Merge branch 'dev_zxh'
This commit is contained in:
commit
d7c19cdc6a
|
|
@ -4,6 +4,7 @@ Think标签过滤器模块 - 支持LlamaIndex流式响应
|
|||
|
||||
from typing import Tuple, Any, Union, Optional
|
||||
import json
|
||||
import re
|
||||
|
||||
class OptimizedDeltaThinkFilter:
|
||||
"""
|
||||
|
|
@ -85,7 +86,6 @@ class OptimizedDeltaThinkFilter:
|
|||
# 检查是否包含常见字段
|
||||
if 'text=' in str_repr or 'delta=' in str_repr or 'content=' in str_repr:
|
||||
# 尝试提取引号内的内容
|
||||
import re
|
||||
text_match = re.search(r'text=[\'"](.*?)[\'"]', str_repr)
|
||||
if text_match:
|
||||
return text_match.group(1)
|
||||
|
|
@ -143,54 +143,137 @@ class OptimizedDeltaThinkFilter:
|
|||
delta_text = self._extract_llamaindex_content(chunk)
|
||||
|
||||
if not delta_text:
|
||||
# 即使没有文本内容，返回当前状态
|
||||
return "", self.output_text, False
|
||||
|
||||
|
||||
# 添加到buffer
|
||||
self.buffer += delta_text
|
||||
output_delta = ""
|
||||
|
||||
# 使用状态机处理
|
||||
i = 0
|
||||
while i < len(self.buffer):
|
||||
if not self.in_think:
|
||||
# 不在think标签内，查找开始标签
|
||||
start = self.buffer.find('<think>', i)
|
||||
if start == -1:
|
||||
# 没有think标签，剩余都是有效文本
|
||||
valid_text = self.buffer[i:]
|
||||
output_delta += valid_text
|
||||
self.output_text += valid_text
|
||||
i = len(self.buffer)
|
||||
# 寻找开始标签
|
||||
start_idx = self.buffer.lower().find('<think>', i)
|
||||
if start_idx == -1:
|
||||
# FIXED: 检查是否有孤立的结束标签
|
||||
end_idx = self.buffer.lower().find('</think>', i)
|
||||
if end_idx != -1:
|
||||
# FIXED: 如果发现孤立结束标签，说明之前的内容都是think内容，应该丢弃
|
||||
# 直接跳过结束标签之前的所有内容
|
||||
# print(f"DEBUG: 发现孤立结束标签，丢弃 {self.buffer[i:end_idx]}")
|
||||
i = end_idx + len('</think>') # 只跳过结束标签
|
||||
continue
|
||||
else:
|
||||
# 没有think标签，剩余都是有效文本
|
||||
valid_text = self.buffer[i:]
|
||||
output_delta += valid_text
|
||||
self.output_text += valid_text
|
||||
i = len(self.buffer)
|
||||
else:
|
||||
# 输出think标签前的部分
|
||||
valid_before = self.buffer[i:start]
|
||||
valid_before = self.buffer[i:start_idx]
|
||||
output_delta += valid_before
|
||||
self.output_text += valid_before
|
||||
|
||||
# 进入think模式
|
||||
self.in_think = True
|
||||
i = start + len('<think>')
|
||||
i = start_idx + len('<think>')
|
||||
|
||||
# 处理立即闭合的标签
|
||||
if self.buffer.find('</think>', i) == i:
|
||||
if self.buffer.lower().find('</think>', i) == i:
|
||||
i += len('</think>')
|
||||
self.in_think = False
|
||||
else:
|
||||
# 在think标签内，查找结束标签
|
||||
end = self.buffer.find('</think>', i)
|
||||
if end == -1:
|
||||
end_idx = self.buffer.lower().find('</think>', i)
|
||||
if end_idx == -1:
|
||||
# 结束标签还没到，跳过所有内容
|
||||
i = len(self.buffer)
|
||||
else:
|
||||
# 找到结束标签
|
||||
self.in_think = False
|
||||
i = end + len('</think>')
|
||||
i = end_idx + len('</think>')
|
||||
|
||||
# 清理已处理的buffer
|
||||
self.buffer = self.buffer[i:] if i < len(self.buffer) else ""
|
||||
|
||||
has_output = len(output_delta) > 0
|
||||
return output_delta, self.output_text, has_output
