【AnythingLLM】安装、使用API调用

一、docker安装

- docker安装和exe安装的区别？

docker pull mintplexlabs/anythingllm
docker images

windows：

$env:STORAGE_LOCATION="$HOME\Documents\anythingllm"; `
If(!(Test-Path $env:STORAGE_LOCATION)) {New-Item $env:STORAGE_LOCATION -ItemType Directory}; `
If(!(Test-Path "$env:STORAGE_LOCATION\.env")) {New-Item "$env:STORAGE_LOCATION\.env" -ItemType File}; `
docker run -d -p 3001:3001 `
--cap-add SYS_ADMIN `
-v "$env:STORAGE_LOCATION`:/app/server/storage" `
-v "$env:STORAGE_LOCATION\.env:/app/server/.env" `
-e STORAGE_DIR="/app/server/storage" `
mintplexlabs/anythingllm;

参考：https://docs.anythingllm.com/installation-docker/local-docker

二、配置AnythingLLM

三、使用API调用AnythingLLM

参考：https://blog.csdn.net/wlddhj/article/details/145713875

1. 生成API密钥

2. “Authorize”API密钥

复制API秘钥，点击“阅读API文档”打开API接口文档，点击右边的“Authorize”按钮，把API秘钥复制进去，然后就可以调试接口了。

运行第一个接口/v1/auth，如果返回截图中的结果，即调用成功。
查看工作区信息：

3. python调用

import requests

def ask_anythingllm(question, slug, api_key):    
    url = f"http://localhost:3001/api/v1/workspace/{slug}/chat"    
    headers = {        
        "Authorization": f"Bearer {api_key}",        
        "Content-Type": "application/json",        
        "accept": "application/json"    
    }    
    data = {        
        "message": question,        
        "mode": "query"  # 可选chat/query模式    
    }    
    response = requests.post(url, headers=headers, json=data)    
    if response.status_code == 200:        
        result = response.json()        
        # 提取有效回答（去除思考过程）        
        # answer = result['textResponse'].split('</think>')[-1].strip()  
        answer = result  
        sources = result.get('sources', [])        
        return answer, sources    
    else:        
        return f"Error: {response.text}", []
    
# 示例调用
api_key = "Your-Api-Key"
slug = "Your-Slug"
question = "你是谁？"
answer, sources = ask_anythingllm(question, slug, api_key)
print("回答:", answer)
print("来源:", [src['title'] for src in sources])