Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Translater项目依赖更新，完善环境创建；新增tools、tool_choice调用示例 #123

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Translater项目依赖更新，完善环境创建；新增tools、tool_choice调用示例 #123

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
31c177b
新增：OpenAI最新版本的tools、tool_choice使用
Mar 26, 2025
22d69cb
【FIX】依赖版本明确；环境搭建完善
Mar 26, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 13 additions & 3 deletions openai-translator/README-CN.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,9 +46,20 @@ OpenAI 翻译器目前还处于早期开发阶段，我正在积极地添加更

1.克隆仓库 `git clone [email protected]:DjangoPeng/openai-translator.git`。

2.OpenAI-翻译器 需要 Python 3.6 或更高版本。使用 `pip install -r requirements.txt` 安装依赖项。
2.OpenAI-翻译器 需要 Python 3.6 或更高版本。建议新建一个 Python 虚拟环境，命名为 `translater`。

3.设置您的 OpenAI API 密钥(`$OPENAI_API_KEY`)或 ChatGLM 模型 URL(`$GLM_MODEL_URL`)。您可以将其添加到环境变量中，或者在 config.yaml 文件中指定。
```shell
conda create -n translater python=3.10

# 激活环境
conda activate translater
```

之后每次使用需要激活此环境。

3.使用 `pip install -r requirements.txt` 安装依赖项。

4.设置您的 OpenAI API 密钥(`$OPENAI_API_KEY`)或 ChatGLM 模型 URL(`$GLM_MODEL_URL`)。您可以将其添加到环境变量中，或者在 config.yaml 文件中指定。

### 使用示例

Expand Down Expand Up @@ -104,4 +115,3 @@ python ai_translator/main.py --model_type GLMModel --glm_model_url $GLM_MODEL_UR




17 changes: 15 additions & 2 deletions openai-translator/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,9 +47,22 @@ The OpenAI Translator is still in its early stages of development, and I'm activ

1.Clone the repository `git clone [email protected]:DjangoPeng/openai-translator.git`.

2.The `OpenAI-Translator` requires Python 3.6 or later. Install the dependencies with `pip install -r requirements.txt`.
2.The `OpenAI-Translator` requires Python 3.6 or later.

3.Set up your OpenAI API key(`$OPENAI_API_KEY`) or ChatGLM Model URL(`$GLM_MODEL_URL`). You can either add it to your environment variables or specify it in the config.yaml file.
After installation, it is recommended to create a new Python virtual environment named `translater`.

```
conda create -n translater python=3.10

# Activate the environment
conda activate translater
```

This environment needs to be activated each time before use.

3.Install the dependencies with `pip install -r requirements.txt`.

4.Set up your OpenAI API key(`$OPENAI_API_KEY`) or ChatGLM Model URL(`$GLM_MODEL_URL`). You can either add it to your environment variables or specify it in the config.yaml file.

