Gemma-7B-it
Gemma 是 Google 开发的一系列轻量级、尖端的开源文本生成模型,采用与 Gemini 模型相同的技术构建,适合用于各种文本生成任务,能够在资源量较小的端侧设备部署。本文介绍了相关API。
功能介绍
调用本接口,发起一次对话请求。
在线调试
平台提供了 API在线调试平台-示例代码 ,用于帮助开发者调试接口,平台集成快速检索、查看开发文档、查看在线调用的请求内容和返回结果、复制和下载示例代码等功能,简单易用,更多内容请查看API在线调试介绍。
HTTP调用
鉴权说明
本文API,支持2种鉴权方式。不同鉴权方式,调用方式不同,使用Header、Query参数不同,详见本文请求说明。开发者可以选择以下任一种方式进行鉴权。
请求说明
- 基本信息
请求地址: https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/gemma_7b_it
请求方式: POST
- Header参数
根据不同鉴权方式,查看对应Header参数。
访问凭证access_token鉴权
名称 | 类型 | 必填 | 描述 |
---|---|---|---|
Content-Type | string | 是 | 固定值application/json |
基于安全认证AK/SK进行签名计算鉴权
名称 | 类型 | 必填 | 描述 |
---|---|---|---|
Content-Type | string | 是 | 固定值application/json |
x-bce-date | string | 否 | 当前时间,遵循ISO8601规范,格式如2016-04-06T08:23:49Z |
Authorization | string | 是 | 用于验证请求合法性的认证信息,更多内容请参考鉴权认证机制,签名工具可参考IAM签名工具 |
- Query参数
只有访问凭证access_token鉴权方式,需使用Query参数。
访问凭证access_token鉴权
名称 | 类型 | 必填 | 描述 |
---|---|---|---|
access_token | string | 是 | 通过API Key和Secret Key获取的access_token,参考Access Token获取 |
- Body参数
名称 | 类型 | 必填 | 描述 |
---|---|---|---|
messages | List(message) | 是 | 聊天上下文信息。说明: (1)messages成员不能为空,1个成员表示单轮对话,多个成员表示多轮对话 (2)最后一个message为当前请求的信息,前面的message为历史对话信息 (3)必须为奇数个成员,成员中message的role必须依次为user、assistant (4)message中的content总长度不能超过11200 个字符 |
stream | bool | 否 | 是否以流式接口的形式返回数据,默认false |
temperature | float | 否 | 说明: (1)较高的数值会使输出更加随机,而较低的数值会使其更加集中和确定 (2)范围 (0, 1.0],不能为0 |
top_k | int | 否 | Top-K 采样参数,在每轮token生成时,保留k个概率最高的token作为候选。说明: (1)影响输出文本的多样性,取值越大,生成文本的多样性越强 (2)取值范围:正整数 |
top_p | float | 否 | 说明: (1)影响输出文本的多样性,取值越大,生成文本的多样性越强 (2)取值范围 [0, 1.0] |
penalty_score | float | 否 | 通过对已生成的token增加惩罚,减少重复生成的现象。说明: (1)值越大表示惩罚越大 (2)取值范围:[1.0, 2.0] |
stop | List(String) | 否 | 生成停止标识。当模型生成结果以stop中某个元素结尾时,停止文本生成。说明: (1)每个元素长度不超过20字符。 (2)最多4个元素 |
user_id | string | 否 | 表示最终用户的唯一标识符 |
message说明
名称 | 类型 | 描述 |
---|---|---|
role | string | 当前支持以下: user: 表示用户 assistant: 表示对话助手 |
content | string | 对话内容,不能为空 |
响应说明
名称 | 类型 | 描述 |
---|---|---|
id | string | 本轮对话的id |
object | string | 回包类型。 chat.completion:多轮对话返回 |
created | int | 时间戳 |
sentence_id | int | 表示当前子句的序号。只有在流式接口模式下会返回该字段 |
is_end | bool | 表示当前子句是否是最后一句。只有在流式接口模式下会返回该字段 |
is_truncated | bool | 当前生成的结果是否被截断 |
result | string | 对话返回结果 |
need_clear_history | bool | 表示用户输入是否存在安全,是否关闭当前会话,清理历史会话信息 true:是,表示用户输入存在安全风险,建议关闭当前会话,清理历史会话信息 false:否,表示用户输入无安全风险 |
ban_round | int | 当need_clear_history为true时,此字段会告知第几轮对话有敏感信息,如果是当前问题,ban_round=-1 |
usage | usage | token统计信息 |
usage说明
名称 | 类型 | 描述 |
---|---|---|
prompt_tokens | int | 问题tokens数 |
completion_tokens | int | 回答tokens数 |
total_tokens | int | tokens总数 |
注意 :同步模式和流式模式,响应参数返回不同,详细内容参考示例描述。
- 同步模式下,响应参数为以上字段的完整json包。
- 流式模式下,各字段的响应参数为 data: {响应参数}。
请求示例(单轮)
以访问凭证access_token鉴权方式为例,说明如何调用API,示例如下。
# 步骤一,获取access_token,替换下列示例中的应用API Key与应用Secret Key
curl 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=[应用API Key]&client_secret=[应用Secret Key]'
# 步骤二,调用本文API,使用步骤一获取的access_token,替换下列示例中的“调用接口获取的access_token”;
curl -X POST 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/gemma_7b_it?access_token=[步骤一调用接口获取的access_token]' -d '{
"messages": [
{"role":"user","content":"Please introduce beijing"}
]
}' | iconv -f utf-8 -t utf-8
import requests
import json
def get_access_token():
"""
使用 API Key,Secret Key 获取access_token,替换下列示例中的应用API Key、应用Secret Key
"""
url = "https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=[应用API Key]&client_secret=[应用Secret Key]"
payload = json.dumps("")
headers = {
'Content-Type': 'application/json',
'Accept': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
return response.json().get("access_token")
def main():
url = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/gemma_7b_it?access_token=" + get_access_token()
payload = json.dumps({
"messages": [
{
"role": "user",
"content": "Please introduce beijing"
}
]
})
headers = {
'Content-Type': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
print(response.text)
if __name__ == '__main__':
main()
