mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-06-11 00:06:04 +00:00
Merge branch 'rc/new-plugin' into refactor/new-plugin-system
This commit is contained in:
Junyan Qin
@@ -102,8 +102,14 @@ class DashScopeAPIRunner(runner.RequestRunner):
|
||||
plain_text = '' # 用户输入的纯文本信息
|
||||
image_ids = [] # 用户输入的图片ID列表 （暂不支持）
|
||||
|
||||
plain_text, image_ids = await self._preprocess_user_message(query)
|
||||
think_start = False
|
||||
think_end = False
|
||||
|
||||
plain_text, image_ids = await self._preprocess_user_message(query)
|
||||
has_thoughts = True # 获取思考过程
|
||||
remove_think = self.pipeline_config['output'].get('misc', '').get('remove-think')
|
||||
if remove_think:
|
||||
has_thoughts = False
|
||||
# 发送对话请求
|
||||
response = dashscope.Application.call(
|
||||
api_key=self.api_key, # 智能体应用的API Key
|
||||
@@ -112,43 +118,108 @@ class DashScopeAPIRunner(runner.RequestRunner):
|
||||
stream=True, # 流式输出
|
||||
incremental_output=True, # 增量输出，使用流式输出需要开启增量输出
|
||||
session_id=query.session.using_conversation.uuid, # 会话ID用于，多轮对话
|
||||
has_thoughts=has_thoughts,
|
||||
# rag_options={ # 主要用于文件交互，暂不支持
|
||||
# "session_file_ids": ["FILE_ID1"], # FILE_ID1 替换为实际的临时文件ID,逗号隔开多个
|
||||
# }
|
||||
)
|
||||
idx_chunk = 0
|
||||
try:
|
||||
is_stream = await query.adapter.is_stream_output_supported()
|
||||
|
||||
for chunk in response:
|
||||
if chunk.get('status_code') != 200:
|
||||
raise DashscopeAPIError(
|
||||
f'Dashscope API 请求失败: status_code={chunk.get("status_code")} message={chunk.get("message")} request_id={chunk.get("request_id")} '
|
||||
)
|
||||
if not chunk:
|
||||
continue
|
||||
except AttributeError:
|
||||
is_stream = False
|
||||
if is_stream:
|
||||
for chunk in response:
|
||||
if chunk.get('status_code') != 200:
|
||||
raise DashscopeAPIError(
|
||||
f'Dashscope API 请求失败: status_code={chunk.get("status_code")} message={chunk.get("message")} request_id={chunk.get("request_id")} '
|
||||
)
|
||||
if not chunk:
|
||||
continue
|
||||
idx_chunk += 1
|
||||
# 获取流式传输的output
|
||||
stream_output = chunk.get('output', {})
|
||||
stream_think = stream_output.get('thoughts', [])
|
||||
if stream_think[0].get('thought'):
|
||||
if not think_start:
|
||||
think_start = True
|
||||
pending_content += f'<think>\n{stream_think[0].get("thought")}'
|
||||
else:
|
||||
# 继续输出 reasoning_content
|
||||
pending_content += stream_think[0].get('thought')
|
||||
elif stream_think[0].get('thought') == '' and not think_end:
|
||||
think_end = True
|
||||
pending_content += '\n</think>\n'
|
||||
if stream_output.get('text') is not None:
|
||||
pending_content += stream_output.get('text')
|
||||
# 是否是流式最后一个chunk
|
||||
is_final = False if stream_output.get('finish_reason', False) == 'null' else True
|
||||
|
||||
# 获取流式传输的output
|
||||
stream_output = chunk.get('output', {})
|
||||
if stream_output.get('text') is not None:
|
||||
pending_content += stream_output.get('text')
|
||||
# 获取模型传出的参考资料列表
|
||||
references_dict_list = stream_output.get('doc_references', [])
|
||||
|
||||
# 保存当前会话的session_id用于下次对话的语境
|
||||
query.session.using_conversation.uuid = stream_output.get('session_id')
|
||||
# 从模型传出的参考资料信息中提取用于替换的字典
|
||||
if references_dict_list is not None:
|
||||
for doc in references_dict_list:
|
||||
if doc.get('index_id') is not None:
|
||||
references_dict[doc.get('index_id')] = doc.get('doc_name')
|
||||
|
||||
# 获取模型传出的参考资料列表
|
||||
references_dict_list = stream_output.get('doc_references', [])
|
||||
# 将参考资料替换到文本中
|
||||
pending_content = self._replace_references(pending_content, references_dict)
|
||||
|
||||
# 从模型传出的参考资料信息中提取用于替换的字典
|
||||
if references_dict_list is not None:
|
||||
for doc in references_dict_list:
|
||||
if doc.get('index_id') is not None:
|
||||
references_dict[doc.get('index_id')] = doc.get('doc_name')
|
||||
if idx_chunk % 8 == 0 or is_final:
|
||||
yield provider_message.MessageChunk(
|
||||
role='assistant',
|
||||
content=pending_content,
|
||||
is_final=is_final,
|
||||
)
|
||||
# 保存当前会话的session_id用于下次对话的语境
|
||||
query.session.using_conversation.uuid = stream_output.get('session_id')
|
||||
else:
|
||||
for chunk in response:
|
||||
if chunk.get('status_code') != 200:
|
||||
raise DashscopeAPIError(
|
||||
f'Dashscope API 请求失败: status_code={chunk.get("status_code")} message={chunk.get("message")} request_id={chunk.get("request_id")} '
|
||||
)
|
||||
if not chunk:
|
||||
continue
|
||||
idx_chunk += 1
|
||||
# 获取流式传输的output
|
||||
stream_output = chunk.get('output', {})
|
||||
stream_think = stream_output.get('thoughts', [])
|
||||
if stream_think[0].get('thought'):
|
||||
if not think_start:
|
||||
think_start = True
|
||||
pending_content += f'<think>\n{stream_think[0].get("thought")}'
