Skip to content

Commit

Permalink
update doc
Browse files Browse the repository at this point in the history
  • Loading branch information
c121914yu committed Feb 4, 2025
1 parent b65cd4d commit 085a522
Show file tree
Hide file tree
Showing 7 changed files with 43 additions and 6 deletions.
2 changes: 1 addition & 1 deletion .github/workflows/docs-deploy-vercel.yml
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,7 @@ jobs:

# Step 4 - Builds the site using Hugo
- name: Build
run: cd docSite && hugo mod get -u github.com/colinwilson/lotusdocs && hugo -v --minify
run: cd docSite && hugo mod get -u github.com/colinwilson/lotusdocs@6d0568e” && hugo -v --minify

# Step 5 - Push our generated site to Vercel
- name: Deploy to Vercel
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/docs-preview.yml
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,7 @@ jobs:

# Step 4 - Builds the site using Hugo
- name: Build
run: cd docSite && hugo mod get -u github.com/colinwilson/lotusdocs && hugo -v --minify
run: cd docSite && hugo mod get -u github.com/colinwilson/lotusdocs@6d0568e” && hugo -v --minify

# Step 5 - Push our generated site to Vercel
- name: Deploy to Vercel
Expand Down
2 changes: 1 addition & 1 deletion docSite/Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ FROM hugomods/hugo:0.117.0 AS builder
WORKDIR /app

ADD ./docSite hugo
RUN cd /app/hugo && hugo mod get -u github.com/colinwilson/lotusdocs && hugo -v --minify
RUN cd /app/hugo && hugo mod get -u github.com/colinwilson/lotusdocs@6d0568e” && hugo -v --minify

FROM fholzer/nginx-brotli:latest

Expand Down
Binary file added docSite/assets/imgs/image-106.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docSite/assets/imgs/image-107.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
7 changes: 7 additions & 0 deletions docSite/content/zh-cn/docs/development/docker.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,13 @@ toc: true
weight: 707
---

## 前置知识

1. 基础的网络知识:端口,防火墙……
2. Docker 和 Docker Compose 基础知识
3. 大模型相关接口和参数
4. RAG 相关知识:向量模型,向量数据库,向量检索

## 部署架构图

![](/imgs/sealos-fastgpt.webp)
Expand Down
36 changes: 33 additions & 3 deletions docSite/content/zh-cn/docs/development/modelConfig/intro.md
Original file line number Diff line number Diff line change
Expand Up @@ -44,8 +44,8 @@ weight: 744

### 核心配置

- 模型 ID:实际发出请求的`model`,全局唯一。
- 自定义请求地址/Token:如果需要绕过`OneAPI`,可以设置自定义请求地址和 Token。一般情况下不需要,如果 OneAPI 不支持某些模型,可以使用该特性。
- 模型 ID:接口请求时候,Body 中`model`字段的值,全局唯一。
- 自定义请求地址/Key:如果需要绕过`OneAPI`,可以设置自定义请求地址和 Token。一般情况下不需要,如果 OneAPI 不支持某些模型,可以使用该特性。

### 模型类型

Expand Down Expand Up @@ -206,7 +206,7 @@ FastGPT 页面上提供了每类模型的简单测试,可以初步检查模型

![alt text](/imgs/image-105.png)

## 模型接入示例
## 特殊接入示例

### ReRank 模型接入

Expand All @@ -227,6 +227,36 @@ FastGPT 页面上提供了每类模型的简单测试,可以初步检查模型

[点击查看部署 ReRank 模型教程](/docs/development/custom-models/bge-rerank/)

### 接入语音识别模型

OneAPI 的语言识别接口,无法正确的识别其他模型(会始终识别成 whisper-1),所以如果想接入其他模型,可以通过自定义请求地址来实现。例如,接入硅基流动的 `FunAudioLLM/SenseVoiceSmall` 模型,可以参考如下配置:

点击模型编辑:

![alt text](/imgs/image-106.png)

填写硅基流动的地址:`https://api.siliconflow.cn/v1/audio/transcriptions`,并填写硅基流动的 API Key。

![alt text](/imgs/image-107.png)

## 其他配置项说明

### 自定义请求地址

如果填写了该值,则可以允许你绕过 OneAPI,直接向自定义请求地址发起请求。需要填写完整的请求地址,例如:

- LLM: {{host}}/v1/chat/completions
- Embedding: {{host}}/v1/embeddings
- STT: {{host}}/v1/audio/transcriptions
- TTS: {{host}}/v1/audio/speech
- Rerank: {{host}}/v1/rerank

自定义请求 Key,则是向自定义请求地址发起请求时候,携带请求头:Authorization: Bearer xxx 进行请求。

所有接口均遵循 OpenAI 提供的模型格式,可参考 [OpenAI API 文档](https://platform.openai.com/docs/api-reference/introduction) 进行配置。

由于 OpenAI 没有提供 ReRank 模型,遵循的是 Cohere 的格式。[点击查看接口请求示例](/docs/development/faq/#如何检查模型问题)


## 旧版模型配置说明

Expand Down

0 comments on commit 085a522

Please sign in to comment.