。
数值较低时，回答更稳定，更适合客服、知识库问答、规则明确的场景。数值较高时，回答更发散，更适合写作、头脑风暴、创意内容等场景。
常见选择：
- 客服、知识库问答：建议偏低。
- 文案、故事、创意建议：可以适当调高。
- 不确定时：建议保持默认。
### Top_p
Top_p 也是控制回复随机性的参数，作用和温度有一定重叠。
通常不建议同时调整温度和 Top_p。如果已经通过温度获得了期望效果，可以保持 Top_p 关闭或默认。
### 停止序列
当 AI 回复中出现指定内容时，会停止继续输出。
普通聊天一般不需要设置。只有在需要模型输出到某个固定标记就结束时才使用。多个停止词可以用 `|` 分隔，例如：`结束|stop`。
### 回复格式
控制 AI 的回答格式。
普通聊天、客服问答、知识库问答通常保持默认即可。只有当后续流程需要读取固定格式的内容时，才需要修改该配置。
如果选择 `json_schema`，还需要填写对应的格式要求。该选项适合需要模型按固定结构返回内容的场景。
### 图片识别
如果模型支持图片识别，这里可以控制 AI 是否读取图片。
打开后，AI 可以读取用户上传的图片，或识别文件链接中的图片内容。例如用户上传截图、海报或表格图片时，模型可以结合图片内容进行回答。
如果弹窗里显示“该模型不支持图片识别”，需要换成支持图片识别的模型。
### 隐藏 AI 输出
打开后，AI 生成的内容不会直接展示给用户，但仍然可以通过 AI 回复输出交给后续节点继续处理。例如先让 AI 整理内部结果，再由下一个节点改写成最终回复。
## 思考配置
部分模型支持先生成思考过程，再输出最终回答。选择这类模型时，弹窗会显示思考配置。
### 思考配置
通常，回复上限=min(模型允许的最大回复上限, 最大上下文-已用上下文)
用于控制模型的思考强度。
所以，一般配置模型时，不会把最大上下文配置成模型实际最大上下文，而是预留预定空间给回答，例如 128k 模型，可以配置 max_context=115000
- **默认**：使用模型默认配置。
- **不思考**：尽量直接回答，适合简单问题。
- **极简思考 / 轻量思考 / 标准思考 / 深度思考 / 极致思考**：问题越复杂，可以选择更高的思考强度。
思考强度配置对齐 OpenAI 规范中的 `reasoning_effort`，并通过 ai-proxy 适配不同模型平台的参数格式。完整规则可参考 [ai-proxy reasoning compatibility](https://github.com/labring/aiproxy/blob/main/docs/REASONING_COMPATIBILITY.zh.md)。
<details>
<summary>OpenAI 兼容枚举与默认 budget 映射</summary>
| FastGPT 选项 | OpenAI 兼容值 | 默认 budget |
| --- | --- | --- |
| 默认 | 不显式传递 `reasoning_effort` | 使用模型默认值 |
| 不思考 | `none` | `0` |
| 极简思考 | `minimal` | `1024` |
| 轻量思考 | `low` | `2048` |
| 标准思考 | `medium` | `8192` |
| 深度思考 | `high` | `16384` |
| 极致思考 | `xhigh` | `32768` |
如果某个平台只支持 token budget，不支持离散档位，ai-proxy 会按上表把 effort 转成 budget。反向归一化时，`<=0` 会被视为 `none`，`1~1024` 视为 `minimal`，`1025~4096` 视为 `low`，`4097~12288` 视为 `medium`，`12289~24576` 视为 `high`，更高则视为 `xhigh`。
</details>
<details>
<summary>OpenAI / OpenAI Responses</summary>
| 目标格式 | 写入字段 | 映射方式 |
| --- | --- | --- |
| OpenAI Chat / Completions | `reasoning_effort` | `none/minimal/low/medium/high/xhigh` 原样写入 |
| OpenAI Responses | `reasoning.effort` | `none/minimal/low/medium/high/xhigh` 原样写入 |
OpenAI Chat / Completions 模式只解析 `reasoning_effort`。当 Gemini、Claude 等请求被转换为 OpenAI 兼容格式时，也会先归一化为该字段。
</details>
<details>
<summary>Google Gemini</summary>
Gemini 原生请求会从 `generationConfig.thinkingConfig` 中解析 `thinkingLevel`、`thinkingBudget` 和 `includeThoughts`。写给 Gemini 上游时，ai-proxy 会根据模型系列选择 `thinkingLevel` 或 `thinkingBudget`。
| OpenAI 兼容值 | Gemini 3+ Pro | Gemini 3+ 非 Pro | gemini-2.5-pro | gemini-2.5-flash | gemini-2.5-flash-lite |
| --- | --- | --- | --- | --- | --- |
| `none` | `thinkingLevel=low` | `thinkingLevel=minimal` | `thinkingBudget=128` | `thinkingBudget=0` | `thinkingBudget=0` |
| `minimal` | `thinkingLevel=low` | `thinkingLevel=minimal` | `thinkingBudget=1024` | `thinkingBudget=1024` | `thinkingBudget=1024` |
| `low` | `thinkingLevel=low` | `thinkingLevel=low` | `thinkingBudget=2048` | `thinkingBudget=2048` | `thinkingBudget=2048` |
| `medium` | `thinkingLevel=low` | `thinkingLevel=medium` | `thinkingBudget=8192` | `thinkingBudget=8192` | `thinkingBudget=8192` |
| `high` | `thinkingLevel=high` | `thinkingLevel=high` | `thinkingBudget=16384` | `thinkingBudget=16384` | `thinkingBudget=16384` |
| `xhigh` | `thinkingLevel=high` | `thinkingLevel=high` | `thinkingBudget=32768` | `thinkingBudget=24576` | `thinkingBudget=24576` |
Gemini 2.5 系列会按模型允许范围 clamp budget。部分 Gemini 模型不能真正关闭 thinking，`none` 会退化为模型允许的最小 level 或 budget。
</details>
<details>
<summary>Claude / Anthropic / Bedrock / Vertex AI</summary>
Claude 原生请求会解析 `thinking` 和 `output_config`。写给 Anthropic 官方、AWS Bedrock Claude 或 Vertex AI Claude 时，字段形态仍遵循 Claude 的 thinking 规则。
| OpenAI 兼容值 | 旧式 / budget 模式 | adaptive 模式 |
| --- | --- | --- |
| `none` | `thinking.type=disabled` | `thinking.type=disabled`，部分 adaptive-only 模型可能移除该字段 |
| `minimal` | `thinking.type=enabled`, `budget_tokens=1024` | `thinking.type=adaptive`, `output_config.effort=low` |
| `low` | `thinking.type=enabled`, `budget_tokens=2048` | `thinking.type=adaptive`, `output_config.effort=low` |
| `medium` | `thinking.type=enabled`, `budget_tokens=8192` | `thinking.type=adaptive`, `output_config.effort=medium` |
| `high` | `thinking.type=enabled`, `budget_tokens=16384` | `thinking.type=adaptive`, `output_config.effort=high` |
| `xhigh` | `thinking.type=enabled`, `budget_tokens=32768` | `thinking.type=adaptive`, `output_config.effort=max` |
budget 模式会保证 `budget_tokens < max_tokens`，并把过小的 budget 提升到上游可接受的最小值。
</details>
<details>
<summary>Ali DashScope / Qwen / QwQ / GLM / Kimi 兼容模型</summary>
| OpenAI 兼容值 | 支持 `thinking_budget` 的模型 | 不支持 budget 的模型 |
| --- | --- | --- |
| `none` | `enable_thinking=false`，移除 `thinking_budget` | `enable_thinking=false` |
| `minimal` | `enable_thinking=true`, `thinking_budget=1024` | `enable_thinking=true` |
| `low` | `enable_thinking=true`, `thinking_budget=2048` | `enable_thinking=true` |
| `medium` | `enable_thinking=true`, `thinking_budget=8192` | `enable_thinking=true` |
| `high` | `enable_thinking=true`, `thinking_budget=16384` | `enable_thinking=true` |
| `xhigh` | `enable_thinking=true`, `thinking_budget=32768` | `enable_thinking=true` |
当前 ai-proxy 会把 `qwen3-*`、`qwq-*`、模型名包含 `glm` 或 `kimi` 的 Ali-compatible 模型视为支持 `thinking_budget`。`qwen3-*` 非流式请求会被强制关闭 thinking，`qwq-*` 请求会被强制改为流式。
</details>
<details>
<summary>Zhipu / DeepSeek / Doubao / Moonshot Kimi</summary>
这些平台当前主要保留开关语义，不保留 budget 或细粒度 effort。
| 平台 | OpenAI 兼容值 | 写给上游的字段 |
| --- | --- | --- |
| Zhipu / DeepSeek / Doubao | `none` | `thinking.type=disabled` |
| Zhipu / DeepSeek / Doubao | `minimal/low/medium/high/xhigh` | `thinking.type=enabled` |
| Moonshot / Kimi 支持开关的模型 | `none` | `thinking.type=disabled`，并移除 `reasoning_effort` |
| Moonshot / Kimi 支持开关的模型 | `minimal/low/medium/high/xhigh` | `thinking.type=enabled`，并移除 `reasoning_effort` |
| Moonshot / Kimi 不支持开关的模型 | 任意值 | 移除 `reasoning_effort`，不发送 `thinking` |
### 系统提示词
Moonshot / Kimi 是否能写入 `thinking.type` 取决于渠道映射后的实际上游模型名。
被放置在上下文数组的最前面，role 为 system，用于引导模型。
</details>
### 记忆轮数（仅简易模式）
部分模型不一定完全支持所有思考选项。如果切换后出现报错，可以改回默认选项。