|
||||
else:
|
||||
# 继续输出 reasoning_content
|
||||
pending_content += stream_think[0].get('thought')
|
||||
elif stream_think[0].get('thought') == '' and not think_end:
|
||||
think_end = True
|
||||
pending_content += '\n</think>\n'
|
||||
if stream_output.get('text') is not None:
|
||||
pending_content += stream_output.get('text')
|
||||
|
||||
# 将参考资料替换到文本中
|
||||
pending_content = self._replace_references(pending_content, references_dict)
|
||||
# 保存当前会话的session_id用于下次对话的语境
|
||||
query.session.using_conversation.uuid = stream_output.get('session_id')
|
||||
|
||||
yield provider_message.Message(
|
||||
role='assistant',
|
||||
content=pending_content,
|
||||
)
|
||||
# 获取模型传出的参考资料列表
|
||||
references_dict_list = stream_output.get('doc_references', [])
|
||||
|
||||
# 从模型传出的参考资料信息中提取用于替换的字典
|
||||
if references_dict_list is not None:
|
||||
for doc in references_dict_list:
|
||||
if doc.get('index_id') is not None:
|
||||
references_dict[doc.get('index_id')] = doc.get('doc_name')
|
||||
|
||||
# 将参考资料替换到文本中
|
||||
pending_content = self._replace_references(pending_content, references_dict)
|
||||
|
||||
yield provider_message.Message(
|
||||
role='assistant',
|
||||
content=pending_content,
|
||||
)
|
||||
|
||||
async def _workflow_messages(
|
||||
self, query: pipeline_query.Query
|
||||
@@ -176,52 +247,108 @@ class DashScopeAPIRunner(runner.RequestRunner):
|
||||
incremental_output=True, # 增量输出，使用流式输出需要开启增量输出
|
||||
session_id=query.session.using_conversation.uuid, # 会话ID用于，多轮对话
|
||||
biz_params=biz_params, # 工作流应用的自定义输入参数传递
|
||||
flow_stream_mode='message_format', # 消息模式，输出/结束节点的流式结果
|
||||
# rag_options={ # 主要用于文件交互，暂不支持
|
||||
# "session_file_ids": ["FILE_ID1"], # FILE_ID1 替换为实际的临时文件ID,逗号隔开多个
|
||||
# }
|
||||
)
|
||||
|
||||
# 处理API返回的流式输出
|
||||
for chunk in response:
|
||||
if chunk.get('status_code') != 200:
|
||||
raise DashscopeAPIError(
|
||||
f'Dashscope API 请求失败: status_code={chunk.get("status_code")} message={chunk.get("message")} request_id={chunk.get("request_id")} '
|
||||
)
|
||||
if not chunk:
|
||||
continue
|
||||
try:
|
||||
is_stream = await query.adapter.is_stream_output_supported()
|
||||
|
||||
# 获取流式传输的output
|
||||
stream_output = chunk.get('output', {})
|
||||
if stream_output.get('text') is not None:
|
||||
pending_content += stream_output.get('text')
|
||||
except AttributeError:
|
||||
is_stream = False
|
||||
idx_chunk = 0
|
||||
if is_stream:
|
||||
for chunk in response:
|
||||
if chunk.get('status_code') != 200:
|
||||
raise DashscopeAPIError(
|
||||
f'Dashscope API 请求失败: status_code={chunk.get("status_code")} message={chunk.get("message")} request_id={chunk.get("request_id")} '
|
||||
)
|
||||
if not chunk:
|
||||
continue
|
||||
idx_chunk += 1
|
||||
# 获取流式传输的output
|
||||
stream_output = chunk.get('output', {})
|
||||
if stream_output.get('workflow_message') is not None:
|
||||
pending_content += stream_output.get('workflow_message').get('message').get('content')
|
||||
# if stream_output.get('text') is not None:
|
||||
# pending_content += stream_output.get('text')
|
||||
|
||||
# 保存当前会话的session_id用于下次对话的语境
|
||||
query.session.using_conversation.uuid = stream_output.get('session_id')
|
||||
is_final = False if stream_output.get('finish_reason', False) == 'null' else True
|
||||
|
||||
# 获取模型传出的参考资料列表
|
||||
references_dict_list = stream_output.get('doc_references', [])
|
||||
# 获取模型传出的参考资料列表
|
||||
references_dict_list = stream_output.get('doc_references', [])
|
||||
|
||||
# 从模型传出的参考资料信息中提取用于替换的字典
|
||||
if references_dict_list is not None:
|
||||
for doc in references_dict_list:
|
||||
if doc.get('index_id') is not None:
|
||||
references_dict[doc.get('index_id')] = doc.get('doc_name')
|
||||
# 从模型传出的参考资料信息中提取用于替换的字典
|
||||
if references_dict_list is not None:
|
||||
for doc in references_dict_list:
|
||||
if doc.get('index_id') is not None:
|
||||
references_dict[doc.get('index_id')] = doc.get('doc_name')
|
||||
|
||||
# 将参考资料替换到文本中
|
||||
pending_content = self._replace_references(pending_content, references_dict)
|
||||
# 将参考资料替换到文本中
|
||||
pending_content = self._replace_references(pending_content, references_dict)
|
||||
if idx_chunk % 8 == 0 or is_final:
|
||||
yield provider_message.MessageChunk(
|
||||
role='assistant',
|
||||
content=pending_content,
|
||||
is_final=is_final,
|
||||
)
|
||||
|
||||
yield provider_message.Message(
|
||||
role='assistant',
|
||||
content=pending_content,
|
||||
)
|
||||
# 保存当前会话的session_id用于下次对话的语境
|
||||
query.session.using_conversation.uuid = stream_output.get('session_id')
|
||||
|
||||
else:
|
||||
for chunk in response:
|
||||
if chunk.get('status_code') != 200:
|
||||
raise DashscopeAPIError(
|
||||
