Update docs/function_call_guide_cn.md
Browse files- docs/function_call_guide_cn.md +138 -16
docs/function_call_guide_cn.md
CHANGED
|
@@ -6,9 +6,122 @@ MiniMax-M1 模型支持函数调用功能,使模型能够识别何时需要调
|
|
| 6 |
|
| 7 |
## 🚀 快速开始
|
| 8 |
|
| 9 |
-
###
|
| 10 |
|
| 11 |
-
MiniMax-M1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
```python
|
| 14 |
from transformers import AutoTokenizer
|
|
@@ -51,21 +164,26 @@ text = tokenizer.apply_chat_template(
|
|
| 51 |
tools=tools
|
| 52 |
)
|
| 53 |
|
| 54 |
-
#
|
| 55 |
import requests
|
| 56 |
payload = {
|
| 57 |
"model": "MiniMaxAI/MiniMax-M1-40k",
|
| 58 |
"prompt": text,
|
| 59 |
"max_tokens": 4000
|
| 60 |
}
|
| 61 |
-
|
| 62 |
response = requests.post(
|
| 63 |
-
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
```
|
| 70 |
|
| 71 |
## 🛠️ 函数调用的定义
|
|
@@ -121,7 +239,6 @@ You are provided with these tools:
|
|
| 121 |
<tools>
|
| 122 |
{"name": "search_web", "description": "搜索函数。", "parameters": {"properties": {"query_list": {"description": "进行搜索的关键词,列表元素个数为1。", "items": {"type": "string"}, "type": "array"}, "query_tag": {"description": "query的分类", "items": {"type": "string"}, "type": "array"}}, "required": ["query_list", "query_tag"], "type": "object"}}
|
| 123 |
</tools>
|
| 124 |
-
|
| 125 |
If you need to call tools, please respond with <tool_calls></tool_calls> XML tags, and provide tool-name and json-object of arguments, following the format below:
|
| 126 |
<tool_calls>
|
| 127 |
{"name": <tool-name>, "arguments": <args-json-object>}
|
|
@@ -146,16 +263,15 @@ Okay, I will search for the OpenAI and Gemini latest release.
|
|
| 146 |
</tool_calls>
|
| 147 |
```
|
| 148 |
|
| 149 |
-
## 📥
|
| 150 |
|
| 151 |
### 解析函数调用
|
| 152 |
|
| 153 |
-
|
| 154 |
|
| 155 |
```python
|
| 156 |
import re
|
| 157 |
import json
|
| 158 |
-
|
| 159 |
def parse_function_calls(content: str):
|
| 160 |
"""
|
| 161 |
解析模型输出中的函数调用
|
|
@@ -265,8 +381,8 @@ tool result: test_result
|
|
| 265 |
<end_of_sentence>
|
| 266 |
```
|
| 267 |
|
| 268 |
-
|
| 269 |
#### 多个结果
|
|
|
|
| 270 |
假如模型同时调用了 `search_web` 和 `get_current_weather` 函数,您可以参考如下格式添加执行结果,`content`包含多个结果。
|
| 271 |
|
| 272 |
```json
|
|
@@ -292,9 +408,15 @@ tool result: test_result
|
|
| 292 |
<beginning_of_sentence>tool name=tools
|
| 293 |
tool name: search_web
|
| 294 |
tool result: test_result1
|
| 295 |
-
|
| 296 |
tool name: get_current_weather
|
| 297 |
tool result: test_result2<end_of_sentence>
|
| 298 |
```
|
| 299 |
|
| 300 |
虽然我们建议您参考以上格式,但只要返回给模型的输入易于理解,`name` 和 `text` 的具体内容完全由您自主决定。
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
|
| 7 |
## 🚀 快速开始
|
| 8 |
|
| 9 |
+
### 使用 vLLM 进行 Function Calls(推荐)
|
| 10 |
|
| 11 |
+
在实际部署过程中,为了支持类似 OpenAI API 的原生 Function Calling(工具调用)能力,MiniMax-M1 模型集成了专属 `tool_call_parser=minimax` 解析器,从而避免对模型输出结果进行额外的正则解析处理。
|
| 12 |
+
|
| 13 |
+
#### 环境准备与重新编译 vLLM
|
| 14 |
+
|
| 15 |
+
由于该功能尚未正式发布在 PyPI 版本中,需基于源码进行编译。以下为基于 vLLM 官方 Docker 镜像 `vllm/vllm-openai:v0.8.3` 的示例流程:
|
| 16 |
+
|
| 17 |
+
```bash
|
| 18 |
+
IMAGE=vllm/vllm-openai:v0.8.3
|
| 19 |
+
DOCKER_RUN_CMD="--network=host --privileged --ipc=host --ulimit memlock=-1 --shm-size=32gb --rm --gpus all --ulimit stack=67108864"
|
| 20 |
+
|
| 21 |
+
# 运行 docker
|
| 22 |
+
sudo docker run -it -v $MODEL_DIR:$MODEL_DIR \
|
| 23 |
+
-v $CODE_DIR:$CODE_DIR \
|
| 24 |
+
--name vllm_function_call \
|
| 25 |
+
$DOCKER_RUN_CMD \
|
| 26 |
+
--entrypoint /bin/bash \
|
| 27 |
+
$IMAGE
|
| 28 |
+
```
|
| 29 |
+
|
| 30 |
+
#### 编译 vLLM 源码
|
| 31 |
+
|
| 32 |
+
进入容器后,执行以下命令以获取源码并重新安装:
|
| 33 |
+
|
| 34 |
+
```bash
|
| 35 |
+
cd $CODE_DIR
|
| 36 |
+
git clone https://github.com/vllm-project/vllm.git
|
| 37 |
+
cd vllm
|
| 38 |
+
pip install -e .
