mirror of
https://github.com/labring/FastGPT.git
synced 2025-07-24 22:03:54 +00:00

* perf: redirect request and err log replace perf: dataset openapi feat: session fix: retry input error feat: 468 doc sub page feat: standard sub perf: rerank tip perf: rerank tip perf: api sdk perf: openapi sub plan perf: sub ui fix: ts * perf: init log * fix: variable select * sub page * icon * perf: llm model config * perf: menu ux * perf: system store * perf: publish app name * fix: init data * perf: flow edit ux * fix: value type format and ux * fix prompt editor default value (#13) * fix prompt editor default value * fix prompt editor update when not focus * add key with variable --------- Co-authored-by: Archer <545436317@qq.com> * fix: value type * doc * i18n * import path * home page * perf: mongo session running * fix: ts * perf: use toast * perf: flow edit * perf: sse response * slider ui * fetch error * fix prompt editor rerender when not focus by key defaultvalue (#14) * perf: prompt editor * feat: dataset search concat * perf: doc * fix:ts * perf: doc * fix json editor onblur value (#15) * faq * vector model default config * ipv6 --------- Co-authored-by: heheer <71265218+newfish-cmyk@users.noreply.github.com>
279 lines
5.4 KiB
Markdown
279 lines
5.4 KiB
Markdown
---
|
||
title: "新 HTTP 模块"
|
||
description: "FastGPT HTTP 模块介绍"
|
||
icon: "http"
|
||
draft: false
|
||
toc: true
|
||
weight: 355
|
||
---
|
||
|
||
## 特点
|
||
|
||
- 可重复添加
|
||
- 有外部输入
|
||
- 手动配置
|
||
- 触发执行
|
||
- 核中核模块
|
||
|
||

|
||
|
||
## 介绍
|
||
|
||
HTTP 模块会向对应的地址发送一个 `POST/GET` 请求,携带部分`系统参数`及`自定义参数`,并接收一个 JSON 响应值,字段也是自定义。
|
||
|
||
- 你还可以通过 JSON 传入自定义的请求头。
|
||
- POST 请求中,数据会被放置在 `body` 中。
|
||
- GET 请求中,数据会被放置在 `query` 中。
|
||
- 在出入参数中,你都可以通过 xxx.xxx 来代表嵌套的对象。
|
||
|
||
## 参数结构
|
||
|
||
### 系统参数说明
|
||
|
||
- appId: 应用的ID
|
||
- chatId: 当前对话的ID,测试模式下不存在。
|
||
- responseChatItemId: 当前对话中,响应的消息ID,测试模式下不存在。
|
||
- variables: 当前对话的全局变量。
|
||
- data: 自定义传递的参数。
|
||
|
||
### 嵌套对象使用
|
||
|
||
#### 入参
|
||
|
||
假设我们设计了`3个`输入。
|
||
|
||
- user.name (string)
|
||
- user.age (number)
|
||
- type (string)
|
||
|
||
最终组成的对象为:
|
||
|
||
```json
|
||
{
|
||
"user": {
|
||
"name": "",
|
||
"age": ""
|
||
},
|
||
"type": ""
|
||
}
|
||
```
|
||
|
||
#### 出参
|
||
|
||
假设接口的输出结构为:
|
||
|
||
```json
|
||
{
|
||
"message": "测试",
|
||
"data":{
|
||
"user": {
|
||
"name": "xxx",
|
||
"age": 12
|
||
},
|
||
"list": [
|
||
{
|
||
"name": "xxx",
|
||
"age": 50
|
||
},
|
||
[{ "test": 22 }]
|
||
],
|
||
"psw": "xxx"
|
||
}
|
||
}
|
||
```
|
||
|
||
最终得到的解析为:
|
||
|
||
```json
|
||
{
|
||
"user": { "name": "xxx", "age": 12 },
|
||
"user.name": "xxx",
|
||
"user.age": 12,
|
||
"list": [ { "name": "xxx", "age": 50 }, [{ "test": 22 }] ],
|
||
"list[0]": { "name": "xxx", "age": 50 },
|
||
"list[0].name": "xxx",
|
||
"list[0].age": 50,
|
||
"list[1]": [ { "test": 22 } ],
|
||
"list[1][0]": { "test": 22 },
|
||
"list[1][0].test": 22,
|
||
"psw": "xxx"
|
||
}
|
||
```
|
||
|
||
你可以使用`json`里对应的`key`来获取值。
|
||
|
||
|
||
### 格式化输出
|
||
|
||
FastGPT v4.6.8 后,加入了出参格式化功能,主要以`json`格式化成`字符串`为主。如果你的输出类型选择了`字符串`,则会将`HTTP`对应`key`的值,转成`json`字符串进行输出。因此,未来你可以直接从`HTTP`接口输出内容至`文本加工`中,然后拼接适当的提示词,最终输入给`AI对话`。
|
||
|
||
## POST 示例
|
||
|
||
**自定义入参**
|
||
|
||
- user.name (string)
|
||