f'Dashscope API 请求失败: status_code={chunk.get("status_code")} message={chunk.get("message")} request_id={chunk.get("request_id")} '
|
||||
)
|
||||
if not chunk:
|
||||
continue
|
||||
|
||||
# 获取流式传输的output
|
||||
stream_output = chunk.get('output', {})
|
||||
if stream_output.get('text') is not None:
|
||||
pending_content += stream_output.get('text')
|
||||
|
||||
is_final = False if stream_output.get('finish_reason', False) == 'null' else True
|
||||
|
||||
# 保存当前会话的session_id用于下次对话的语境
|
||||
query.session.using_conversation.uuid = stream_output.get('session_id')
|
||||
|
||||
# 获取模型传出的参考资料列表
|
||||
references_dict_list = stream_output.get('doc_references', [])
|
||||
|
||||
# 从模型传出的参考资料信息中提取用于替换的字典
|
||||
if references_dict_list is not None:
|
||||
for doc in references_dict_list:
|
||||
if doc.get('index_id') is not None:
|
||||
references_dict[doc.get('index_id')] = doc.get('doc_name')
|
||||
|
||||
# 将参考资料替换到文本中
|
||||
pending_content = self._replace_references(pending_content, references_dict)
|
||||
|
||||
yield provider_message.Message(
|
||||
role='assistant',
|
||||
content=pending_content,
|
||||
)
|
||||
|
||||
async def run(self, query: pipeline_query.Query) -> typing.AsyncGenerator[provider_message.Message, None]:
|
||||
"""运行"""
|
||||
msg_seq = 0
|
||||
if self.app_type == 'agent':
|
||||
async for msg in self._agent_messages(query):
|
||||
if isinstance(msg, provider_message.MessageChunk):
|
||||
msg_seq += 1
|
||||
msg.msg_sequence = msg_seq
|
||||
yield msg
|
||||
elif self.app_type == 'workflow':
|
||||
async for msg in self._workflow_messages(query):
|
||||
if isinstance(msg, provider_message.MessageChunk):
|
||||
msg_seq += 1
|
||||
msg.msg_sequence = msg_seq
|
||||
yield msg
|
||||
else:
|
||||
raise DashscopeAPIError(f'不支持的 Dashscope 应用类型: {self.app_type}')
|
||||
|
||||
@@ -3,7 +3,6 @@ from __future__ import annotations
|
||||
import typing
|
||||
import json
|
||||
import uuid
|
||||
import re
|
||||
import base64
|
||||
|
||||
|
||||
@@ -38,29 +37,38 @@ class DifyServiceAPIRunner(runner.RequestRunner):
|
||||
base_url=self.pipeline_config['ai']['dify-service-api']['base-url'],
|
||||
)
|
||||
|
||||
def _try_convert_thinking(self, resp_text: str) -> str:
|
||||
"""尝试转换 Dify 的思考提示"""
|
||||
if not resp_text.startswith(
|
||||
'<details style="color:gray;background-color: #f8f8f8;padding: 8px;border-radius: 4px;" open> <summary> Thinking... </summary>'
|
||||
):
|
||||
return resp_text
|
||||
def _process_thinking_content(
|
||||
self,
|
||||
content: str,
|
||||
) -> tuple[str, str]:
|
||||
"""处理思维链内容
|
||||
|
||||
if self.pipeline_config['ai']['dify-service-api']['thinking-convert'] == 'original':
|
||||
return resp_text
|
||||
Args:
|
||||
content: 原始内容
|
||||
Returns:
|
||||
(处理后的内容, 提取的思维链内容)
|
||||
"""
|
||||
remove_think = self.pipeline_config['output'].get('misc', '').get('remove-think')
|
||||
thinking_content = ''
|
||||
# 从 content 中提取 <think> 标签内容
|
||||
if content and '<think>' in content and '</think>' in content:
|
||||
import re
|
||||
|
||||
if self.pipeline_config['ai']['dify-service-api']['thinking-convert'] == 'remove':
|
||||
return re.sub(
|
||||
r'<details style="color:gray;background-color: #f8f8f8;padding: 8px;border-radius: 4px;" open> <summary> Thinking... </summary>.*?</details>',
|
||||
'',
|
||||
resp_text,
|
||||
flags=re.DOTALL,
|
||||
)
|
||||
think_pattern = r'<think>(.*?)</think>'
|
||||
think_matches = re.findall(think_pattern, content, re.DOTALL)
|
||||
if think_matches:
|
||||
thinking_content = '\n'.join(think_matches)
|
||||
# 移除 content 中的 <think> 标签
|
||||
content = re.sub(think_pattern, '', content, flags=re.DOTALL).strip()
|
||||
|
||||
if self.pipeline_config['ai']['dify-service-api']['thinking-convert'] == 'plain':
|
||||
pattern = r'<details style="color:gray;background-color: #f8f8f8;padding: 8px;border-radius: 4px;" open> <summary> Thinking... </summary>(.*?)</details>'
|
||||
thinking_text = re.search(pattern, resp_text, flags=re.DOTALL)
|
||||
content_text = re.sub(pattern, '', resp_text, flags=re.DOTALL)
|
||||
return f'<think>{thinking_text.group(1)}</think>\n{content_text}'
|
||||
# 3. 根据 remove_think 参数决定是否保留思维链
|
||||
if remove_think:
|
||||
return content, ''
|
||||
else:
|
||||
# 如果有思维链内容，将其以 <think> 格式添加到 content 开头
|
||||
if thinking_content:
|
||||
content = f'<think>\n{thinking_content}\n</think>\n{content}'.strip()
|
||||
return content, thinking_content
|
||||
|
||||
async def _preprocess_user_message(self, query: pipeline_query.Query) -> tuple[str, list[str]]:
|
||||
"""预处理用户消息，提取纯文本，并将图片上传到 Dify 服务
|
||||
@@ -134,17 +142,20 @@ class DifyServiceAPIRunner(runner.RequestRunner):
|
||||
if mode == 'workflow':
|
||||
if chunk['event'] == 'node_finished':
