mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-07-21 03:46:11 +00:00
chore: Add PyPI package support for uvx/pip installation (#1764)
* Initial plan * Add package structure and resource path utilities - Created langbot/ package with __init__.py and __main__.py entry point - Added paths utility to find frontend and resource files from package installation - Updated config loading to use resource paths - Updated frontend serving to use resource paths - Added MANIFEST.in for package data inclusion - Updated pyproject.toml with build system and entry points Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com> * Add PyPI publishing workflow and update license - Created GitHub Actions workflow to build frontend and publish to PyPI - Added license field to pyproject.toml to fix deprecation warning - Updated .gitignore to exclude build artifacts - Tested package building successfully Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com> * Add PyPI installation documentation - Created PYPI_INSTALLATION.md with detailed installation and usage instructions - Updated README.md to feature uvx/pip installation as recommended method - Updated README_EN.md with same changes for English documentation Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com> * Address code review feedback - Made package-data configuration more specific to langbot package only - Improved path detection with caching to avoid repeated file I/O - Removed sys.path searching which was incorrect for package data - Removed interactive input() call for non-interactive environment compatibility - Simplified error messages for version check Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com> * Fix code review issues - Use specific exception types instead of bare except - Fix misleading comments about directory levels - Remove redundant existence check before makedirs with exist_ok=True - Use context manager for file opening to ensure proper cleanup Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com> * Simplify package configuration and document behavioral differences - Removed redundant package-data configuration, relying on MANIFEST.in - Added documentation about behavioral differences between package and source installation - Clarified that include-package-data=true uses MANIFEST.in for data files Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com> * chore: update pyproject.toml * chore: try pack templates in langbot/ * chore: update * chore: update * chore: update * chore: update * chore: update * chore: adjust dir structure * chore: fix imports * fix: read default-pipeline-config.json * fix: read default-pipeline-config.json * fix: tests * ci: publish pypi * chore: bump version 4.6.0-beta.1 for testing * chore: add templates/** * fix: send adapters and requesters icons * chore: bump version 4.6.0b2 for testing * chore: add platform field for docker-compose.yaml --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com> Co-authored-by: Junyan Qin <rockchinq@gmail.com>
This commit is contained in:
Copilot
@@ -0,0 +1,242 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import typing
|
||||
import dashscope
|
||||
import openai
|
||||
|
||||
from . import modelscopechatcmpl
|
||||
from .. import requester
|
||||
import langbot_plugin.api.entities.builtin.resource.tool as resource_tool
|
||||
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
|
||||
import langbot_plugin.api.entities.builtin.provider.message as provider_message
|
||||
|
||||
|
||||
class BailianChatCompletions(modelscopechatcmpl.ModelScopeChatCompletions):
|
||||
"""阿里云百炼大模型平台 ChatCompletion API 请求器"""
|
||||
|
||||
client: openai.AsyncClient
|
||||
|
||||
default_config: dict[str, typing.Any] = {
|
||||
'base_url': 'https://dashscope.aliyuncs.com/compatible-mode/v1',
|
||||
'timeout': 120,
|
||||
}
|
||||
|
||||
async def _closure_stream(
|
||||
self,
|
||||
query: pipeline_query.Query,
|
||||
req_messages: list[dict],
|
||||
use_model: requester.RuntimeLLMModel,
|
||||
use_funcs: list[resource_tool.LLMTool] = None,
|
||||
extra_args: dict[str, typing.Any] = {},
|
||||
remove_think: bool = False,
|
||||
) -> provider_message.Message | typing.AsyncGenerator[provider_message.MessageChunk, None]:
|
||||
self.client.api_key = use_model.token_mgr.get_token()
|
||||
|
||||
args = {}
|
||||
args['model'] = use_model.model_entity.name
|
||||
|
||||
if use_funcs:
|
||||
tools = await self.ap.tool_mgr.generate_tools_for_openai(use_funcs)
|
||||
|
||||
if tools:
|
||||
args['tools'] = tools
|
||||
|
||||
# 设置此次请求中的messages
|
||||
messages = req_messages.copy()
|
||||
|
||||
is_use_dashscope_call = False # 是否使用阿里原生库调用