- user.age (number)
|
||
- type (string)
|
||
|
||
**自定义出参**
|
||
|
||
- message (string)
|
||
- data.name (string)
|
||
- data.age (number)
|
||
|
||
那么,这个模块发出的请求则是:
|
||
|
||
{{< tabs tabTotal="2" >}}
|
||
{{< tab tabName="POST 请求示例" >}}
|
||
{{< markdownify >}}
|
||
|
||
```bash
|
||
curl --location --request POST 'http://xxxx.com' \
|
||
--header 'Content-Type: application/json' \
|
||
--data-raw '{
|
||
"appId": "65782f7ffae5f7854ed4498b",
|
||
"chatId": "xxxx",
|
||
"responseChatItemId": "xxxx",
|
||
"variables": {
|
||
"cTime": "2023-12-18 13:45:46"
|
||
},
|
||
"data": {
|
||
"user": {
|
||
"name": "",
|
||
"age": ""
|
||
},
|
||
"type": ""
|
||
}
|
||
}'
|
||
```
|
||
|
||
{{< /markdownify >}}
|
||
{{< /tab >}}
|
||
|
||
{{< tab tabName="POST响应" >}}
|
||
{{< markdownify >}}
|
||
|
||
```json
|
||
{
|
||
"message": "message",
|
||
"data": {
|
||
"name": "name",
|
||
"age": 10
|
||
}
|
||
}
|
||
```
|
||
{{< /markdownify >}}
|
||
{{< /tab >}}
|
||
{{< /tabs >}}
|
||
|
||
## GET 示例
|
||
|
||
GET 中,不推荐使用嵌套参数,否则会出现奇怪的问题。此外,GET 请求中,FastGPT 会将参数扁平化,不会将自定义参单独抽到 data 中,同时全局变量也会扁平化,因此需要注意字段 key 是否冲突。
|
||
|
||
**自定义入参**
|
||
|
||
- name (string)
|
||
- age (number)
|
||
- type (string)
|
||
|
||
**自定义出参**
|
||
|
||
- message (string)
|
||
- name (string)
|
||
- age (number)
|
||
|
||
那么,这个模块发出的请求则是:
|
||
|
||
{{< tabs tabTotal="2" >}}
|
||
{{< tab tabName="GET 请求示例" >}}
|
||
{{< markdownify >}}
|
||
|
||
```bash
|
||
curl --location --request GET 'http://xxx.com/test?name&age&type&appId=65782f7ffae5f7854ed4498b&chatId=xxxx&responseChatItemId=xxxx&cTime=2023-12-18 13:45:46'
|
||
```
|
||
|
||
{{< /markdownify >}}
|
||
{{< /tab >}}
|
||
|
||
{{< tab tabName="GET 响应" >}}
|
||
{{< markdownify >}}
|
||
|
||
```json
|
||
{
|
||
"message": "message",
|
||
"data": {
|
||
"name": "name",
|
||
"age": 10
|
||
}
|
||
}
|
||
```
|
||
{{< /markdownify >}}
|
||
{{< /tab >}}
|
||
{{< /tabs >}}
|
||
|
||
|
||
## laf 对接 HTTP 示例
|
||
|
||
{{% alert context="warning" %}}
|
||
如果你不想额外部署服务,可以使用 [Laf](https://laf.dev/) 来快速开发上线接口,即写即发,无需部署。
|
||
{{% /alert %}}
|
||
|
||
下面是在 Laf 编写的 POST 请求示例:
|
||
|
||
```ts
|
||
import cloud from '@lafjs/cloud'
|
||
const db = cloud.database()
|
||
|
||
type RequestType = {
|
||
appId: string;
|
||
data: {
|
||
appointment: string;
|
||
action: 'post' | 'delete' | 'put' | 'get'
|
||
}
|
||
}
|
||
|
||
export default async function (ctx: FunctionContext) {
|
||
try {
|
||
// 从 body 中获取参数
|
||
const { appId, data: { appointment, action } } = ctx.body as RequestType
|
||
|
||
const parseBody = JSON.parse(appointment)
|
||
if (action === 'get') {
|
||
return await getRecord(parseBody)
|
||
}
|
||
if (action === 'post') {
|
||
return await createRecord(parseBody)
|
||
}
|
||
if (action === 'put') {
|
||
return await putRecord(parseBody)
|
||
}
|
||
if (action === 'delete') {
|
||
return await removeRecord(parseBody)
|
||
}
|
||
|
||
|
||
return {
|
||
response: "异常"
|
||
}
|
||
} catch (err) {
|
||
return {
|
||
response: "异常"
|
||
}
|
||
}
|
||
}
|
||
```
|
||
|
||
## 作用
|
||
|
||
通过 HTTP 模块你可以无限扩展,比如:
|
||
- 操作数据库
|
||
- 调用外部数据源
|
||
- 执行联网搜索
|
||
- 发送邮箱
|
||
- ....
|
||
|
||
|
||
## 相关示例
|
||
|
||
- [谷歌搜索](/docs/workflow/examples/google_search/)
|
||
- [实验室预约(操作数据库)](/docs/workflow/examples/lab_appointment/) |