|
||||
if chunk['data']['node_type'] == 'answer':
|
||||
content, _ = self._process_thinking_content(chunk['data']['outputs']['answer'])
|
||||
|
||||
yield provider_message.Message(
|
||||
role='assistant',
|
||||
content=self._try_convert_thinking(chunk['data']['outputs']['answer']),
|
||||
content=content,
|
||||
)
|
||||
elif mode == 'basic':
|
||||
if chunk['event'] == 'message':
|
||||
basic_mode_pending_chunk += chunk['answer']
|
||||
elif chunk['event'] == 'message_end':
|
||||
content, _ = self._process_thinking_content(basic_mode_pending_chunk)
|
||||
yield provider_message.Message(
|
||||
role='assistant',
|
||||
content=self._try_convert_thinking(basic_mode_pending_chunk),
|
||||
content=content,
|
||||
)
|
||||
basic_mode_pending_chunk = ''
|
||||
|
||||
@@ -195,14 +206,15 @@ class DifyServiceAPIRunner(runner.RequestRunner):
|
||||
if chunk['event'] in ignored_events:
|
||||
continue
|
||||
|
||||
if chunk['event'] == 'agent_message':
|
||||
if chunk['event'] == 'agent_message' or chunk['event'] == 'message':
|
||||
pending_agent_message += chunk['answer']
|
||||
else:
|
||||
if pending_agent_message.strip() != '':
|
||||
pending_agent_message = pending_agent_message.replace('</details>Action:', '</details>')
|
||||
content, _ = self._process_thinking_content(pending_agent_message)
|
||||
yield provider_message.Message(
|
||||
role='assistant',
|
||||
content=self._try_convert_thinking(pending_agent_message),
|
||||
content=content,
|
||||
)
|
||||
pending_agent_message = ''
|
||||
|
||||
@@ -312,26 +324,352 @@ class DifyServiceAPIRunner(runner.RequestRunner):
|
||||
elif chunk['event'] == 'workflow_finished':
|
||||
if chunk['data']['error']:
|
||||
raise errors.DifyAPIError(chunk['data']['error'])
|
||||
content, _ = self._process_thinking_content(chunk['data']['outputs']['summary'])
|
||||
|
||||
msg = provider_message.Message(
|
||||
role='assistant',
|
||||
content=chunk['data']['outputs']['summary'],
|
||||
content=content,
|
||||
)
|
||||
|
||||
yield msg
|
||||
|
||||
async def _chat_messages_chunk(
|
||||
self, query: pipeline_query.Query
|
||||
) -> typing.AsyncGenerator[provider_message.MessageChunk, None]:
|
||||
"""调用聊天助手"""
|
||||
cov_id = query.session.using_conversation.uuid or ''
|
||||
query.variables['conversation_id'] = cov_id
|
||||
|
||||
plain_text, image_ids = await self._preprocess_user_message(query)
|
||||
|
||||
files = [
|
||||
{
|
||||
'type': 'image',
|
||||
'transfer_method': 'local_file',
|
||||
'upload_file_id': image_id,
|
||||
}
|
||||
for image_id in image_ids
|
||||
]
|
||||
|
||||
basic_mode_pending_chunk = ''
|
||||
|
||||
inputs = {}
|
||||
|
||||
inputs.update(query.variables)
|
||||
message_idx = 0
|
||||
|
||||
chunk = None # 初始化chunk变量，防止在没有响应时引用错误
|
||||
|
||||
is_final = False
|
||||
think_start = False
|
||||
think_end = False
|
||||
|
||||
remove_think = self.pipeline_config['output'].get('misc', '').get('remove-think')
|
||||
|
||||
async for chunk in self.dify_client.chat_messages(
|
||||
inputs=inputs,
|
||||
query=plain_text,
|
||||
user=f'{query.session.launcher_type.value}_{query.session.launcher_id}',
|
||||
conversation_id=cov_id,
|
||||
files=files,
|
||||
timeout=120,
|
||||
):
|
||||
self.ap.logger.debug('dify-chat-chunk: ' + str(chunk))
|
||||
|
||||
# if chunk['event'] == 'workflow_started':
|
||||
# mode = 'workflow'
|
||||
# if mode == 'workflow':
|
||||
# elif mode == 'basic':
|
||||
# 因为都只是返回的 message也没有工具调用什么的，暂时不分类
|
||||
if chunk['event'] == 'message':
|
||||
message_idx += 1
|
||||
if remove_think:
|
||||
if '<think>' in chunk['answer'] and not think_start:
|
||||
think_start = True
|
||||
continue
|
||||
if '</think>' in chunk['answer'] and not think_end:
|
||||
import re
|
||||
|
||||
content = re.sub(r'^\n</think>', '', chunk['answer'])
|
||||
basic_mode_pending_chunk += content
|
||||
think_end = True
|
||||
elif think_end:
|
||||
basic_mode_pending_chunk += chunk['answer']
|
||||
if think_start:
|
||||
continue
|
||||
|
||||
else:
|
||||
basic_mode_pending_chunk += chunk['answer']
|
||||
|
||||
if chunk['event'] == 'message_end':
|
||||
is_final = True
|
||||
|
||||
if is_final or message_idx % 8 == 0:
|
||||
# content, _ = self._process_thinking_content(basic_mode_pending_chunk)
|
||||
yield provider_message.MessageChunk(
|
||||
role='assistant',
|
||||
content=basic_mode_pending_chunk,
|
||||
is_final=is_final,
|
||||
)
|
||||
|
||||
if chunk is None:
|
||||
raise errors.DifyAPIError('Dify API 没有返回任何响应，请检查网络连接和API配置')
|
||||
|
||||
query.session.using_conversation.uuid = chunk['conversation_id']
|
||||
|
||||
async def _agent_chat_messages_chunk(
|
||||
self, query: pipeline_query.Query
|
||||