可以配置模型支持的记忆轮数，如果模型的超出上下文，系统会自动截断，尽可能保证不超模型上下文。
### 隐藏 AI 思考
所以尽管配置 30 轮对话，实际运行时候，不一定会达到 30 轮。
打开后，用户只会看到最终回答，看不到 AI 的思考过程。调试应用时，可以临时关闭该开关，观察模型的中间思考内容。
document/data/doc-last-modified.json
......@@ -13,144 +13,144 @@
"content/faq/other.mdx": "2026-04-26T21:08:47+08:00",
"content/faq/points_consumption.en.mdx": "2026-04-26T21:08:47+08:00",
"content/faq/points_consumption.mdx": "2026-04-26T21:08:47+08:00",
"content/guide/admin/sso.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/admin/sso.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/admin/teamMode.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/admin/teamMode.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/evaluation.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/evaluation.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/general/ai_settings.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/general/ai_settings.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/general/chat_input_guide.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/general/chat_input_guide.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/general/fileInput.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/general/fileInput.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/publish/dingtalk.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/publish/dingtalk.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/publish/feishu.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/publish/feishu.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/publish/mcp_server.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/publish/mcp_server.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/publish/official_account.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/publish/official_account.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/publish/openapi.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/publish/openapi.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/publish/wechat.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/publish/wechat.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/publish/wecom.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/publish/wecom.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/tools/mcp_tools.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/tools/mcp_tools.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/tools/system-plugins/bing_search_plugin.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/tools/system-plugins/bing_search_plugin.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/tools/system-plugins/dev_system_tool.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/tools/system-plugins/dev_system_tool.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/tools/system-plugins/doc2x_plugin_guide.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/tools/system-plugins/doc2x_plugin_guide.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/tools/system-plugins/google_search_plugin_guide.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/tools/system-plugins/google_search_plugin_guide.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/tools/system-plugins/searxng_plugin_guide.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/tools/system-plugins/searxng_plugin_guide.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/tools/system-plugins/upload_system_tool.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/tools/system-plugins/upload_system_tool.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/intro.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/intro.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/ai_chat.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/ai_chat.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/content_extract.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/content_extract.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/coreferenceResolution.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/coreferenceResolution.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/custom_feedback.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/custom_feedback.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/dataset_search.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/dataset_search.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/document_parsing.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/document_parsing.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/form_input.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/form_input.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/http.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/http.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/knowledge_base_search_merge.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/knowledge_base_search_merge.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/laf.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/laf.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/loop.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/loop.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/parallel_run.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/parallel_run.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/question_classify.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/question_classify.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/reply.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/reply.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/sandbox-v2.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/sandbox-v2.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/text_editor.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/text_editor.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/tfswitch.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/tfswitch.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/tool.