fix #4402 #4617

Deprecate reserved_label_len arg


Former-commit-id: 4b6568984c0be4b31e7aa91b7c0d52b7f7b12b0b

src/llamafactory/data/formatter.py

@@ -16,97 +16,10 @@ import json
 import re
 from abc import ABC, abstractmethod
 from dataclasses import dataclass, field
-from typing import Any, Dict, List, Literal, Optional, Sequence, Set, Tuple, Union
+from typing import List, Literal, Optional, Tuple, Union
 
-
-SLOTS = Sequence[Union[str, Set[str], Dict[str, str]]]
-
-
-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}"
-)
-
-
-def default_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 = ", required" if name in tool["parameters"].get("required", []) else ""
-            enum = ", should be one of [{}]".format(", ".join(param["enum"])) if param.get("enum", None) else ""
-            items = (
-                ", where each item should be {}".format(param["items"].get("type", "")) if param.get("items") else ""
-            )
-            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))
-
-
-def default_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
-
-
-def glm4_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)
-
-
-def glm4_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))]
+from .data_utils import SLOTS
+from .tool_utils import DefaultToolUtils, GLM4ToolUtils
 
 
 @dataclass
@@ -168,15 +81,12 @@ class StringFormatter(Formatter):
 @dataclass
 class FunctionFormatter(Formatter):
     def __post_init__(self):
-        has_name, has_args = False, False
-        for slot in filter(lambda s: isinstance(s, str), self.slots):
-            if "{{name}}" in slot:
-                has_name = True
-            if "{{arguments}}" in slot:
-                has_args = True
-
-        if not has_name or not has_args:
-            raise ValueError("Name and arguments placeholders are required in the function formatter.")
+        if self.tool_format == "default":
+            self.slots = DefaultToolUtils.get_function_slots() + self.slots
+        elif self.tool_format == "glm4":
+            self.slots = GLM4ToolUtils.get_function_slots() + self.slots
+        else:
+            raise NotImplementedError("Tool format {} was not found.".format(self.tool_format))
 
     def apply(self, **kwargs) -> SLOTS:
         content = kwargs.pop("content")
@@ -210,11 +120,11 @@ class FunctionFormatter(Formatter):
 class ToolFormatter(Formatter):
     def __post_init__(self):
         if self.tool_format == "default":
-            self._tool_formatter = default_tool_formatter
-            self._tool_extractor = default_tool_extractor
+            self._tool_formatter = DefaultToolUtils.tool_formatter
+            self._tool_extractor = DefaultToolUtils.tool_extractor
         elif self.tool_format == "glm4":
-            self._tool_formatter = glm4_tool_formatter
-            self._tool_extractor = glm4_tool_extractor
+            self._tool_formatter = GLM4ToolUtils.tool_formatter
+            self._tool_extractor = GLM4ToolUtils.tool_extractor
         else:
             raise NotImplementedError("Tool format {} was not found.".format(self.tool_format))