响应示例(单轮)
HTTP/1.1 200 OK
Date: Thu, 23 Mar 2023 03:12:03 GMT
Content-Type: application/json;charset=utf-8
Statement: AI-generated
{
"id": "as-v3tyafku74",
"object": "chat.completion",
"created": 1710752493,
"result": " Hello! I'm here to help you with any questions you may have. Beijing is the capital city of China, located in the northern part of the country. It is a city with a rich history and culture, known for its historical landmarks, cultural attractions, and modern infrastructure. Some of the most famous landmarks in Beijing include the Great Wall of China, the Forbidden City, and the Temple of Heaven. Beijing is also home to many museums, parks, and cultural centers, making it a great destination for both domestic and international tourists.\nHowever, I must point out that the term \"Beijing\" is actually the pinyin romanization of the city's Chinese name, which is 北京 (Běijīng). The city's official name in Chinese is 北京市 (Běijīng Shì). Please let me know if you have any other questions!",
"is_truncated": false,
"need_clear_history": false,
"usage": {
"prompt_tokens": 4,
"completion_tokens": 184,
"total_tokens": 188
}
}
请求示例(多轮)
# 步骤一,获取access_token,替换下列示例中的应用API Key与应用Secret Key
curl 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=[应用API Key]&client_secret=[应用Secret Key]'
# 步骤二,调用本文API,使用步骤一获取的access_token,替换下列示例中的“调用接口获取的access_token”;
curl -X POST 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/gemma_7b_it?access_token=[步骤一调用接口获取的access_token]' -d '{
"messages": [
{"role":"user","content":"Please introduce beijing"},
{"role":"assistant","content":" Hello! I'm here to help you with any questions you may have. Beijing is the capital city of China, located in the northern part of the country. It is a city with a rich history and culture, known for its historical landmarks, cultural attractions, and modern infrastructure. Some of the most famous landmarks in Beijing include the Great Wall of China, the Forbidden City, and the Temple of Heaven. Beijing is also home to many museums, parks, and cultural centers, making it a great destination for both domestic and international tourists.\nHowever, I must point out that the term \"Beijing\" is actually the pinyin romanization of the city's Chinese name, which is 北京 (Běijīng). The city's official name in Chinese is 北京市 (Běijīng Shì). Please let me know if you have any other questions!"},
{"role":"user","content": "Please introduce shanghai"}
]
}' | iconv -f utf-8 -t utf-8
import requests
import json
def get_access_token():
"""
使用 API Key,Secret Key 获取access_token,替换下列示例中的应用API Key、应用Secret Key
"""
url = "https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=[应用API Key]&client_secret=[应用Secret Key]"
payload = json.dumps("")
headers = {
'Content-Type': 'application/json',
'Accept': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
return response.json().get("access_token")
def main():
url = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/gemma_7b_it?access_token=" + get_access_token()
payload = json.dumps({
"messages": [
{
"role": "user",
"content": "Please introduce beijing"
},
{
"role": "assistant",
"content": " Hello! I'm here to help you with any questions you may have. Beijing is the capital city of China, located in the northern part of the country. It is a city with a rich history and culture, known for its historical landmarks, cultural attractions, and modern infrastructure. Some of the most famous landmarks in Beijing include the Great Wall of China, the Forbidden City, and the Temple of Heaven. Beijing is also home to many museums, parks, and cultural centers, making it a great destination for both domestic and international tourists.\nHowever, I must point out that the term \"Beijing\" is actually the pinyin romanization of the city's Chinese name, which is 北京 (Běijīng). The city's official name in Chinese is 北京市 (Běijīng Shì). Please let me know if you have any other questions!"