) -> typing.AsyncGenerator[provider_message.MessageChunk, None]:
|
||||
"""调用聊天助手"""
|
||||
cov_id = query.session.using_conversation.uuid or ''
|
||||
query.variables['conversation_id'] = cov_id
|
||||
|
||||
plain_text, image_ids = await self._preprocess_user_message(query)
|
||||
|
||||
files = [
|
||||
{
|
||||
'type': 'image',
|
||||
'transfer_method': 'local_file',
|
||||
'upload_file_id': image_id,
|
||||
}
|
||||
for image_id in image_ids
|
||||
]
|
||||
|
||||
ignored_events = []
|
||||
|
||||
inputs = {}
|
||||
|
||||
inputs.update(query.variables)
|
||||
|
||||
pending_agent_message = ''
|
||||
|
||||
chunk = None # 初始化chunk变量，防止在没有响应时引用错误
|
||||
message_idx = 0
|
||||
is_final = False
|
||||
think_start = False
|
||||
think_end = False
|
||||
|
||||
remove_think = self.pipeline_config['output'].get('misc', '').get('remove-think')
|
||||
|
||||
async for chunk in self.dify_client.chat_messages(
|
||||
inputs=inputs,
|
||||
query=plain_text,
|
||||
user=f'{query.session.launcher_type.value}_{query.session.launcher_id}',
|
||||
response_mode='streaming',
|
||||
conversation_id=cov_id,
|
||||
files=files,
|
||||
timeout=120,
|
||||
):
|
||||
self.ap.logger.debug('dify-agent-chunk: ' + str(chunk))
|
||||
|
||||
if chunk['event'] in ignored_events:
|
||||
continue
|
||||
|
||||
if chunk['event'] == 'agent_message':
|
||||
message_idx += 1
|
||||
if remove_think:
|
||||
if '<think>' in chunk['answer'] and not think_start:
|
||||
think_start = True
|
||||
continue
|
||||
if '</think>' in chunk['answer'] and not think_end:
|
||||
import re
|
||||
|
||||
content = re.sub(r'^\n</think>', '', chunk['answer'])
|
||||
pending_agent_message += content
|
||||
think_end = True
|
||||
elif think_end or not think_start:
|
||||
pending_agent_message += chunk['answer']
|
||||
if think_start:
|
||||
continue
|
||||
|
||||
else:
|
||||
pending_agent_message += chunk['answer']
|
||||
elif chunk['event'] == 'message_end':
|
||||
is_final = True
|
||||
else:
|
||||
if chunk['event'] == 'agent_thought':
|
||||
if chunk['tool'] != '' and chunk['observation'] != '': # 工具调用结果，跳过
|
||||
continue
|
||||
message_idx += 1
|
||||
if chunk['tool']:
|
||||
msg = provider_message.MessageChunk(
|
||||
role='assistant',
|
||||
tool_calls=[
|
||||
provider_message.ToolCall(
|
||||
id=chunk['id'],
|
||||
type='function',
|
||||
function=provider_message.FunctionCall(
|
||||
name=chunk['tool'],
|
||||
arguments=json.dumps({}),
|
||||
),
|
||||
)
|
||||
],
|
||||
)
|
||||
yield msg
|
||||
if chunk['event'] == 'message_file':
|
||||
message_idx += 1
|
||||
if chunk['type'] == 'image' and chunk['belongs_to'] == 'assistant':
|
||||
base_url = self.dify_client.base_url
|
||||
|
||||
if base_url.endswith('/v1'):
|
||||
base_url = base_url[:-3]
|
||||
|
||||
image_url = base_url + chunk['url']
|
||||
|
||||
yield provider_message.MessageChunk(
|
||||
role='assistant',
|
||||
content=[provider_message.ContentElement.from_image_url(image_url)],
|
||||
is_final=is_final,
|
||||
)
|
||||
|
||||
if chunk['event'] == 'error':
|
||||
raise errors.DifyAPIError('dify 服务错误: ' + chunk['message'])
|
||||
if message_idx % 8 == 0 or is_final:
|
||||
yield provider_message.MessageChunk(
|
||||
role='assistant',
|
||||
content=pending_agent_message,
|
||||
is_final=is_final,
|
||||
)
|
||||
|
||||
if chunk is None:
|
||||
raise errors.DifyAPIError('Dify API 没有返回任何响应，请检查网络连接和API配置')
|
||||
|
||||
query.session.using_conversation.uuid = chunk['conversation_id']
|
||||
|
||||
async def _workflow_messages_chunk(
|
||||
self, query: pipeline_query.Query
|
||||
) -> typing.AsyncGenerator[provider_message.MessageChunk, None]:
|
||||
"""调用工作流"""
|
||||
|
||||
if not query.session.using_conversation.uuid:
|
||||
query.session.using_conversation.uuid = str(uuid.uuid4())
|
||||
|
||||
query.variables['conversation_id'] = query.session.using_conversation.uuid
|
||||
|
||||
plain_text, image_ids = await self._preprocess_user_message(query)
|
||||
|
||||
files = [
|
||||
{
|
||||
'type': 'image',
|
||||
'transfer_method': 'local_file',
|
||||
'upload_file_id': image_id,
|
||||
}
|
||||
for image_id in image_ids
|
||||
]
|
||||
|
||||
ignored_events = ['workflow_started']
|
||||
|
||||
inputs = { # these variables are legacy variables, we need to keep them for compatibility
|
||||
'langbot_user_message_text': plain_text,
|
||||
'langbot_session_id': query.variables['session_id'],
|
||||
'langbot_conversation_id': query.variables['conversation_id'],
|
||||
'langbot_msg_create_time': query.variables['msg_create_time'],
|
||||
}
|
||||
|
||||
inputs.update(query.variables)
|
||||
messsage_idx = 0
|
||||
is_final = False
|
||||
think_start = False
|
||||
think_end = False
|
||||
workflow_contents = ''
|
||||
|
||||
