：大模型RAG對話系統

cURL 命令

注意：以下樣本中，<service_url>替換為RAG服務的訪問地址；<service_token>替換為RAG服務的Token。擷取方式詳情請參見擷取調用資訊。

• 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": "什麼是人工智慧平台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": "什麼是人工智慧平台PAI?"}'

  支援添加其他可調推理參數，例如{"question":"什麼是人工智慧平台PAI?", "temperature": 0.9}。

• Chat(Knowledge Base)：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": "什麼是人工智慧平台PAI?"}'

  支援添加其他可調推理參數，例如{"question":"什麼是人工智慧平台PAI?", "temperature": 0.9}。

• Chat(Web Search)：api/v1/query/search

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

Python指令碼

注意：以下樣本中，SERVICE_URL配置為RAG服務的訪問地址；Authorization配置為RAG服務的Token。擷取方式詳情請參見擷取調用資訊。

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":"什麼是人工智慧平台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')
# Chat（Knowledge Base）
test_post_api_query(SERVICE_URL + 'api/v1/query')

cURL命令

注意：以下樣本中，<service_url>替換為RAG服務的訪問地址；<service_token>替換為RAG服務的Token。擷取方式詳情請參見擷取調用資訊。

以RAG對話為例：

# 發送請求。 
curl -X 'POST'  '<service_url>api/v1/query' -H 'Authorization: <service_token>' -H 'accept: application/json'  -H 'Content-Type: application/json'  -d '{"question": "什麼是人工智慧平台PAI?"}'

# 傳入上述請求返回的session_id（對話歷史會話唯一標識），傳入session_id後，將對話歷史進行記錄，調用大模型將自動攜帶儲存的對話歷史。
curl -X 'POST'  '<service_url>api/v1/query' -H 'Authorization: <service_token>' -H 'accept: application/json'  -H 'Content-Type: application/json'  -d '{"question": "它有什麼優勢?","session_id": "ed7a80e2e20442eab****"}'

# 傳入chat_history（使用者與模型的對話歷史），list中的每個元素是形式為{"user":"使用者輸入","bot":"模型輸出"}的一輪對話，多輪對話按時間順序排列。
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是什嗎？", "bot":"PAI是阿里雲的人工智慧平台......"}]}'

# 同時傳入session_id和chat_history，會用chat_history對儲存的session_id所對應的對話歷史進行追加更新。 
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是什嗎？", "bot":"PAI是阿里雲的人工智慧平台......"}], "session_id": "1702ffxxad3xxx6fxxx97daf7c"}'

Python

注意：以下樣本中，SERVICE_URL配置為RAG服務的訪問地址；Authorization配置為RAG服務的Token。擷取方式詳情請參見擷取調用資訊。

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": "什麼是人工智慧平台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": "它有什麼優勢？",
       "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")
# Chat（Knowledge Base）
test_post_api_query_with_chat_history(SERVICE_URL + "api/v1/query")