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/tool.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/user-selection.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/user-selection.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/variable_update.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/build/workflow/nodes/variable_update.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/chat/htmlRendering.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/chat/htmlRendering.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/chat/quoteList.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/chat/quoteList.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/collection_tags.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/collection_tags.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/dataset_engine.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/dataset_engine.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/rag.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/rag.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/template.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/template.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/third-party/api_dataset.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/third-party/api_dataset.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/third-party/dingtalk_dataset.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/third-party/dingtalk_dataset.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/third-party/lark_dataset.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/third-party/lark_dataset.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/third-party/third_dataset.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/third-party/third_dataset.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/third-party/yuque_dataset.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/third-party/yuque_dataset.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/dataset/websync.en.mdx": "2026-05-07T14:57:37+08:00",
"content/guide/dataset/websync.mdx": "2026-05-07T14:57:37+08:00",
"content/guide/getting-started/index.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/getting-started/index.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/getting-started/quick-start.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/getting-started/quick-start.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/index.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/index.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/version/cloud/faq.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/version/cloud/faq.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/version/cloud/intro.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/version/cloud/intro.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/version/cloud/privacy.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/version/cloud/privacy.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/version/cloud/terms.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/version/cloud/terms.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/version/commercial.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/version/commercial.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/version/opensource/intro.en.mdx": "2026-05-07T14:57:37+08:00",
"content/guide/version/opensource/intro.mdx": "2026-05-07T14:57:37+08:00",
"content/guide/version/opensource/license.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/version/opensource/license.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/workspace/customDomain.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/workspace/customDomain.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/workspace/team/invitation_link.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/workspace/team/invitation_link.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/workspace/team/team_roles_permissions.en.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/workspace/team/team_roles_permissions.mdx": "2026-05-07T14:11:45+08:00",
"content/guide/admin/sso.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/admin/sso.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/admin/teamMode.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/admin/teamMode.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/evaluation.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/evaluation.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/general/ai_settings.en.mdx": "2026-05-08T15:58:10+08:00",
"content/guide/build/general/ai_settings.mdx": "2026-05-08T15:58:10+08:00",
"content/guide/build/general/chat_input_guide.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/general/chat_input_guide.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/general/fileInput.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/general/fileInput.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/publish/dingtalk.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/publish/dingtalk.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/publish/feishu.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/publish/feishu.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/publish/mcp_server.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/publish/mcp_server.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/publish/official_account.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/publish/official_account.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/publish/openapi.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/publish/openapi.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/publish/wechat.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/publish/wechat.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/publish/wecom.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/publish/wecom.