### Usage

Expand Down
18 changes: 9 additions & 9 deletions openai-translator/requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,9 @@
openai==1.14.2
pdfplumber
simplejson
requests
PyYAML
pillow
reportlab
pandas
loguru
openai==1.65.4
pdfplumber==0.11.5
simplejson==3.20.1
requests==2.32.3
PyYAML==6.0.2
pillow==11.1.0
reportlab==4.3.1
pandas==2.2.3
loguru==0.7.3
221 changes: 146 additions & 75 deletions openai_api/function_call.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -132,12 +132,14 @@
},
{
"cell_type": "code",
"execution_count": null,
"id": "eb420fcd-1a4d-4cc8-90cf-39a92cf28060",
"metadata": {
"jupyter": {
"is_executing": true
}
},
"outputs": [],
"source": [
"# 使用了retry库，指定在请求失败时的重试策略。\n",
"# 这里设定的是指数等待（wait_random_exponential），时间间隔的最大值为40秒，并且最多重试3次（stop_after_attempt(3)）。\n",
Expand Down Expand Up @@ -187,9 +189,7 @@
" print(\"Unable to generate ChatCompletion response\")\n",
" print(f\"Exception: {e}\")\n",
" return e\n"
],
"outputs": [],
"execution_count": null
]
},
{
"cell_type": "code",
Expand Down Expand Up @@ -342,12 +342,12 @@
"name": "stdout",
"output_type": "stream",
"text": [
"\u001B[31msystem: Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.\n",
"\u001B[0m\n",
"\u001B[32muser: What's the weather like today\n",
"\u001B[0m\n",
"\u001B[34massistant[content]: Sure, could you please provide me with the location for which you would like to know the current weather?\n",
"\u001B[0m\n"
"\u001b[31msystem: Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.\n",
"\u001b[0m\n",
"\u001b[32muser: What's the weather like today\n",
"\u001b[0m\n",
"\u001b[34massistant[content]: Sure, could you please provide me with the location for which you would like to know the current weather?\n",
"\u001b[0m\n"
]
}
],
Expand Down Expand Up @@ -443,16 +443,16 @@
"name": "stdout",
"output_type": "stream",
"text": [
"\u001B[31msystem: Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.\n",
"\u001B[0m\n",
"\u001B[32muser: What's the weather like today\n",
"\u001B[0m\n",
"\u001B[34massistant[content]: Sure, could you please provide me with the location for which you would like to know the current weather?\n",
"\u001B[0m\n",
"\u001B[32muser: I'm in Shanghai, China.\n",
"\u001B[0m\n",
"\u001B[34massistant[function_call]: {'name': 'get_current_weather', 'arguments': '{\"location\":\"Shanghai, China\",\"format\":\"celsius\"}'}\n",
"\u001B[0m\n"
"\u001b[31msystem: Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.\n",
"\u001b[0m\n",
"\u001b[32muser: What's the weather like today\n",
"\u001b[0m\n",
"\u001b[34massistant[content]: Sure, could you please provide me with the location for which you would like to know the current weather?\n",
"\u001b[0m\n",
"\u001b[32muser: I'm in Shanghai, China.\n",
"\u001b[0m\n",
"\u001b[34massistant[function_call]: {'name': 'get_current_weather', 'arguments': '{\"location\":\"Shanghai, China\",\"format\":\"celsius\"}'}\n",
"\u001b[0m\n"
]
}
],
Expand Down Expand Up @@ -502,12 +502,12 @@
"name": "stdout",
"output_type": "stream",
"text": [
"\u001B[31msystem: Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.\n",
"\u001B[0m\n",
"\u001B[32muser: what is the weather going to be like in Shanghai, China over the next x days\n",
"\u001B[0m\n",
"\u001B[34massistant[content]: Sure! Please provide the number of days you would like to know the weather forecast for in Shanghai, China.\n",
"\u001B[0m\n"
"\u001b[31msystem: Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.\n",
"\u001b[0m\n",
"\u001b[32muser: what is the weather going to be like in Shanghai, China over the next x days\n",
"\u001b[0m\n",
"\u001b[34massistant[content]: Sure! Please provide the number of days you would like to know the weather forecast for in Shanghai, China.\n",
"\u001b[0m\n"
]
}
],
Expand Down Expand Up @@ -569,16 +569,16 @@
"name": "stdout",
"output_type": "stream",
"text": [
"\u001B[31msystem: Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.\n",
"\u001B[0m\n",
"\u001B[32muser: what is the weather going to be like in Shanghai, China over the next x days\n",
"\u001B[0m\n",
"\u001B[34massistant[content]: Sure! Please provide the number of days you would like to know the weather forecast for in Shanghai, China.\n",
"\u001B[0m\n",
"\u001B[32muser: 5 days\n",
"\u001B[0m\n",
"\u001B[34massistant[function_call]: {'name': 'get_n_day_weather_forecast', 'arguments': '{\"location\":\"Shanghai, China\",\"format\":\"celsius\",\"num_days\":5}'}\n",