|
| 39 |
+
```
|
| 40 |
+
|
| 41 |
+
#### 启动 vLLM API 服务
|
| 42 |
+
|
| 43 |
+
```bash
|
| 44 |
+
export SAFETENSORS_FAST_GPU=1
|
| 45 |
+
export VLLM_USE_V1=0
|
| 46 |
+
|
| 47 |
+
python3 -m vllm.entrypoints.openai.api_server \
|
| 48 |
+
--model MiniMax-M1-80k \
|
| 49 |
+
--tensor-parallel-size 8 \
|
| 50 |
+
--trust-remote-code \
|
| 51 |
+
--quantization experts_int8 \
|
| 52 |
+
--enable-auto-tool-choice \
|
| 53 |
+
--tool-call-parser minimax \
|
| 54 |
+
--chat-template vllm/examples/tool_chat_template_minimax_m1.jinja \
|
| 55 |
+
--max_model_len 4096 \
|
| 56 |
+
--dtype bfloat16 \
|
| 57 |
+
--gpu-memory-utilization 0.85
|
| 58 |
+
```
|
| 59 |
+
|
| 60 |
+
**⚠️ 注意:**
|
| 61 |
+
- `--tool-call-parser minimax` 为关键参数,用于启用 MiniMax-M1 自定义解析器
|
| 62 |
+
- `--enable-auto-tool-choice` 启用自动工具选择
|
| 63 |
+
- `--chat-template` 模板文件需要适配 tool calling 格式
|
| 64 |
+
|
| 65 |
+
#### Function Call 测试脚本示例
|
| 66 |
+
|
| 67 |
+
以下 Python 脚本基于 OpenAI SDK 实现了一个天气查询函数的调用示例:
|
| 68 |
+
|
| 69 |
+
```python
|
| 70 |
+
from openai import OpenAI
|
| 71 |
+
import json
|
| 72 |
+
|
| 73 |
+
client = OpenAI(base_url="http://localhost:8000/v1", api_key="dummy")
|
| 74 |
+
|
| 75 |
+
def get_weather(location: str, unit: str):
|
| 76 |
+
return f"Getting the weather for {location} in {unit}..."
|
| 77 |
+
|
| 78 |
+
tool_functions = {"get_weather": get_weather}
|
| 79 |
+
|
| 80 |
+
tools = [{
|
| 81 |
+
"type": "function",
|
| 82 |
+
"function": {
|
| 83 |
+
"name": "get_weather",
|
| 84 |
+
"description": "Get the current weather in a given location",
|
| 85 |
+
"parameters": {
|
| 86 |
+
"type": "object",
|
| 87 |
+
"properties": {
|
| 88 |
+
"location": {"type": "string", "description": "City and state, e.g., 'San Francisco, CA'"},
|
| 89 |
+
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
|
| 90 |
+
},
|
| 91 |
+
"required": ["location", "unit"]
|
| 92 |
+
}
|
| 93 |
+
}
|
| 94 |
+
}]
|
| 95 |
+
|
| 96 |
+
response = client.chat.completions.create(
|
| 97 |
+
model=client.models.list().data[0].id,
|
| 98 |
+
messages=[{"role": "user", "content": "What's the weather like in San Francisco? use celsius."}],
|
| 99 |
+
tools=tools,
|
| 100 |
+
tool_choice="auto"
|
| 101 |
+
)
|
| 102 |
+
|
| 103 |
+
print(response)
|
| 104 |
+
|
| 105 |
+
tool_call = response.choices[0].message.tool_calls[0].function
|
| 106 |
+
print(f"Function called: {tool_call.name}")
|
| 107 |
+
print(f"Arguments: {tool_call.arguments}")
|
| 108 |
+
print(f"Result: {get_weather(**json.loads(tool_call.arguments))}")
|
| 109 |
+
```
|
| 110 |
+
|
| 111 |
+
**输出示例:**
|
| 112 |
+
```
|
| 113 |
+
Function called: get_weather
|
| 114 |
+
Arguments: {"location": "San Francisco, CA", "unit": "celsius"}
|
| 115 |
+
Result: Getting the weather for San Francisco, CA in celsius...
