jiazhizhong/higress
1
0
Fork 0
mirror of https://github.com/alibaba/higress.git synced 2026-06-08 04:07:31 +08:00
Code Issues Packages Projects Releases Wiki Activity

update plugins doc (#1305)

Browse Source
This commit is contained in:
澄潭
2024-09-12 21:48:40 +08:00
committed by GitHub
parent 0f9113ed82
commit c7c4ae1da2
80 changed files with 7373 additions and 2368 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
plugins/wasm-go/extensions/ai-rag/README.md
View File

@@ -1,9 +1,22 @@
# 简介
---
title: AI RAG
keywords: [ AI网关, AI RAG ]
description: AI RAG 插件配置参考
---
## 功能说明
通过对接阿里云向量检索服务实现LLM-RAG，流程如图所示：
<img src="https://img.alicdn.com/imgextra/i1/O1CN01LuRVs41KhoeuzakeF_!!6000000001196-0-tps-1926-1316.jpg" width=600>
# 配置说明
## 运行属性
插件执行阶段：`默认阶段`
插件执行优先级：`400`
## 配置说明
| 名称 | 数据类型 | 填写要求 | 默认值 | 描述 |
|----------------|-----------------|------|-----|----------------------------------------------------------------------------------|
| `dashscope.apiKey` | string | 必填 | - | 用于在访问通义千问服务时进行认证的令牌。 |
@@ -20,7 +33,7 @@
插件开启后，在使用链路追踪功能时，会在span的attribute中添加rag检索到的文档id信息，供排查问题使用。
# 示例
## 示例
```yaml
dashscope:
@@ -54,4 +67,4 @@ dashvector:
经过RAG插件处理后LLM返回的结果为：
```
海南追尾事故发生在海文高速公路文昌至海口方向37公里处。关于事故的具体原因，交警部门当时仍在进一步调查中，所以根据提供的信息无法确定事故的确切原因。人员伤亡情况是1人死亡（司机当场死亡），另有8人受伤（包括2名儿童和6名成人），所有受伤人员都被解救并送往医院进行治疗。
```
```

61
plugins/wasm-go/extensions/ai-rag/README_EN.md Normal file
View File

@@ -0,0 +1,61 @@
---
title: AI RAG
keywords: [ AI Gateway, AI RAG ]
description: AI RAG Plugin Configuration Reference
---
## Function Description
Implement LLM-RAG by integrating with Alibaba Cloud Vector Search Service, as shown in the figure below:
<img src="https://img.alicdn.com/imgextra/i1/O1CN01LuRVs41KhoeuzakeF_!!6000000001196-0-tps-1926-1316.jpg" width=600>
## Running Attributes
Plugin execution phase: `Default Phase`
Plugin execution priority: `400`
## Configuration Description
| Name | Data Type | Requirement | Default Value | Description |
|--------------------------|-----------|-------------|---------------|-------------------------------------------------------------------------------------------|
| `dashscope.apiKey` | string | Required | - | Token used for authentication when accessing Tongyi Qianwen service. |
| `dashscope.serviceFQDN` | string | Required | - | Tongyi Qianwen service name |
| `dashscope.servicePort` | int | Required | - | Tongyi Qianwen service port |
| `dashscope.serviceHost` | string | Required | - | Domain name for accessing Tongyi Qianwen service |
| `dashvector.apiKey` | string | Required | - | Token used for authentication when accessing Alibaba Cloud Vector Search Service. |
| `dashvector.serviceFQDN`| string | Required | - | Alibaba Cloud Vector Search service name |
| `dashvector.servicePort`| int | Required | - | Alibaba Cloud Vector Search service port |
| `dashvector.serviceHost`| string | Required | - | Domain name for accessing Alibaba Cloud Vector Search service |
| `dashvector.topk` | int | Required | - | Number of vectors to retrieve from Alibaba Cloud Vector Search |
| `dashvector.threshold` | float | Required | - | Vector distance threshold; documents above this threshold will be filtered out |
| `dashvector.field` | string | Required | - | Field name where documents are stored in Alibaba Cloud Vector Search |
Once the plugin is enabled, while using the tracing feature, the document ID information retrieved by RAG will be added to the span's attributes for troubleshooting purposes.
## Example
```yaml
dashscope:
apiKey: xxxxxxxxxxxxxxx
serviceFQDN: dashscope
servicePort: 443
serviceHost: dashscope.aliyuncs.com
dashvector:
apiKey: xxxxxxxxxxxxxxxxxxxx
serviceFQDN: dashvector
servicePort: 443
serviceHost: vrs-cn-xxxxxxxxxxxxxxx.dashvector.cn-hangzhou.aliyuncs.com
collection: xxxxxxxxxxxxxxx
topk: 1
threshold: 0.4
field: raw
```
The [CEC-Corpus](https://github.com/shijiebei2009/CEC-Corpus) dataset contains 332 news reports on emergency events, along with annotation data. The original news text is extracted, vectorized, and then added to Alibaba Cloud Vector Search Service. For text vectorization tutorials, you can refer to [“Implementing Semantic Search Based on Vector Search Service and Lingji”](https://help.aliyun.com/document_detail/2510234.html).
Below is an example enhanced using RAG, with the original request being:
```
Where did the rear-end collision in Hainan occur? What was the cause? How many casualties were there?
```
The result returned by LLM without RAG plugin processing was:
```
I'm sorry, as an AI model, I cannot retrieve and update specific information on news events in real time, including details such as location, cause, and casualties. For such specific events, it is recommended that you consult the latest news reports or official announcements for accurate information. You can visit mainstream media websites, use news applications, or follow announcements from relevant government departments to get dynamic updates.
```
After processing with RAG plugin, the result returned by LLM was:
```
The rear-end collision in Hainan occurred on the Haiven Expressway, 37 kilometers from Wenchang to Haikou. Regarding the specific cause of the accident, traffic police were still conducting further investigations at the time, so the exact cause of the accident cannot be determined based on the provided information. The casualty situation is 1 death (the driver died on the spot) and 8 injuries (including 2 children and 6 adults). All injured persons were rescued and sent to the hospital for treatment.
```