"\u001B[0m\n"
"\u001b[31msystem: Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.\n",
"\u001b[0m\n",
"\u001b[32muser: what is the weather going to be like in Shanghai, China over the next x days\n",
"\u001b[0m\n",
"\u001b[34massistant[content]: Sure! Please provide the number of days you would like to know the weather forecast for in Shanghai, China.\n",
"\u001b[0m\n",
"\u001b[32muser: 5 days\n",
"\u001b[0m\n",
"\u001b[34massistant[function_call]: {'name': 'get_n_day_weather_forecast', 'arguments': '{\"location\":\"Shanghai, China\",\"format\":\"celsius\",\"num_days\":5}'}\n",
"\u001b[0m\n"
]
}
],
Expand Down Expand Up @@ -634,12 +634,12 @@
"name": "stdout",
"output_type": "stream",
"text": [
"\u001B[31msystem: Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.\n",
"\u001B[0m\n",
"\u001B[32muser: Give me a weather report for San Diego, USA.\n",
"\u001B[0m\n",
"\u001B[34massistant[function_call]: {'name': 'get_n_day_weather_forecast', 'arguments': '{\"location\":\"San Diego, USA\",\"format\":\"celsius\",\"num_days\":1}'}\n",
"\u001B[0m\n"
"\u001b[31msystem: Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.\n",
"\u001b[0m\n",
"\u001b[32muser: Give me a weather report for San Diego, USA.\n",
"\u001b[0m\n",
"\u001b[34massistant[function_call]: {'name': 'get_n_day_weather_forecast', 'arguments': '{\"location\":\"San Diego, USA\",\"format\":\"celsius\",\"num_days\":1}'}\n",
"\u001b[0m\n"
]
}
],
Expand Down Expand Up @@ -692,12 +692,12 @@
"name": "stdout",
"output_type": "stream",
"text": [
"\u001B[31msystem: Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.\n",
"\u001B[0m\n",
"\u001B[32muser: Give me a weather report for San Diego, USA.\n",
"\u001B[0m\n",
"\u001B[34massistant[function_call]: {'name': 'get_current_weather', 'arguments': '{\"location\":\"San Diego, USA\",\"format\":\"celsius\"}'}\n",
"\u001B[0m\n"
"\u001b[31msystem: Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.\n",
"\u001b[0m\n",
"\u001b[32muser: Give me a weather report for San Diego, USA.\n",
"\u001b[0m\n",
"\u001b[34massistant[function_call]: {'name': 'get_current_weather', 'arguments': '{\"location\":\"San Diego, USA\",\"format\":\"celsius\"}'}\n",
"\u001b[0m\n"
]
}
],
Expand Down Expand Up @@ -759,12 +759,12 @@
"name": "stdout",
"output_type": "stream",
"text": [
"\u001B[31msystem: Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.\n",
"\u001B[0m\n",
"\u001B[32muser: Give me the current weather (use Celcius) for Toronto, Canada.\n",
"\u001B[0m\n",
"\u001B[34massistant[content]: Sure! Let me retrieve the current weather for Toronto, Canada in Celsius.\n",
"\u001B[0m\n"
"\u001b[31msystem: Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.\n",
"\u001b[0m\n",
"\u001b[32muser: Give me the current weather (use Celcius) for Toronto, Canada.\n",
"\u001b[0m\n",
"\u001b[34massistant[content]: Sure! Let me retrieve the current weather for Toronto, Canada in Celsius.\n",
"\u001b[0m\n"
]
}
],
Expand Down Expand Up @@ -1119,14 +1119,14 @@
"name": "stdout",
"output_type": "stream",
"text": [
"\u001B[31msystem: Answer user questions by generating SQL queries against the Chinook Music Database.\n",
"\u001B[0m\n",
"\u001B[32muser: Hi, who are the top 5 artists by number of tracks?\n",
"\u001B[0m\n",
"\u001B[34massistant[function_call]: {'name': 'ask_database', 'arguments': '{\"query\":\"SELECT artists.Name, COUNT(tracks.TrackId) AS TrackCount\\\\nFROM artists\\\\nJOIN albums ON artists.ArtistId = albums.ArtistId\\\\nJOIN tracks ON albums.AlbumId = tracks.AlbumId\\\\nGROUP BY artists.Name\\\\nORDER BY TrackCount DESC\\\\nLIMIT 5;\"}'}\n",
"\u001B[0m\n",
"\u001B[35mfunction (ask_database): [('Iron Maiden', 213), ('U2', 135), ('Led Zeppelin', 114), ('Metallica', 112), ('Lost', 92)]\n",
"\u001B[0m\n"
"\u001b[31msystem: Answer user questions by generating SQL queries against the Chinook Music Database.\n",
"\u001b[0m\n",
"\u001b[32muser: Hi, who are the top 5 artists by number of tracks?\n",
"\u001b[0m\n",
"\u001b[34massistant[function_call]: {'name': 'ask_database', 'arguments': '{\"query\":\"SELECT artists.Name, COUNT(tracks.TrackId) AS TrackCount\\\\nFROM artists\\\\nJOIN albums ON artists.ArtistId = albums.ArtistId\\\\nJOIN tracks ON albums.AlbumId = tracks.AlbumId\\\\nGROUP BY artists.Name\\\\nORDER BY TrackCount DESC\\\\nLIMIT 5;\"}'}\n",
