python后端调用Deep Seek API

YY_oot2025-02-15 11:52

python后端调用Deep Seek API

需要依次下载
●Ollama
●Deepseek R1 LLM模型
●嵌入模型nomic-embed-text / bge-m3
●AnythingLLM

参考教程：
Deepseek R1打造本地化RAG知识库:安装部署使用详细教程
 手把手教你：deepseek R1基于 AnythingLLM API 调用本地知识库

python调用anythingllm的API

python 复制代码

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()
        sources = result.get('sources', [])
        return answer, sources
    else:
        return f"Error: {response.text}", []

# 示例调用
workspace = "" # 填入workspace 名字，注意要全小写
api_key = "" # api_key
question = "你是谁？"
print(question)
answer, sources = ask_anythingllm(question, workspace, api_key)
print("回答:", answer)
print("来源:", [src['title'] for src in sources])

注意workspace_name与anythingllm平台上的显示有所出入，要全部小写，且空格要改成连字符，比如说
MY Workspaces 要写成my-workspaces
DeepSeek 要写成deepseek

结果：