remove_think = self.pipeline_config['output'].get('misc', '').get('remove-think')
|
||||
async for chunk in self.dify_client.workflow_run(
|
||||
inputs=inputs,
|
||||
user=f'{query.session.launcher_type.value}_{query.session.launcher_id}',
|
||||
files=files,
|
||||
timeout=120,
|
||||
):
|
||||
self.ap.logger.debug('dify-workflow-chunk: ' + str(chunk))
|
||||
if chunk['event'] in ignored_events:
|
||||
continue
|
||||
if chunk['event'] == 'workflow_finished':
|
||||
is_final = True
|
||||
if chunk['data']['error']:
|
||||
raise errors.DifyAPIError(chunk['data']['error'])
|
||||
|
||||
if chunk['event'] == 'text_chunk':
|
||||
messsage_idx += 1
|
||||
if remove_think:
|
||||
if '<think>' in chunk['data']['text'] and not think_start:
|
||||
think_start = True
|
||||
continue
|
||||
if '</think>' in chunk['data']['text'] and not think_end:
|
||||
import re
|
||||
|
||||
content = re.sub(r'^\n</think>', '', chunk['data']['text'])
|
||||
workflow_contents += content
|
||||
think_end = True
|
||||
elif think_end:
|
||||
workflow_contents += chunk['data']['text']
|
||||
if think_start:
|
||||
continue
|
||||
|
||||
else:
|
||||
workflow_contents += chunk['data']['text']
|
||||
|
||||
if chunk['event'] == 'node_started':
|
||||
if chunk['data']['node_type'] == 'start' or chunk['data']['node_type'] == 'end':
|
||||
continue
|
||||
messsage_idx += 1
|
||||
msg = provider_message.MessageChunk(
|
||||
role='assistant',
|
||||
content=None,
|
||||
tool_calls=[
|
||||
provider_message.ToolCall(
|
||||
id=chunk['data']['node_id'],
|
||||
type='function',
|
||||
function=provider_message.FunctionCall(
|
||||
name=chunk['data']['title'],
|
||||
arguments=json.dumps({}),
|
||||
),
|
||||
)
|
||||
],
|
||||
)
|
||||
|
||||
yield msg
|
||||
|
||||
if messsage_idx % 8 == 0 or is_final:
|
||||
yield provider_message.MessageChunk(
|
||||
role='assistant',
|
||||
content=workflow_contents,
|
||||
is_final=is_final,
|
||||
)
|
||||
|
||||
async def run(self, query: pipeline_query.Query) -> typing.AsyncGenerator[provider_message.Message, None]:
|
||||
"""运行请求"""
|
||||
if self.pipeline_config['ai']['dify-service-api']['app-type'] == 'chat':
|
||||
async for msg in self._chat_messages(query):
|
||||
yield msg
|
||||
elif self.pipeline_config['ai']['dify-service-api']['app-type'] == 'agent':
|
||||
async for msg in self._agent_chat_messages(query):
|
||||
yield msg
|
||||
elif self.pipeline_config['ai']['dify-service-api']['app-type'] == 'workflow':
|
||||
async for msg in self._workflow_messages(query):
|
||||
yield msg
|
||||
if await query.adapter.is_stream_output_supported():
|
||||
msg_idx = 0
|
||||
if self.pipeline_config['ai']['dify-service-api']['app-type'] == 'chat':
|
||||
async for msg in self._chat_messages_chunk(query):
|
||||
msg_idx += 1
|
||||
msg.msg_sequence = msg_idx
|
||||
yield msg
|
||||
elif self.pipeline_config['ai']['dify-service-api']['app-type'] == 'agent':
|
||||
async for msg in self._agent_chat_messages_chunk(query):
|
||||
msg_idx += 1
|
||||
msg.msg_sequence = msg_idx
|
||||
yield msg
|
||||
elif self.pipeline_config['ai']['dify-service-api']['app-type'] == 'workflow':
|
||||
async for msg in self._workflow_messages_chunk(query):
|
||||
msg_idx += 1
|
||||
msg.msg_sequence = msg_idx
|
||||
yield msg
|
||||
else:
|
||||
raise errors.DifyAPIError(
|
||||
f'不支持的 Dify 应用类型: {self.pipeline_config["ai"]["dify-service-api"]["app-type"]}'
|
||||
)
|
||||
else:
|
||||
raise errors.DifyAPIError(
|
||||
f'不支持的 Dify 应用类型: {self.pipeline_config["ai"]["dify-service-api"]["app-type"]}'
|
||||
)
|
||||
if self.pipeline_config['ai']['dify-service-api']['app-type'] == 'chat':
|
||||
async for msg in self._chat_messages(query):
|
||||
yield msg
|
||||
elif self.pipeline_config['ai']['dify-service-api']['app-type'] == 'agent':
|
||||
async for msg in self._agent_chat_messages(query):
|
||||
yield msg
|
||||
elif self.pipeline_config['ai']['dify-service-api']['app-type'] == 'workflow':
|
||||
async for msg in self._workflow_messages(query):
|
||||
yield msg
|
||||
else:
|
||||
raise errors.DifyAPIError(
|
||||
f'不支持的 Dify 应用类型: {self.pipeline_config["ai"]["dify-service-api"]["app-type"]}'
|
||||
)
|
||||
|
||||
@@ -1,39 +1,179 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import copy
|
||||
import typing
|
||||
|
||||
from .. import runner
|
||||
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
|
||||
import langbot_plugin.api.entities.builtin.provider.message as provider_message
|
||||
|
||||
|
||||
rag_combined_prompt_template = """
|
||||
The following are relevant context entries retrieved from the knowledge base.
|
||||
Please use them to answer the user's message.
|
||||
Respond in the same language as the user's input.