},
{
"role": "user",
"content": "Please introduce shanghai"
}
]
})
headers = {
'Content-Type': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
print(response.text)
if __name__ == '__main__':
main()
响应示例(多轮)
HTTP/1.1 200 OK
Date: Mon, 12 Apr 2021 06:27:55 GMT
Content-Type: application/json;charset=utf-8
Statement: AI-generated
{
"id": "as-qbt6q4dy1b",
"object": "chat.completion",
"created": 1710752681,
"result": "Of course! Shanghai is a city located in the eastern coast of China, and it is the largest city in China in terms of population and economic output. Shanghai is known for its vibrant culture, rich history, and modern infrastructure. The city is home to many famous landmarks, including the iconic Oriental Pearl Tower, the Bund, and the Shanghai Tower, which is the tallest building in China and the second-tallest in the world.\nShanghai is also a major financial and transportation hub, with a bustling port and an international airport that connects the city to the rest of the world. The city has a diverse population, with a mix of Chinese and international influences, and it is known for its vibrant nightlife, delicious food, and cultural events.\nIn addition, Shanghai has a long history, dating back to the 10th century, and it has been a major commercial center for centuries. The city has been influenced by various cultures, including Chinese, European, and Japanese, and it has a unique blend of traditional and modern architecture.\nOverall, Shanghai is a fascinating and exciting city that offers something for everyone, from its rich history and culture to its modern amenities and attractions.",
"is_truncated": false,
"need_clear_history": false,
"usage": {
"prompt_tokens": 193,
"completion_tokens": 249,
"total_tokens": 442
}
}
请求示例(流式)
# 步骤一,获取access_token,替换下列示例中的应用API Key与应用Secret Key
curl 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=[应用API Key]&client_secret=[应用Secret Key]'
# 步骤二,调用本文API,使用步骤一获取的access_token,替换下列示例中的“调用接口获取的access_token”;
curl -X POST 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/gemma_7b_it?access_token=[步骤一调用接口获取的access_token]' -d '{
"messages": [
{"role":"user", "content": "Please introduce beijing"}
],
"stream": true
}'
import requests
import json
def get_access_token():
"""
使用 API Key,Secret Key 获取access_token,替换下列示例中的应用API Key、应用Secret Key
"""
url = "https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=[应用API Key]&client_secret=[应用Secret Key]"
payload = json.dumps("")
headers = {
'Content-Type': 'application/json',
'Accept': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
return response.json().get("access_token")
def main():
url = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/gemma_7b_it?access_token=" + get_access_token()
payload = json.dumps({
"messages": [
{
"role": "user",
"content": "Please introduce beijing"
}
],
"stream": True
})
headers = {
'Content-Type': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload, stream=True)
for line in response.iter_lines():
print(line.decode("UTF-8"))
if __name__ == '__main__':
main()
响应示例(流式)
HTTP/1.1 200 OK
Date: Mon, 12 Apr 2021 06:27:55 GMT
Content-Type: text/event-stream;charset=utf-8
Cache-Control: no-cache
Statement: AI-generated
data: {"id":"as-tmhgw60jxb","object":"chat.completion","created":1710759872,"sentence_id":1,"is_end":false,"is_truncated":false,"result":"m here to help you with any questions you may have. Beijing is the capital city of China,","need_clear_history":false,"usage":{"prompt_tokens":4,"completion_tokens":0,"total_tokens":4}}
data: {"id":"as-tmhgw60jxb","object":"chat.completion","created":1710759872,"sentence_id":2,"is_end":false,"is_truncated":false,"result":" located in the northern part of the country. It is a city with a rich history and culture, known for its ancient temples, palaces, and walls, as well as its modern architecture and vibrant urban life. Beijing is home to many famous landmarks,","need_clear_history":false,"usage":{"prompt_tokens":4,"completion_tokens":0,"total_tokens":4}}
data: {"id":"as-tmhgw60jxb","object":"chat.completion","created":1710759873,"sentence_id":3,"is_end":false,"is_truncated":false,"result":" such as the Great Wall of China, the Forbidden City, and the Temple of Heaven. The city is also known for its delicious cuisine,","need_clear_history":false,"usage":{"prompt_tokens":4,"completion_tokens":0,"total_tokens":4}}
data: {"id":"as-tmhgw60jxb","object":"chat.completion","created":1710759873,"sentence_id":4,"is_end":false,"is_truncated":false,"result":" including traditional dishes such as Peking duck and hot pot. Beijing has a population of over 21 million people and is a major hub for business, culture,","need_clear_history":false,"usage":{"prompt_tokens":4,"completion_tokens":0,"total_tokens":4}}
data: {"id":"as-tmhgw60jxb","object":"chat.completion","created":1710759874,"sentence_id":5,"is_end":true,"is_truncated":false,"result":" and tourism in China. Is there anything else you would like to know about Beijing?","need_clear_history":false,"usage":{"prompt_tokens":4,"completion_tokens":158,"total_tokens":162}}
SDK调用
平台支持通过Python SDK、Go SDK、Java SDK 和 Node.js SDK调用本文API,SDK调用说明文档请参考推理服务V1-对话Chat文档。
错误码
如果请求错误,服务器返回的JSON文本包含以下参数。
名称 | 描述 |
---|---|
error_code | 错误码 |
error_msg | 错误描述信息,帮助理解和解决发生的错误 |
例如Access Token失效返回以下内容,需要重新获取新的Access Token再次请求。
{
"error_code": 110,
"error_msg": "Access token invalid or no longer valid"
}
更多相关错误码,请查看错误码说明。