|
| 116 |
+
```
|
| 117 |
+
|
| 118 |
+
### 手动解析模型输出
|
| 119 |
+
|
| 120 |
+
如果您无法使用 vLLM 的内置解析器,或者需要使用其他推理框架(如 transformers、TGI 等),可以使用以下方法手动解析模型的原始输出。这种方法需要您自己解析模型输出的 XML 标签格式。
|
| 121 |
+
|
| 122 |
+
#### 使用 Transformers 的示例
|
| 123 |
+
|
| 124 |
+
以下是使用 transformers 库的完整示例:
|
| 125 |
|
| 126 |
```python
|
| 127 |
from transformers import AutoTokenizer
|
|
|
|
| 164 |
tools=tools
|
| 165 |
)
|
| 166 |
|
| 167 |
+
# 发送请求(这里使用任何推理服务)
|
| 168 |
import requests
|
| 169 |
payload = {
|
| 170 |
"model": "MiniMaxAI/MiniMax-M1-40k",
|
| 171 |
"prompt": text,
|
| 172 |
"max_tokens": 4000
|
| 173 |
}
|
|
|
|
| 174 |
response = requests.post(
|
| 175 |
+
"http://localhost:8000/v1/completions",
|
| 176 |
+
headers={"Content-Type": "application/json"},
|
| 177 |
+
json=payload,
|
| 178 |
+
stream=False,
|
| 179 |
+
)
|
| 180 |
+
|
| 181 |
+
# 模型输出需要手动解析
|
| 182 |
+
raw_output = response.json()["choices"][0]["text"]
|
| 183 |
+
print("原始输出:", raw_output)
|
| 184 |
+
|
| 185 |
+
# 使用下面的解析函数处理输出
|
| 186 |
+
function_calls = parse_function_calls(raw_output)
|
| 187 |
```
|
| 188 |
|
| 189 |
## 🛠️ 函数调用的定义
|
|
|
|
| 239 |
<tools>
|
| 240 |
{"name": "search_web", "description": "搜索函数。", "parameters": {"properties": {"query_list": {"description": "进行搜索的关键词,列表元素个数为1。", "items": {"type": "string"}, "type": "array"}, "query_tag": {"description": "query的分类", "items": {"type": "string"}, "type": "array"}}, "required": ["query_list", "query_tag"], "type": "object"}}
|
| 241 |
</tools>
|
|
|
|
| 242 |
If you need to call tools, please respond with <tool_calls></tool_calls> XML tags, and provide tool-name and json-object of arguments, following the format below:
|
| 243 |
<tool_calls>
|
| 244 |
{"name": <tool-name>, "arguments": <args-json-object>}
|
|
|
|
| 263 |
</tool_calls>
|
| 264 |
```
|
| 265 |
|
| 266 |
+
## 📥 手动解析函数调用结果
|
| 267 |
|
| 268 |
### 解析函数调用
|
| 269 |
|
| 270 |
+
当需要手动解析时,您需要解析模型输出的 XML 标签格式:
|
| 271 |
|
| 272 |
```python
|
| 273 |
import re
|
| 274 |
import json
|
|
|
|
| 275 |
def parse_function_calls(content: str):
|
| 276 |
"""
|
| 277 |
解析模型输出中的函数调用
|
|
|
|
| 381 |
<end_of_sentence>
|
| 382 |
```
|
| 383 |
|
|
|
|
| 384 |
#### 多个结果
|
| 385 |
+
|
| 386 |
假如模型同时调用了 `search_web` 和 `get_current_weather` 函数,您可以参考如下格式添加执行结果,`content`包含多个结果。
|
| 387 |
|
| 388 |
```json
|
|
|
|
| 408 |
<beginning_of_sentence>tool name=tools
|
| 409 |
tool name: search_web
|
| 410 |
tool result: test_result1
|
|
|
|
| 411 |
tool name: get_current_weather
|
| 412 |
tool result: test_result2<end_of_sentence>
|
| 413 |
```
|
| 414 |
|
| 415 |
虽然我们建议您参考以上格式,但只要返回给模型的输入易于理解,`name` 和 `text` 的具体内容完全由您自主决定。
|
| 416 |
+
|
| 417 |
+
## 📚 参考资料
|
| 418 |
+
|
| 419 |
+
- [MiniMax-M1 模型仓库](https://github.com/MiniMaxAI/MiniMax-M1)
|
| 420 |
+
- [vLLM 项目主页](https://github.com/vllm-project/vllm)
|
| 421 |
+
- [vLLM Function Calling PR](https://github.com/vllm-project/vllm/pull/20297)
|
| 422 |
+
- [OpenAI Python SDK](https://github.com/openai/openai-python)
|