參考教程：
Deepseek R1打造本地化RAG知識庫:安裝部署使用詳細(xì)教程
手把手教你：deepseek R1基于 AnythingLLM API 調(diào)用本地知識庫

python調(diào)用anythingllm的API

import requests
# import jsondef
def ask_anythingllm(question, workspace_name, api_key):url = f"http://localhost:3001/api/v1/workspace/{workspace_name}/chat"headers = {"Authorization": f"Bearer {api_key}","Content-Type": "application/json","accept": "application/json"}data = {"message": question,"mode": "query"  # 可選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（去除思考過程）answer = result['textResponse'].split('</think>')[-1].strip()sources = result.get('sources', [])return answer, sourceselse:return f"Error: {response.text}", []# 示例調(diào)用
workspace = "" # 填入workspace 名字，注意要全小寫
api_key = "" # api_key
question = "你是誰？"
print(question)
answer, sources = ask_anythingllm(question, workspace, api_key)
print("回答:", answer)
print("來源:", [src['title'] for src in sources])

注意workspace_name與anythingllm平臺上的顯示有所出入，要全部小寫，且空格要改成連字符，比如說
MY Workspaces要寫成my-workspaces
DeepSeek要寫成deepseek

結(jié)果：