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/tools/mcp_tools.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/tools/mcp_tools.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/tools/system-plugins/bing_search_plugin.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/tools/system-plugins/bing_search_plugin.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/tools/system-plugins/dev_system_tool.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/tools/system-plugins/dev_system_tool.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/tools/system-plugins/doc2x_plugin_guide.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/tools/system-plugins/doc2x_plugin_guide.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/tools/system-plugins/google_search_plugin_guide.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/tools/system-plugins/google_search_plugin_guide.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/tools/system-plugins/searxng_plugin_guide.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/tools/system-plugins/searxng_plugin_guide.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/tools/system-plugins/upload_system_tool.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/tools/system-plugins/upload_system_tool.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/intro.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/intro.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/ai_chat.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/ai_chat.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/content_extract.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/content_extract.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/coreferenceResolution.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/coreferenceResolution.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/custom_feedback.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/custom_feedback.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/dataset_search.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/dataset_search.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/document_parsing.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/document_parsing.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/form_input.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/form_input.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/http.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/http.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/knowledge_base_search_merge.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/knowledge_base_search_merge.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/laf.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/laf.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/loop.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/loop.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/parallel_run.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/parallel_run.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/question_classify.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/question_classify.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/reply.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/reply.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/sandbox-v2.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/sandbox-v2.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/text_editor.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/text_editor.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/tfswitch.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/tfswitch.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/tool.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/tool.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/user-selection.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/user-selection.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/variable_update.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/build/workflow/nodes/variable_update.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/chat/htmlRendering.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/chat/htmlRendering.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/chat/quoteList.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/chat/quoteList.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/collection_tags.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/collection_tags.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/dataset_engine.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/dataset_engine.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/rag.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/rag.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/template.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/template.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/third-party/api_dataset.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/third-party/api_dataset.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/third-party/dingtalk_dataset.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/third-party/dingtalk_dataset.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/third-party/lark_dataset.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/third-party/lark_dataset.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/third-party/third_dataset.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/third-party/third_dataset.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/third-party/yuque_dataset.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/third-party/yuque_dataset.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/websync.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/dataset/websync.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/getting-started/index.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/getting-started/index.