"\u001b[0m\n",
"\u001b[35mfunction (ask_database): [('Iron Maiden', 213), ('U2', 135), ('Led Zeppelin', 114), ('Metallica', 112), ('Lost', 92)]\n",
"\u001b[0m\n"
]
}
],
Expand Down Expand Up @@ -1254,20 +1254,20 @@
"name": "stdout",
"output_type": "stream",
"text": [
"\u001B[31msystem: Answer user questions by generating SQL queries against the Chinook Music Database.\n",
"\u001B[0m\n",
"\u001B[32muser: Hi, who are the top 5 artists by number of tracks?\n",
"\u001B[0m\n",
"\u001B[34massistant[function_call]: {'name': 'ask_database', 'arguments': '{\"query\":\"SELECT artists.Name, COUNT(tracks.TrackId) AS TrackCount\\\\nFROM artists\\\\nJOIN albums ON artists.ArtistId = albums.ArtistId\\\\nJOIN tracks ON albums.AlbumId = tracks.AlbumId\\\\nGROUP BY artists.Name\\\\nORDER BY TrackCount DESC\\\\nLIMIT 5;\"}'}\n",
"\u001B[0m\n",
"\u001B[35mfunction (ask_database): [('Iron Maiden', 213), ('U2', 135), ('Led Zeppelin', 114), ('Metallica', 112), ('Lost', 92)]\n",
"\u001B[0m\n",
"\u001B[32muser: What is the name of the album with the most tracks?\n",
"\u001B[0m\n",
"\u001B[34massistant[function_call]: {'name': 'ask_database', 'arguments': '{\"query\":\"SELECT albums.Title, COUNT(tracks.TrackId) AS TrackCount\\\\nFROM albums\\\\nJOIN tracks ON albums.AlbumId = tracks.AlbumId\\\\nGROUP BY albums.Title\\\\nORDER BY TrackCount DESC\\\\nLIMIT 1;\"}'}\n",
"\u001B[0m\n",
"\u001B[35mfunction (ask_database): [('Greatest Hits', 57)]\n",
"\u001B[0m\n"
"\u001b[31msystem: Answer user questions by generating SQL queries against the Chinook Music Database.\n",
"\u001b[0m\n",
"\u001b[32muser: Hi, who are the top 5 artists by number of tracks?\n",
"\u001b[0m\n",
"\u001b[34massistant[function_call]: {'name': 'ask_database', 'arguments': '{\"query\":\"SELECT artists.Name, COUNT(tracks.TrackId) AS TrackCount\\\\nFROM artists\\\\nJOIN albums ON artists.ArtistId = albums.ArtistId\\\\nJOIN tracks ON albums.AlbumId = tracks.AlbumId\\\\nGROUP BY artists.Name\\\\nORDER BY TrackCount DESC\\\\nLIMIT 5;\"}'}\n",
"\u001b[0m\n",
"\u001b[35mfunction (ask_database): [('Iron Maiden', 213), ('U2', 135), ('Led Zeppelin', 114), ('Metallica', 112), ('Lost', 92)]\n",
"\u001b[0m\n",
"\u001b[32muser: What is the name of the album with the most tracks?\n",
"\u001b[0m\n",
"\u001b[34massistant[function_call]: {'name': 'ask_database', 'arguments': '{\"query\":\"SELECT albums.Title, COUNT(tracks.TrackId) AS TrackCount\\\\nFROM albums\\\\nJOIN tracks ON albums.AlbumId = tracks.AlbumId\\\\nGROUP BY albums.Title\\\\nORDER BY TrackCount DESC\\\\nLIMIT 1;\"}'}\n",
"\u001b[0m\n",
"\u001b[35mfunction (ask_database): [('Greatest Hits', 57)]\n",
"\u001b[0m\n"
]
}
],
Expand Down Expand Up @@ -1303,6 +1303,77 @@
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"id": "3dbcb0e6",
"metadata": {},
"source": [
"## OpenAI最新版本的tools、tool_choice使用\n",
"[新增]最新OpenAI版本的functions和function_call已经被tools、tool_choice所替代\n",
"参考： https://platform.openai.com/docs/guides/function-calling"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a24ad343",
"metadata": {},
"outputs": [],
"source": [
"from openai import OpenAI\n",
"import os\n",
"\n",
"# DeepSeek API调用（deepseek-chat）\n",
"client = OpenAI(\n",
" api_key=\"XXX\",\n",
" base_url=\"https://api.deepseek.com\"\n",
")\n",
"\n",
"response = client.chat.completions.create(\n",
" model=\"deepseek-chat\", # 替换为您使用的模型\n",
" messages=[\n",
" {\"role\": \"user\", \"content\": \"今天北京天气怎么样？\"}\n",
" ],\n",
" tools=[\n",
" {\n",
" \"type\": \"function\",\n",
" \"function\": {\n",
" \"name\": \"get_n_day_weather_forecast\",\n",
" \"description\": \"获取未来N天的天气预报\",\n",
" \"parameters\": {\n",
" \"type\": \"object\",\n",
" \"properties\": {\n",
" \"location\": {\n",
" \"type\": \"string\",\n",
" \"description\": \"要查询天气的城市名称\"\n",
" },\n",
" \"days\": {\n",
" \"type\": \"integer\",\n",
" \"description\": \"要查询的天数\"\n",
" }\n",
" },\n",
" \"required\": [\"location\", \"days\"]\n",
" }\n",
" }\n",
" }\n",
" ],\n",
" tool_choice={\"type\": \"function\", \"function\": {\"name\": \"get_n_day_weather_forecast\"}}\n",
")\n",
"\n",
"print(response)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2247fe31",
"metadata": {},
"outputs": [],
"source": [
"print(response.choices[0].finish_reason)\n",
"print(response.choices[0].message.tool_calls)"
]
},
{
"cell_type": "markdown",
"id": "b5c5dc6e-0a61-46a1-b04f-03f23c9161b2",
Expand Down