src/llamafactory/data/tool_utils.py

# Copyright 2024 the LlamaFactory team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import json
import re
from abc import ABC, abstractmethod
from dataclasses import dataclass
from typing import Any, Dict, List, Tuple, Union

from .data_utils import SLOTS


DEFAULT_TOOL_PROMPT = (
    "You have access to the following tools:\n{tool_text}"
    "Use the following format if using a tool:\n"
    "```\n"
    "Action: tool name (one of [{tool_names}]).\n"
    "Action Input: the input to the tool, in a JSON format representing the kwargs "
    """(e.g. ```{{"input": "hello world", "num_beams": 5}}```).\n"""
    "```\n"
)


GLM4_TOOL_PROMPT = (
    "你是一个名为 ChatGLM 的人工智能助手。你是基于智谱AI训练的语言模型 GLM-4 模型开发的，"
    "你的任务是针对用户的问题和要求提供适当的答复和支持。# 可用工具{tool_text}"
)


@dataclass
class ToolUtils(ABC):
    @staticmethod
    @abstractmethod
    def get_function_slots() -> SLOTS: ...

    @staticmethod
    @abstractmethod
    def tool_formatter(tools: List[Dict[str, Any]]) -> str: ...

    @staticmethod
    @abstractmethod
    def tool_extractor(content: str) -> Union[str, List[Tuple[str, str]]]: ...


class DefaultToolUtils(ToolUtils):
    @staticmethod
    def get_function_slots() -> SLOTS:
        return ["Action: {{name}}\nAction Input: {{arguments}}\n"]

    @staticmethod
    def tool_formatter(tools: List[Dict[str, Any]]) -> str:
        tool_text = ""
        tool_names = []
        for tool in tools:
            param_text = ""
            for name, param in tool["parameters"]["properties"].items():
                required, enum, items = "", "", ""
                if name in tool["parameters"].get("required", []):
                    required = ", required"

                if param.get("enum", None):
                    enum = ", should be one of [{}]".format(", ".join(param["enum"]))

                if param.get("items", None):
                    items = ", where each item should be {}".format(param["items"].get("type", ""))

                param_text += "  - {name} ({type}{required}): {desc}{enum}{items}\n".format(
                    name=name,
                    type=param.get("type", ""),
                    required=required,
                    desc=param.get("description", ""),
                    enum=enum,
                    items=items,
                )

            tool_text += "> Tool Name: {name}\nTool Description: {desc}\nTool Args:\n{args}\n".format(
                name=tool["name"], desc=tool.get("description", ""), args=param_text
            )
            tool_names.append(tool["name"])

        return DEFAULT_TOOL_PROMPT.format(tool_text=tool_text, tool_names=", ".join(tool_names))

    @staticmethod
    def tool_extractor(content: str) -> Union[str, List[Tuple[str, str]]]:
        regex = re.compile(r"Action:\s*([a-zA-Z0-9_]+)\s*Action Input:\s*(.+?)(?=\s*Action:|\s*$)", re.DOTALL)
        action_match: List[Tuple[str, str]] = re.findall(regex, content)
        if not action_match:
            return content

        results = []
        for match in action_match:
            tool_name = match[0].strip()
            tool_input = match[1].strip().strip('"').strip("```")
            try:
                arguments = json.loads(tool_input)
                results.append((tool_name, json.dumps(arguments, ensure_ascii=False)))
            except json.JSONDecodeError:
                return content

        return results


class GLM4ToolUtils(ToolUtils):
    @staticmethod
    def get_function_slots() -> SLOTS:
        return ["{{name}}\n{{arguments}}"]

    @staticmethod
    def tool_formatter(tools: List[Dict[str, Any]]) -> str:
        tool_text = ""
        for tool in tools:
            tool_text += "\n\n## {name}\n\n{body}\n在调用上述函数时，请使用 Json 格式表示调用的参数。".format(
                name=tool["name"], body=json.dumps(tool, indent=4, ensure_ascii=False)
            )

        return GLM4_TOOL_PROMPT.format(tool_text=tool_text)

    @staticmethod
    def tool_extractor(content: str) -> Union[str, List[Tuple[str, str]]]:
        if "\n" not in content:
            return content

        tool_name, tool_input = content.split("\n", maxsplit=1)
        try:
            arguments = json.loads(tool_input)
        except json.JSONDecodeError:
            return content

        return [(tool_name, json.dumps(arguments, ensure_ascii=False))]