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/getting-started/quick-start.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/getting-started/quick-start.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/index.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/index.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/version/cloud/faq.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/version/cloud/faq.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/version/cloud/intro.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/version/cloud/intro.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/version/cloud/privacy.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/version/cloud/privacy.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/version/cloud/terms.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/version/cloud/terms.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/version/commercial.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/version/commercial.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/version/opensource/intro.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/version/opensource/intro.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/version/opensource/license.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/version/opensource/license.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/workspace/customDomain.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/workspace/customDomain.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/workspace/team/invitation_link.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/workspace/team/invitation_link.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/workspace/team/team_roles_permissions.en.mdx": "2026-05-07T15:06:40+08:00",
"content/guide/workspace/team/team_roles_permissions.mdx": "2026-05-07T15:06:40+08:00",
"content/openapi/app.en.mdx": "2026-04-26T21:08:47+08:00",
"content/openapi/app.mdx": "2026-04-26T21:08:47+08:00",
"content/openapi/chat.en.mdx": "2026-04-26T21:08:47+08:00",
"content/openapi/chat.mdx": "2026-04-26T21:08:47+08:00",
"content/openapi/dataset.en.mdx": "2026-05-07T14:11:45+08:00",
"content/openapi/dataset.mdx": "2026-05-07T14:11:45+08:00",
"content/openapi/dataset.en.mdx": "2026-05-07T15:06:40+08:00",
"content/openapi/dataset.mdx": "2026-05-07T15:06:40+08:00",
"content/openapi/index.en.mdx": "2026-04-26T21:08:47+08:00",
"content/openapi/index.mdx": "2026-04-26T21:08:47+08:00",
"content/openapi/intro.en.mdx": "2026-04-26T21:08:47+08:00",
......@@ -161,8 +161,8 @@
"content/self-host/config/env.mdx": "2026-05-06T18:25:24+08:00",
"content/self-host/config/json.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/config/json.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/config/model/intro.en.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/config/model/intro.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/config/model/intro.en.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/config/model/intro.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/config/model/minimax.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/config/model/minimax.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/config/model/siliconCloud.en.mdx": "2026-04-26T21:08:47+08:00",
......@@ -187,14 +187,14 @@
"content/self-host/custom-models/ollama.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/custom-models/xinference.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/custom-models/xinference.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/deploy/docker.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/deploy/docker.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/deploy/docker.en.mdx": "2026-05-07T15:08:21+08:00",
"content/self-host/deploy/docker.mdx": "2026-05-07T15:08:21+08:00",
"content/self-host/deploy/sealos.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/deploy/sealos.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/design/dataset.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/design/dataset.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/design/design_plugin.en.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/design/design_plugin.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/design/design_plugin.en.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/design/design_plugin.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/dev.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/dev.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/index.en.mdx": "2026-04-26T21:08:47+08:00",
......@@ -274,8 +274,8 @@
"content/self-host/upgrading/outdated/40.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/41.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/41.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/4100.en.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/4100.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/4100.en.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/4100.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/4101.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/4101.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/4110.en.mdx": "2026-04-26T21:08:47+08:00",
......@@ -314,16 +314,16 @@
"content/self-host/upgrading/outdated/462.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/463.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/463.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/464.en.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/464.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/465.en.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/465.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/464.en.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/464.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/465.en.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/465.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/466.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/466.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/467.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/467.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/468.en.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/468.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/468.en.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/468.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/469.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/469.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/47.en.mdx": "2026-04-26T21:08:47+08:00",
