您正在学习的是试看内容，报名后可学习全部内容
报名课程
当前课程未解锁
3.1 LangChain 入门
主要内容：
- 环境准备：Python、LangChain、Jupyter Notebook 安装
- LLM 实战：基于 LangChain 实现 Prompt、Tool calling、Structured output 以及 Reasoning
1. 环境准备
1.1. 软件安装
1.1.1. Python 安装
Python 3.10+
https://www.python.org/downloads/
1.1.2. LangChain 安装
https://docs.langchain.com/oss/python/langchain/install
https://github.com/langchain-ai
1.1.3. Jupyter 安装
2. LangChain 实战
2.1. OpenAI API 调用
2.1.1. 示例代码
2.1.1.1. 使用 Open AI API 调用 qwen 模型
import os
from openai import OpenAI
client = OpenAI(
# 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx",
api_key=os.getenv("DASHSCOPE_API_KEY"),
base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
model="qwen-plus", # 此处以qwen-plus为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
messages=[
{'role': 'system', 'content': 'You are a helpful assistant.'},
{'role': 'user', 'content': '你是谁？'}],
max_tokens=100, # 设置最大输出token数
)
print(completion.model_dump_json())2.1.1.2. 使用 LangChain Open AI API 调用 qwen 模型
from langchain_openai import ChatOpenAI
import os
chatLLM = ChatOpenAI(
api_key=os.getenv("DASHSCOPE_API_KEY"),
base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
model="qwen-plus", # 此处以qwen-plus为例，您可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
# other params...
)
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "你是谁？"}]
response = chatLLM.invoke(messages)
print(response.to_json())2.1.1.3. 使用 DashScope API 调用 qwen 模型
import os
from dashscope import Generation
messages = [
{'role': 'system', 'content': 'You are a helpful assistant.'},
{'role': 'user', 'content': '你是谁？'}
]
response = Generation.call(
# 若没有配置环境变量，请用百炼API Key将下行替换为：api_key = "sk-xxx",
api_key=os.getenv("DASHSCOPE_API_KEY"),
model="qwen-plus", # 模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
messages=messages,
result_format="message"
)
if response.status_code == 200:
print(response.output.choices[0].message.content)
else:
print(f"HTTP返回码：{response.status_code}")
print(f"错误码：{response.code}")
print(f"错误信息：{response.message}")
print("请参考文档：https://help.aliyun.com/zh/model-studio/developer-reference/error-code")2.2. 提示词（Prompts）
2.2.1. 零样本提示（Zero-Shot Prompting）
from langchain_openai import ChatOpenAI
from langchain.messages import HumanMessage, AIMessage, SystemMessage
import os
chatLLM = ChatOpenAI(
api_key=os.getenv("DASHSCOPE_API_KEY"),
base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
model="qwen-plus", # 此处以qwen-plus为例，您可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
# other params...
)
systemMessage = SystemMessage(content="You are a helpful assistant.");
userMessage = HumanMessage(content="""
Classify the text into neutral, negative or positive.
Text: I think the vacation is okay.
Sentiment:
""");
messages = [systemMessage, userMessage];
response = chatLLM.invoke(messages)
print(response.content)2.2.2. 少样本提示（Few-Shot Prompting）
from langchain_openai import ChatOpenAI
from langchain.messages import HumanMessage, AIMessage, SystemMessage
import os
chatLLM = ChatOpenAI(
api_key=os.getenv("DASHSCOPE_API_KEY"),
base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
model="qwen-plus", # 此处以qwen-plus为例，您可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
# other params...
)
systemMessage = SystemMessage(content="You are a helpful assistant.");
userMessage = HumanMessage(content="""
A "whatpu" is a small, furry animal native to Tanzania. An example of a sentence that uses the word whatpu is:
We were traveling in Africa and we saw these very cute whatpus.
To do a "farduddle" means to jump up and down really fast. An example of a sentence that uses the word farduddle is:
""");
messages = [systemMessage, userMessage];
response = chatLLM.invoke(messages)
print(response.content)