|
||||
|
||||
|
||||
def process_delta_robust(self, chunk: Any) -> Tuple[str, str, bool]:
|
||||
"""
|
||||
更健壮的处理方法，使用正则表达式
|
||||
|
||||
Args:
|
||||
chunk: LlamaIndex流式chunk
|
||||
|
||||
Returns:
|
||||
Tuple[str, str, bool]: 处理结果
|
||||
"""
|
||||
# 提取文本
|
||||
delta_text = self._extract_llamaindex_content(chunk)
|
||||
|
||||
if not delta_text:
|
||||
return "", self.output_text, False
|
||||
|
||||
# 添加到buffer
|
||||
self.buffer += delta_text
|
||||
|
||||
output_delta = ""
|
||||
processed_text = ""
|
||||
|
||||
# 状态机处理
|
||||
while True:
|
||||
if not self.in_think:
|
||||
# 寻找开始标签
|
||||
start_match = re.search(r'<think>', self.buffer, re.IGNORECASE)
|
||||
if not start_match:
|
||||
# FIXED: 检查是否有孤立的结束标签
|
||||
end_match = re.search(r'</think>', self.buffer, re.IGNORECASE)
|
||||
if end_match:
|
||||
# FIXED: 如果发现孤立结束标签，说明之前的内容都是think内容，应该丢弃
|
||||
# 只移除结束标签，之前的内容已在上个chunk中被跳过
|
||||
end_pos = end_match.start()
|
||||
# print(f"DEBUG: 发现孤立结束标签，位置 {end_pos}")
|
||||
self.buffer = self.buffer[end_pos + len('</think>'):]
|
||||
continue
|
||||
else:
|
||||
# 既没有开始也没有结束标签，全部输出
|
||||
processed_text = self.buffer
|
||||
self.buffer = ""
|
||||
break
|
||||
|
||||
# 输出开始标签之前的内容
|
||||
start_pos = start_match.start()
|
||||
output_before = self.buffer[:start_pos]
|
||||
processed_text += output_before
|
||||
|
||||
# 移动buffer
|
||||
self.buffer = self.buffer[start_pos + len('<think>'):]
|
||||
self.in_think = True
|
||||
else:
|
||||
# 在think标签内，寻找结束标签
|
||||
end_match = re.search(r'</think>', self.buffer, re.IGNORECASE)
|
||||
if not end_match:
|
||||
# 结束标签不在这个buffer中
|
||||
# 清空buffer（think内容），等待下一个chunk
|
||||
self.buffer = ""
|
||||
break
|
||||
|
||||
# 找到结束标签
|
||||
end_pos = end_match.start()
|
||||
# 跳过think内容
|
||||
self.buffer = self.buffer[end_pos + len('</think>'):]
|
||||
self.in_think = False
|
||||
|
||||
# 更新输出
|
||||
output_delta = processed_text
|
||||
self.output_text += processed_text
|
||||
|
||||
has_output = len(output_delta) > 0
|
||||
return output_delta, self.output_text, has_output
|
||||
|
||||
def process_with_metadata(self, chunk: Any) -> dict:
|
||||
"""
|
||||
|
|
@ -206,7 +289,7 @@ class OptimizedDeltaThinkFilter:
|
|||
original_content = self._extract_llamaindex_content(chunk)
|
||||
|
||||
# 处理内容
|
||||
delta_output, full_text, has_output = self.process_delta(original_content)
|
||||
delta_output, full_text, has_output = self.process_delta_robust(original_content)
|
||||
|
||||
return {
|
||||
"delta": delta_output,
|
||||
|
|
|
|||
|
|
@ -259,7 +259,7 @@ class RAGEngine:
|
|||
async for chunk in stream_response:
|
||||
# 提取文本内容
|
||||
# text_chunk = self.extract_text_from_chunk(chunk)
|
||||
delta, full_text, has_output = think_filter.process_delta(chunk)
|
||||
delta, full_text, has_output = think_filter.process_delta_robust(chunk)
|
||||
|
||||
if delta is not None:
|
||||
full_response += delta
|
||||
|
|
|
|||
Loading…
Reference in New Issue