|
||||
|
||||
<context>
|
||||
{rag_context}
|
||||
</context>
|
||||
|
||||
<user_message>
|
||||
{user_message}
|
||||
</user_message>
|
||||
"""
|
||||
|
||||
|
||||
@runner.runner_class('local-agent')
|
||||
class LocalAgentRunner(runner.RequestRunner):
|
||||
"""本地Agent请求运行器"""
|
||||
|
||||
async def run(self, query: pipeline_query.Query) -> typing.AsyncGenerator[provider_message.Message, None]:
|
||||
class ToolCallTracker:
|
||||
"""工具调用追踪器"""
|
||||
|
||||
def __init__(self):
|
||||
self.active_calls: dict[str, dict] = {}
|
||||
self.completed_calls: list[provider_message.ToolCall] = []
|
||||
|
||||
async def run(
|
||||
self, query: pipeline_query.Query
|
||||
) -> typing.AsyncGenerator[provider_message.Message | provider_message.MessageChunk, None]:
|
||||
"""运行请求"""
|
||||
pending_tool_calls = []
|
||||
|
||||
req_messages = query.prompt.messages.copy() + query.messages.copy() + [query.user_message]
|
||||
kb_uuid = query.pipeline_config['ai']['local-agent']['knowledge-base']
|
||||
|
||||
use_llm_model = await self.ap.model_mgr.get_model_by_uuid(query.use_llm_model_uuid)
|
||||
if kb_uuid == '__none__':
|
||||
kb_uuid = None
|
||||
|
||||
# 首次请求
|
||||
msg = await use_llm_model.requester.invoke_llm(
|
||||
query,
|
||||
use_llm_model,
|
||||
req_messages,
|
||||
query.use_funcs,
|
||||
extra_args=use_llm_model.model_entity.extra_args,
|
||||
)
|
||||
user_message = copy.deepcopy(query.user_message)
|
||||
|
||||
yield msg
|
||||
user_message_text = ''
|
||||
|
||||
pending_tool_calls = msg.tool_calls
|
||||
if isinstance(user_message.content, str):
|
||||
user_message_text = user_message.content
|
||||
elif isinstance(user_message.content, list):
|
||||
for ce in user_message.content:
|
||||
if ce.type == 'text':
|
||||
user_message_text += ce.text
|
||||
break
|
||||
|
||||
req_messages.append(msg)
|
||||
if kb_uuid and user_message_text:
|
||||
# only support text for now
|
||||
kb = await self.ap.rag_mgr.get_knowledge_base_by_uuid(kb_uuid)
|
||||
|
||||
if not kb:
|
||||
self.ap.logger.warning(f'Knowledge base {kb_uuid} not found')
|
||||
raise ValueError(f'Knowledge base {kb_uuid} not found')
|
||||
|
||||
result = await kb.retrieve(user_message_text, kb.knowledge_base_entity.top_k)
|
||||
|
||||
final_user_message_text = ''
|
||||
|
||||
if result:
|
||||
rag_context = '\n\n'.join(
|
||||
f'[{i + 1}] {entry.metadata.get("text", "")}' for i, entry in enumerate(result)
|
||||
)
|
||||
final_user_message_text = rag_combined_prompt_template.format(
|
||||
rag_context=rag_context, user_message=user_message_text
|
||||
)
|
||||
|
||||
else:
|
||||
final_user_message_text = user_message_text
|
||||
|
||||
self.ap.logger.debug(f'Final user message text: {final_user_message_text}')
|
||||
|
||||
for ce in user_message.content:
|
||||
if ce.type == 'text':
|
||||
ce.text = final_user_message_text
|
||||
break
|
||||
|
||||
req_messages = query.prompt.messages.copy() + query.messages.copy() + [user_message]
|
||||
|
||||
try:
|
||||
is_stream = await query.adapter.is_stream_output_supported()
|
||||
except AttributeError:
|
||||
is_stream = False
|
||||
|
||||
remove_think = self.pipeline_config['output'].get('misc', '').get('remove-think')
|
||||
|
||||
if not is_stream:
|
||||
# 非流式输出，直接请求
|
||||
|
||||
msg = await query.use_llm_model.requester.invoke_llm(
|
||||
query,
|
||||
query.use_llm_model,
|
||||
req_messages,
|
||||
query.use_funcs,
|
||||
extra_args=query.use_llm_model.model_entity.extra_args,
|
||||
remove_think=remove_think,
|
||||
)
|
||||
yield msg
|
||||
final_msg = msg
|
||||
else:
|
||||
# 流式输出，需要处理工具调用
|
||||
tool_calls_map: dict[str, provider_message.ToolCall] = {}
|
||||
msg_idx = 0
|
||||
accumulated_content = '' # 从开始累积的所有内容
|
||||
last_role = 'assistant'
|
||||
msg_sequence = 1
|
||||
async for msg in query.use_llm_model.requester.invoke_llm_stream(
|
||||
query,
|
||||
query.use_llm_model,
|
||||
req_messages,
|
||||
query.use_funcs,
|
||||
extra_args=query.use_llm_model.model_entity.extra_args,
|
||||
remove_think=remove_think,
|
||||
):
|
||||
msg_idx = msg_idx + 1
|
||||
|
||||
# 记录角色
|
||||
if msg.role:
|
||||
last_role = msg.role
|
||||
|
||||
# 累积内容
|
||||
if msg.content:
|
||||
accumulated_content += msg.content
|
||||
|
||||
# 处理工具调用
|
||||
if msg.tool_calls:
|
||||
for tool_call in msg.tool_calls:
|
||||
if tool_call.id not in tool_calls_map:
|
||||
tool_calls_map[tool_call.id] = provider_message.ToolCall(
|
||||
id=tool_call.id,
|
||||
type=tool_call.type,
|
||||
function=provider_message.FunctionCall(
|
||||
name=tool_call.function.name if tool_call.function else '', arguments=''
|
||||
),
|
||||
)
|
||||
if tool_call.function and tool_call.function.arguments:
|
||||
# 流式处理中，工具调用参数可能分多个chunk返回，需要追加而不是覆盖
|
||||
tool_calls_map[tool_call.id].function.arguments += tool_call.function.arguments