......@@ -340,14 +340,14 @@
"content/self-host/upgrading/outdated/4811.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/4812.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/4812.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/4813.en.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/4813.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/4813.en.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/4813.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/4814.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/4814.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/4815.en.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/4815.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/4816.en.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/4816.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/4815.en.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/4815.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/4816.en.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/4816.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/4817.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/4817.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/4818.en.mdx": "2026-04-26T21:08:47+08:00",
......@@ -384,16 +384,16 @@
"content/self-host/upgrading/outdated/491.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/4910.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/4910.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/4911.en.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/4911.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/4911.en.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/4911.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/4912.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/4912.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/4913.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/4913.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/4914.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/4914.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/492.en.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/492.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/492.en.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/492.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/493.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/493.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/494.en.mdx": "2026-04-26T21:08:47+08:00",
......@@ -406,12 +406,12 @@
"content/self-host/upgrading/outdated/497.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/498.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/498.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/outdated/499.en.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/499.mdx": "2026-05-07T14:11:45+08:00",
"content/self-host/upgrading/outdated/499.en.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/outdated/499.mdx": "2026-05-07T15:06:40+08:00",
"content/self-host/upgrading/upgrade-intruction.en.mdx": "2026-04-26T21:08:47+08:00",
"content/self-host/upgrading/upgrade-intruction.mdx": "2026-04-26T21:08:47+08:00",
"content/toc.en.mdx": "2026-05-07T14:11:45+08:00",
"content/toc.mdx": "2026-05-07T14:11:45+08:00",
"content/toc.en.mdx": "2026-05-07T15:06:40+08:00",
"content/toc.mdx": "2026-05-07T15:06:40+08:00",
"content/use-cases/app-cases/dalle3.en.mdx": "2026-04-26T21:08:47+08:00",
"content/use-cases/app-cases/dalle3.mdx": "2026-04-26T21:08:47+08:00",
"content/use-cases/app-cases/english_essay_correction_bot.en.mdx": "2026-04-26T21:08:47+08:00",
......@@ -426,10 +426,10 @@
"content/use-cases/app-cases/lab_appointment.mdx": "2026-04-26T21:08:47+08:00",
"content/use-cases/app-cases/multi_turn_translation_bot.en.mdx": "2026-04-26T21:08:47+08:00",
"content/use-cases/app-cases/multi_turn_translation_bot.mdx": "2026-04-26T21:08:47+08:00",
"content/use-cases/app-cases/submit_application_template.en.mdx": "2026-05-07T14:11:45+08:00",
"content/use-cases/app-cases/submit_application_template.mdx": "2026-05-07T14:11:45+08:00",
"content/use-cases/app-cases/submit_application_template.en.mdx": "2026-05-07T15:06:40+08:00",
"content/use-cases/app-cases/submit_application_template.mdx": "2026-05-07T15:06:40+08:00",
"content/use-cases/app-cases/translate-subtitle-using-gpt.en.mdx": "2026-04-26T21:08:47+08:00",
"content/use-cases/app-cases/translate-subtitle-using-gpt.mdx": "2026-04-26T21:08:47+08:00",
"content/use-cases/index.en.mdx": "2026-05-07T14:11:45+08:00",
"content/use-cases/index.mdx": "2026-05-07T14:11:45+08:00"
"content/use-cases/index.en.mdx": "2026-05-07T15:06:40+08:00",
"content/use-cases/index.mdx": "2026-05-07T15:06:40+08:00"
}
\ No newline at end of file
document/package.json
......@@ -2,6 +2,7 @@
"name": "@fastgpt/document",
"version": "1.0.0",
"private": true,
"packageManager": "pnpm@10.33.4",
"scripts": {
"build": "next build",
"dev": "next dev --turbo",
......
document/public/imgs/image-53.png
document/public/imgs/image-53.png

136 KB | W: | H:

document/public/imgs/image-53.png

162 KB | W: | H:

document/public/imgs/image-53.png
document/public/imgs/image-53.png
document/public/imgs/image-53.png
document/public/imgs/image-53.png
  • 2-up
  • Swipe
  • Onion skin
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or sign in to comment