总结与编辑文本

在 Python 中使用 DeepSeek

James Chapman

AI Curriculum Lead, DataCamp

回顾…

  • 问答
response = client.chat.completions.create(
  model="deepseek-ai/DeepSeek-V4-Pro",
  messages=[{"role": "user", "content": "How many days are in October?"}]
)

print(response.choices[0].message.content)

October has **31 days**.  

It's one of the seven months in the Gregorian calendar with 31 days...
在 Python 中使用 DeepSeek

文本编辑

  • 示例：更新姓名、代词和职位

$$

prompt = """
Update name to Maarten, pronouns to he/him, and job title to Senior Content Developer
in the following text:

Joanne is a Content Developer at DataCamp. Her favorite programming language is R,
which she uses for her statistical analyses.
"""
在 Python 中使用 DeepSeek

文本编辑

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Pro",

    messages=[{"role": "user", "content": prompt}]

)

print(response.choices[0].message.content)

Here's the updated text with the requested changes:

Maarten is a Senior Content Developer at DataCamp. His favorite programming language
is R, which he uses for his statistical analyses.

Let me know if you'd like any further adjustments!
在 Python 中使用 DeepSeek

文本摘要

  • 示例：客户聊天记录摘要

客户支持团队

text = """
Customer: Hi, I'm trying to log into 
my account, but it keeps saying 
my password is incorrect. I'm sure 
I'm entering the right one.  

Support: I'm sorry to hear that! 
Have you tried resetting your password?  
...
"""
在 Python 中使用 DeepSeek

文本摘要

prompt = f"""Summarize the customer support chat 
             in three concise key points: {text}"""


response = client.chat.completions.create(
  model="deepseek-ai/DeepSeek-V4-Pro",
  messages=[{"role": "user", "content": prompt}]
)
print(response.choices[0].message.content)

1. **登录问题**：因密码错误且未收到重置链接，用户无法登录。
2. **重置建议**：支持在确认发送后重新发送了重置邮件。
3. **快速解决**：用户改用 Google 登录并解决。
在 Python 中使用 DeepSeek

控制响应长度

  • max_tokens = 5
response = client.chat.completions.create(
  model="deepseek-ai/DeepSeek-V4-Pro",
  messages=[{"role":"user",
      "content":"Write a haiku about AI."}],
  max_tokens=5
)


**Silent circuits hum
  • max_tokens = 30
response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Pro",
    messages=[{"role":"user",
      "content":"Write a haiku about AI."}],
    max_tokens=30
)


**Silent circuits hum,**  
**thoughts of light and logic bloom—**  
**minds beyond our own.**
在 Python 中使用 DeepSeek

理解 Token

$$

  • Token（标记）：帮助 AI 理解与处理文本的最小文本单位

$$

句子 "How can the OpenAI API deliver business value?"，其中每个 token 用不同颜色高亮。

1 https://lunary.ai/deepseek-tokenizer
在 Python 中使用 DeepSeek

计算成本

 

  • API 费用取决于平台、模型和token 数量 💰

    • 定价以成本/token计
    • 输入与输出 token 可能价格不同

  • 提高 max_tokens 会增加成本 📈

Screenshot 2025-03-05 at 11.46.54.png

在 Python 中使用 DeepSeek

计算成本

prompt = f"""Summarize the customer support chat 
             in three concise key points: {text}"""

max_tokens = 500

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Pro",
    messages=[{"role": "user", "content": prompt}], 
    max_tokens=max_tokens
)
在 Python 中使用 DeepSeek

计算成本

# Define price per token
input_token_price = 2.1 / 1_000_000
output_token_price = 4.4 / 1_000_000

# Extract token usage
input_tokens = response.usage.prompt_tokens

output_tokens = max_tokens

# Calculate cost
cost = (input_tokens * input_token_price + output_tokens * output_token_price)
print(f"Estimated cost: ${cost}")

Estimated cost: $0.0153964
在 Python 中使用 DeepSeek

Vamos praticar!

在 Python 中使用 DeepSeek

Preparing Video For Download...