|
||||
# continue
|
||||
# 每8个chunk或最后一个chunk时，输出所有累积的内容
|
||||
if msg_idx % 8 == 0 or msg.is_final:
|
||||
msg_sequence += 1
|
||||
yield provider_message.MessageChunk(
|
||||
role=last_role,
|
||||
content=accumulated_content, # 输出所有累积内容
|
||||
tool_calls=list(tool_calls_map.values()) if (tool_calls_map and msg.is_final) else None,
|
||||
is_final=msg.is_final,
|
||||
msg_sequence=msg_sequence,
|
||||
)
|
||||
|
||||
# 创建最终消息用于后续处理
|
||||
final_msg = provider_message.MessageChunk(
|
||||
role=last_role,
|
||||
content=accumulated_content,
|
||||
tool_calls=list(tool_calls_map.values()) if tool_calls_map else None,
|
||||
msg_sequence=msg_sequence,
|
||||
)
|
||||
|
||||
pending_tool_calls = final_msg.tool_calls
|
||||
first_content = final_msg.content
|
||||
if isinstance(final_msg, provider_message.MessageChunk):
|
||||
first_end_sequence = final_msg.msg_sequence
|
||||
|
||||
req_messages.append(final_msg)
|
||||
|
||||
# 持续请求，只要还有待处理的工具调用就继续处理调用
|
||||
while pending_tool_calls:
|
||||
@@ -43,13 +183,19 @@ class LocalAgentRunner(runner.RequestRunner):
|
||||
|
||||
parameters = json.loads(func.arguments)
|
||||
|
||||
func_ret = await self.ap.tool_mgr.execute_func_call(func.name, parameters)
|
||||
|
||||
msg = provider_message.Message(
|
||||
role='tool',
|
||||
content=json.dumps(func_ret, ensure_ascii=False),
|
||||
tool_call_id=tool_call.id,
|
||||
)
|
||||
func_ret = await self.ap.tool_mgr.execute_func_call(query, func.name, parameters)
|
||||
if is_stream:
|
||||
msg = provider_message.MessageChunk(
|
||||
role='tool',
|
||||
content=json.dumps(func_ret, ensure_ascii=False),
|
||||
tool_call_id=tool_call.id,
|
||||
)
|
||||
else:
|
||||
msg = provider_message.Message(
|
||||
role='tool',
|
||||
content=json.dumps(func_ret, ensure_ascii=False),
|
||||
tool_call_id=tool_call.id,
|
||||
)
|
||||
|
||||
yield msg
|
||||
|
||||
@@ -62,17 +208,81 @@ class LocalAgentRunner(runner.RequestRunner):
|
||||
|
||||
req_messages.append(err_msg)
|
||||
|
||||
# 处理完所有调用，再次请求
|
||||
msg = await use_llm_model.requester.invoke_llm(
|
||||
query,
|
||||
use_llm_model,
|
||||
req_messages,
|
||||
query.use_funcs,
|
||||
extra_args=use_llm_model.model_entity.extra_args,
|
||||
)
|
||||
if is_stream:
|
||||
tool_calls_map = {}
|
||||
msg_idx = 0
|
||||
accumulated_content = '' # 从开始累积的所有内容
|
||||
last_role = 'assistant'
|
||||
msg_sequence = first_end_sequence
|
||||
|
||||
yield msg
|
||||
async for msg in query.use_llm_model.requester.invoke_llm_stream(
|
||||
query,
|
||||
query.use_llm_model,
|
||||
req_messages,
|
||||
query.use_funcs,
|
||||
extra_args=query.use_llm_model.model_entity.extra_args,
|
||||
remove_think=remove_think,
|
||||
):
|
||||
msg_idx += 1
|
||||
|
||||
pending_tool_calls = msg.tool_calls
|
||||
# 记录角色
|
||||
if msg.role:
|
||||
last_role = msg.role
|
||||
|
||||
req_messages.append(msg)
|
||||
# 第一次请求工具调用时的内容
|
||||
if msg_idx == 1:
|
||||
accumulated_content = first_content if first_content is not None else accumulated_content
|
||||
|
||||
# 累积内容
|
||||
if msg.content:
|
||||
accumulated_content += msg.content
|
||||
|
||||
# 处理工具调用
|
||||
if msg.tool_calls:
|
||||
for tool_call in msg.tool_calls:
|
||||
if tool_call.id not in tool_calls_map:
|
||||
tool_calls_map[tool_call.id] = provider_message.ToolCall(
|
||||
id=tool_call.id,
|
||||
type=tool_call.type,
|
||||
function=provider_message.FunctionCall(
|
||||
name=tool_call.function.name if tool_call.function else '', arguments=''
|
||||
),
|
||||
)
|
||||
if tool_call.function and tool_call.function.arguments:
|
||||
# 流式处理中，工具调用参数可能分多个chunk返回，需要追加而不是覆盖
|
||||
tool_calls_map[tool_call.id].function.arguments += tool_call.function.arguments
|
||||
|
||||
# 每8个chunk或最后一个chunk时，输出所有累积的内容
|
||||
if msg_idx % 8 == 0 or msg.is_final:
|
||||
msg_sequence += 1
|
||||
yield provider_message.MessageChunk(
|
||||
role=last_role,
|
||||
content=accumulated_content, # 输出所有累积内容
|
||||
tool_calls=list(tool_calls_map.values()) if (tool_calls_map and msg.is_final) else None,
|
||||
is_final=msg.is_final,
|
||||
msg_sequence=msg_sequence,
|
||||
)
|
||||
|
||||
final_msg = provider_message.MessageChunk(
|
||||
role=last_role,
|
||||
content=accumulated_content,
|
||||
tool_calls=list(tool_calls_map.values()) if tool_calls_map else None,
|
||||
msg_sequence=msg_sequence,
|
||||
)
|
||||
else:
|
||||
# 处理完所有调用，再次请求
|
||||
msg = await query.use_llm_model.requester.invoke_llm(
|
||||
query,
|
||||
query.use_llm_model,
|
||||
req_messages,
|
||||
query.use_funcs,
|
||||
extra_args=query.use_llm_model.model_entity.extra_args,
|
||||
remove_think=remove_think,
|
||||
)
|
||||
|
||||
yield msg
|
||||
final_msg = msg
|
||||
|
||||
pending_tool_calls = final_msg.tool_calls
|
||||
|
||||
req_messages.append(final_msg)
|
||||
|
||||
Reference in New Issue
Block a user