大模型RAG对话系统

cURL 命令

注意：以下示例中，<service_url>替换为RAG服务的访问地址；<service_token>替换为RAG服务的Token。获取方式详情请参见获取调用信息。

• Retrieval：api/v1/query/retrieval

  curl -X 'POST'  '<service_url>api/v1/query/retrieval' -H 'Authorization: <service_token>' -H 'accept: application/json' -H 'Content-Type: application/json'  -d '{"question": "什么是人工智能平台PAI?"}'

• LLM：/api/v1/query/llm

  curl -X 'POST'  '<service_url>api/v1/query/llm' -H 'Authorization: <service_token>' -H 'accept: application/json'  -H 'Content-Type: application/json'  -d '{"question": "什么是人工智能平台PAI?"}'

  支持添加其他可调推理参数，例如{"question":"什么是人工智能平台PAI?", "temperature": 0.9}。

• RAG(Retrieval+LLM)：api/v1/query

  curl -X 'POST'  '<service_url>api/v1/query' -H 'Authorization: <service_token>' -H 'accept: application/json'  -H 'Content-Type: application/json'  -d '{"question": "什么是人工智能平台PAI?"}'

  支持添加其他可调推理参数，例如{"question":"什么是人工智能平台PAI?", "temperature": 0.9}。

• RAG(Search Web)：api/v1/query/search

  curl --location '<service_url>api/v1/query/search' \
  --header 'Authorization: <service_token>' \
  --header 'Content-Type: application/json' \
  --data '{"question":"中国电影票房排名", "stream": true}'

Python脚本

注意：以下示例中，SERVICE_URL配置为RAG服务的访问地址；Authorization配置为RAG服务的Token。获取方式详情请参见获取调用信息。

import requests

SERVICE_URL = 'http://xxxx.****.cn-beijing.pai-eas.aliyuncs.com/'
headers = {
    'accept': 'application/json',
    'Content-Type': 'application/json',
    'Authorization': 'MDA5NmJkNzkyMGM1Zj****YzM4M2YwMDUzZTdiZmI5YzljYjZmNA==',
}

def test_post_api_query(url):
    data = {
       "question":"什么是人工智能平台PAI?" 
    }
    response = requests.post(url, headers=headers, json=data)

    if response.status_code != 200:
        raise ValueError(f'Error post to {url}, code: {response.status_code}')
    ans = dict(response.json())

    print(f"======= Question =======\n {data['question']}")
    if 'answer' in ans.keys():
        print(f"======= Answer =======\n {ans['answer']}")
    if 'docs' in ans.keys():
        print(f"======= Retrieved Docs =======\n {ans['docs']}\n\n")
 
# LLM 
test_post_api_query(SERVICE_URL + 'api/v1/query/llm')
# Retrieval
test_post_api_query(SERVICE_URL + 'api/v1/query/retrieval')
# RAG（Retrieval+LLM）
test_post_api_query(SERVICE_URL + 'api/v1/query')

cURL命令

注意：以下示例中，<service_url>替换为RAG服务的访问地址；<service_token>替换为RAG服务的Token。获取方式详情请参见获取调用信息。

以RAG对话为例：

# 发送请求。 
curl -X 'POST'  '<service_url>api/v1//query' -H 'Authorization: <service_token>' -H 'accept: application/json'  -H 'Content-Type: application/json'  -d '{"question": "什么是人工智能平台PAI?"}'

# 传入上述请求返回的session_id（对话历史会话唯一标识），传入session_id后，将对话历史进行记录，调用大模型将自动携带存储的对话历史。
curl -X 'POST'  '<service_url>api/v1//query' -H 'Authorization: <service_token>' -H 'accept: application/json'  -H 'Content-Type: application/json'  -d '{"question": "它有什么优势?","session_id": "ed7a80e2e20442eab****"}'

# 传入chat_history（用户与模型的对话历史），list中的每个元素是形式为{"user":"用户输入","bot":"模型输出"}的一轮对话，多轮对话按时间顺序排列。
curl -X 'POST'  '<service_url>api/v1//query' -H 'Authorization: <service_token>' -H 'accept: application/json'  -H 'Content-Type: application/json'  -d '{"question":"它有哪些功能？", "chat_history": [{"user":"PAI是什么？", "bot":"PAI是阿里云的人工智能平台......"}]}'

# 同时传入session_id和chat_history，会用chat_history对存储的session_id所对应的对话历史进行追加更新。 
curl -X 'POST'  '<service_url>api/v1//query' -H 'Authorization: <service_token>' -H 'accept: application/json'  -H 'Content-Type: application/json'  -d '{"question":"它有哪些功能？", "chat_history": [{"user":"PAI是什么？", "bot":"PAI是阿里云的人工智能平台......"}], "session_id": "1702ffxxad3xxx6fxxx97daf7c"}'

Python

注意：以下示例中，SERVICE_URL配置为RAG服务的访问地址；Authorization配置为RAG服务的Token。获取方式详情请参见获取调用信息。

import requests

SERVICE_URL = 'http://xxxx.****.cn-beijing.pai-eas.aliyuncs.com'
headers = {
    'accept': 'application/json',
    'Content-Type': 'application/json',
    'Authorization': 'MDA5NmJkN****jNlMDgzYzM4M2YwMDUzZTdiZmI5YzljYjZmNA==',
}

def test_post_api_query_with_chat_history(url):
    # Round 1 query
    data = {
       "question": "什么是人工智能平台PAI?"
    }
    response = requests.post(url, headers=headers, json=data)

    if response.status_code != 200:
        raise ValueError(f'Error post to {url}, code: {response.status_code}')
    ans = dict(response.json())
    print(f"=======Round 1: Question =======\n {data['question']}")
    if 'answer' in ans.keys():
        print(f"=======Round 1: Answer =======\n {ans['answer']} session_id: {ans['session_id']}")
    if 'docs' in ans.keys():
        print(f"=======Round 1: Retrieved Docs =======\n {ans['docs']}")
   
    # Round 2 query
    data_2 = {
       "question": "它有什么优势？",
       "session_id": ans['session_id']
    }
    response_2 = requests.post(url, headers=headers, json=data_2)

    if response.status_code != 200:
        raise ValueError(f'Error post to {url}, code: {response.status_code}')
    ans_2 = dict(response_2.json())
    print(f"=======Round 2: Question =======\n {data_2['question']}")
    if 'answer' in ans.keys():
        print(f"=======Round 2: Answer =======\n {ans_2['answer']} session_id: {ans_2['session_id']}")
    if 'docs' in ans.keys():
        print(f"=======Round 2: Retrieved Docs =======\n {ans['docs']}")
    print("\n")

# LLM
test_post_api_query_with_chat_history(SERVICE_URL + "api/v1/query/llm")
# RAG（Retrieval+LLM）
test_post_api_query_with_chat_history(SERVICE_URL + "api/v1/query")