ros/LlamaFactory
1
0
Fork 0
mirror of https://github.com/hiyouga/LlamaFactory.git synced 2026-02-01 08:13:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

[feat] support new function call value (#9610)

Browse Source 
Co-authored-by: Yaowei Zheng <hiyouga@buaa.edu.cn>
This commit is contained in:
Xunpeng Xiao
2025-12-14 00:20:33 +08:00
committed by GitHub
parent 110d21713e
commit fdd24276ed
2 changed files with 42 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

55
src/llamafactory/data/formatter.py
View File

@@ -97,31 +97,46 @@ class FunctionFormatter(StringFormatter):
@override
def apply(self, **kwargs) -> SLOTS:
content: str = kwargs.pop("content")
thought_words, thought = kwargs.pop("thought_words", None), None
if thought_words and len(thought_words) == 2:
regex = re.compile(rf"{re.escape(thought_words[0])}(.*?){re.escape(thought_words[1])}", re.DOTALL)
thought = re.search(regex, content)
thought_words = kwargs.pop("thought_words", None)
tool_call_words = kwargs.pop("tool_call_words", None)
if thought:
content = content.replace(thought.group(0), "")
def _parse_functions(json_content: str) -> list["FunctionCall"]:
try:
tool_calls = json.loads(json_content)
if not isinstance(tool_calls, list): # parallel function call
tool_calls = [tool_calls]
functions: list[FunctionCall] = []
try:
tool_calls = json.loads(content)
if not isinstance(tool_calls, list): # parallel function call
tool_calls = [tool_calls]
return [FunctionCall(tc["name"], json.dumps(tc["arguments"], ensure_ascii=False)) for tc in tool_calls]
except json.JSONDecodeError:
raise RuntimeError(f"Invalid JSON format in function message: {str([content])}.")
for tool_call in tool_calls:
functions.append(
FunctionCall(tool_call["name"], json.dumps(tool_call["arguments"], ensure_ascii=False))
)
tool_call_match = None
if tool_call_words and len(tool_call_words) == 2:
tool_call_regex = re.compile(
rf"{re.escape(tool_call_words[0])}(.*?){re.escape(tool_call_words[1])}", re.DOTALL
)
tool_call_match = re.search(tool_call_regex, content)
except json.JSONDecodeError:
raise RuntimeError(f"Invalid JSON format in function message: {str([content])}.") # flat string
if tool_call_match is None:
thought_match = None
if thought_words and len(thought_words) == 2:
regex = re.compile(rf"{re.escape(thought_words[0])}(.*?){re.escape(thought_words[1])}", re.DOTALL)
thought_match = re.search(regex, content)
function_str = self.tool_utils.function_formatter(functions)
if thought:
function_str = thought.group(0) + function_str
if thought_match:
json_part = content.replace(thought_match.group(0), "")
else:
json_part = content
functions = _parse_functions(json_part)
function_str = self.tool_utils.function_formatter(functions)
if thought_match:
function_str = thought_match.group(0) + function_str
else:
thought_content = content.replace(tool_call_match.group(0), "")
functions = _parse_functions(tool_call_match.group(1))
function_str = self.tool_utils.function_formatter(functions)
function_str = thought_content + function_str
return super().apply(content=function_str)