安装 | 许可证 | 行为准则 | 贡献

GenAI: 为IPython的生成式AI工具

🦾 在IPython中使用代码、SQL查询、DataFrames、异常等获取GPT帮助。

🌍 支持所有Jupyter环境，包括IPython、JupyterLab、Jupyter Notebook和Noteable。

TL;DR 现在开始

%pip install genai
%load_ext genai

Genai应用实例

• 博客文章
• 示例笔记本

介绍

我们从IPython中提取了上下文，结合了OpenAI的大型语言模型，为您提供了一种更全面的笔记本体验，该体验适用于所有Jupyter环境，包括IPython、JupyterLab、Jupyter Notebook和Noteable。 🦾🌏

需求

Python 3.8+

安装

Poetry

poetry add genai

Pip

pip install genai

加载IPython扩展

在使用IPython或您首选的笔记本平台之前，请确保首先设置OPENAI_API_KEY环境变量。

%load_ext genai

特性

• %%assist 魔法命令，可以从自然语言生成代码
• 自定义异常建议

自定义异常建议

In [1]: %load_ext genai

In [2]: import pandas as pd

In [3]: df = pd.DataFrame(dict(col1=['a', 'b', 'c']), index=['first', 'second', 'third'])

In [4]: df.sort_values()
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[4], line 1
----> 1 df.sort_values()

File ~/.pyenv/versions/3.9.9/lib/python3.9/site-packages/pandas/util/_decorators.py:331, in deprecate_nonkeyword_arguments.<locals>.decorate.<locals>.wrapper(*args, **kwargs)
    325 if len(args) > num_allow_args:
    326     warnings.warn(
    327         msg.format(arguments=_format_argument_list(allow_args)),
    328         FutureWarning,
    329         stacklevel=find_stack_level(),
    330     )
--> 331 return func(*args, **kwargs)

TypeError: sort_values() missing 1 required positional argument: 'by'

💡 建议

错误消息表明pandas数据框的sort_values()方法缺少一个必需的位置参数。

sort_values()方法需要您传递一个列名或列名列表作为by参数。这将用于确定排序方式。

以下是一个示例

import pandas as pd

df = pd.DataFrame({
    'Name': ['Alice', 'Bob', 'Carol', 'David', 'Eva'],
    'Age': [32, 24, 28, 35, 29],
    'Salary': [60000, 40000, 35000, 80000, 45000]
})

# sort by Age column:
df_sorted = df.sort_values(by='Age')
print(df_sorted)

在这个示例中，by参数设置为'Age'，按年龄升序排序数据框。请注意，如果您想按多个列排序，也可以传递列名列表。

示例

In [1]: %load_ext genai

In [2]: %%assist
   ...:
   ...: Can you explain this query to me so I can be sure we're doing the right things?
   ...:
   ...: ```sql
   ...: SELECT
   ...:   COUNT(*) AS num_downloads,
   ...:   DATE_TRUNC(DATE(timestamp), DAY) AS day
   ...: FROM `bigquery-public-data.pypi.file_downloads`
   ...: WHERE
   ...:   file.project = 'genai'
   ...:   -- Only query the last 6 months of history
   ...:   AND DATE(timestamp)
   ...:     BETWEEN DATE_TRUNC(DATE_SUB(CURRENT_DATE(), INTERVAL 6 MONTH), MONTH)
   ...:     AND CURRENT_DATE()
   ...: GROUP BY day
   ...: ORDER BY day DESC

"This is a SQL query that counts the number of downloads for the 'genai' project on the Python Package Index (PyPI) over the last 6 months, grouped by day. The query selects the count and the date, truncating the date to the day level so that it's easier to read.

Here is a breakdown of each part of the query:

- `SELECT COUNT(*) AS num_downloads, DATE_TRUNC(DATE(timestamp), DAY) AS day`: This selects the count of the number of rows matched by the query as `num_downloads`, and the date truncated to the day level as `day`.
- `FROM `bigquery-public-data.pypi.file_downloads``: This specifies the table to query from.
- `WHERE file.project = 'genai'`: This filters the rows by only including downloads for the 'genai' project.
- `AND DATE(timestamp) BETWEEN DATE_TRUNC(DATE_SUB(CURRENT_DATE(), INTERVAL 6 MONTH), MONTH) AND CURRENT_DATE()`: This filters the rows by only including downloads from the last 6 months. The `DATE_SUB` function subtracts 6 months from the current date (`CURRENT_DATE()`), `DATE_TRUNC` truncates the result to be the start of the month and `DATE` converts the timestamp column to a date so the `BETWEEN` condition can filter rows between the start of 6 months ago and "today."
- `GROUP BY day`: This groups the rows by day so that the counts are aggregated by date.
- `ORDER BY day DESC`: This orders the rows so that the most recent date appears first in the result."