|
||||
is_enable_multi_model = True # 是否支持多轮对话
|
||||
use_time_num = 0 # 模型已调用次数，防止存在多文件时重复调用
|
||||
use_time_ids = [] # 已调用的ID列表
|
||||
message_id = 0 # 记录消息序号
|
||||
|
||||
for msg in messages:
|
||||
# print(msg)
|
||||
if 'content' in msg and isinstance(msg['content'], list):
|
||||
for me in msg['content']:
|
||||
if me['type'] == 'image_base64':
|
||||
me['image_url'] = {'url': me['image_base64']}
|
||||
me['type'] = 'image_url'
|
||||
del me['image_base64']
|
||||
elif me['type'] == 'file_url' and '.' in me.get('file_name', ''):
|
||||
# 1. 视频文件推理
|
||||
# https://bailian.console.aliyun.com/?tab=doc#/doc/?type=model&url=2845871
|
||||
file_type = me.get('file_name').lower().split('.')[-1]
|
||||
if file_type in ['mp4', 'avi', 'mkv', 'mov', 'flv', 'wmv']:
|
||||
me['type'] = 'video_url'
|
||||
me['video_url'] = {'url': me['file_url']}
|
||||
del me['file_url']
|
||||
del me['file_name']
|
||||
use_time_num += 1
|
||||
use_time_ids.append(message_id)
|
||||
is_enable_multi_model = False
|
||||
# 2. 语音文件识别, 无法通过openai的audio字段传递，暂时不支持
|
||||
# https://bailian.console.aliyun.com/?tab=doc#/doc/?type=model&url=2979031
|
||||
elif file_type in [
|
||||
'aac',
|
||||
'amr',
|
||||
'aiff',
|
||||
'flac',
|
||||
'm4a',
|
||||
'mp3',
|
||||
'mpeg',
|
||||
'ogg',
|
||||
'opus',
|
||||
'wav',
|
||||
'webm',
|
||||
'wma',
|
||||
]:
|
||||
me['audio'] = me['file_url']
|
||||
me['type'] = 'audio'
|
||||
del me['file_url']
|
||||
del me['type']
|
||||
del me['file_name']
|
||||
is_use_dashscope_call = True
|
||||
use_time_num += 1
|
||||
use_time_ids.append(message_id)
|
||||
is_enable_multi_model = False
|
||||
message_id += 1
|
||||
|
||||
# 使用列表推导式，保留不在 use_time_ids[:-1] 中的元素，仅保留最后一个多媒体消息
|
||||
if not is_enable_multi_model and use_time_num > 1:
|
||||
messages = [msg for idx, msg in enumerate(messages) if idx not in use_time_ids[:-1]]
|
||||
|
||||
if not is_enable_multi_model:
|
||||
messages = [msg for msg in messages if 'resp_message_id' not in msg]
|
||||
|
||||
args['messages'] = messages
|
||||
args['stream'] = True
|
||||
|
||||
# 流式处理状态
|
||||
# tool_calls_map: dict[str, provider_message.ToolCall] = {}
|
||||
chunk_idx = 0
|
||||
thinking_started = False
|
||||
thinking_ended = False
|
||||
role = 'assistant' # 默认角色
|
||||
|
||||
if is_use_dashscope_call:
|
||||
response = dashscope.MultiModalConversation.call(
|
||||
# 若没有配置环境变量，请用百炼API Key将下行替换为：api_key = "sk-xxx"
|
||||
api_key=use_model.token_mgr.get_token(),
|
||||
model=use_model.model_entity.name,
|
||||
messages=messages,
|
||||
result_format='message',
|
||||
asr_options={
|
||||
# "language": "zh", # 可选，若已知音频的语种，可通过该参数指定待识别语种，以提升识别准确率
|
||||
'enable_lid': True,
|
||||
'enable_itn': False,
|
||||
},
|
||||
stream=True,
|
||||
)
|
||||
content_length_list = []
|
||||
previous_length = 0 # 记录上一次的内容长度
|
||||
for res in response:
|
||||
chunk = res['output']
|
||||
# 解析 chunk 数据
|
||||
if hasattr(chunk, 'choices') and chunk.choices:
|
||||
choice = chunk.choices[0]
|
||||
delta_content = choice['message'].content[0]['text']
|
||||
finish_reason = choice['finish_reason']
|
||||
content_length_list.append(len(delta_content))
|
||||
else:
|
||||
delta_content = ''
|
||||
finish_reason = None
|
||||
|
||||
# 跳过空的第一个 chunk（只有 role 没有内容）
|
||||
if chunk_idx == 0 and not delta_content:
|
||||
chunk_idx += 1
|
||||
continue
|
||||
|
||||
# 检查 content_length_list 是否有足够的数据
|
||||
if len(content_length_list) >= 2:
|
||||
now_content = delta_content[previous_length : content_length_list[-1]]
|
||||
previous_length = content_length_list[-1] # 更新上一次的长度
|
||||
else:
|
||||
now_content = delta_content # 第一次循环时直接使用 delta_content
|
||||
previous_length = len(delta_content) # 更新上一次的长度
|
||||
|
||||
# 构建 MessageChunk - 只包含增量内容
|
||||
chunk_data = {
|
||||
'role': role,
|
||||
'content': now_content if now_content else None,
|
||||
'is_final': bool(finish_reason) and finish_reason != 'null',
|
||||
}
|
||||
|
||||
# 移除 None 值
|
||||
chunk_data = {k: v for k, v in chunk_data.items() if v is not None}
|
||||
yield provider_message.MessageChunk(**chunk_data)
|
||||
chunk_idx += 1
|
||||
else:
|
||||
async for chunk in self._req_stream(args, extra_body=extra_args):
|
||||
# 解析 chunk 数据
|
||||
if hasattr(chunk, 'choices') and chunk.choices:
|
||||
choice = chunk.choices[0]
|
||||
delta = choice.delta.model_dump() if hasattr(choice, 'delta') else {}
|
||||
finish_reason = getattr(choice, 'finish_reason', None)
|
||||
else:
|
||||
delta = {}
|
||||
finish_reason = None
|
||||
|
||||
# 从第一个 chunk 获取 role，后续使用这个 role
|
||||
if 'role' in delta and delta['role']:
|
||||
role = delta['role']
|
||||
|
||||
# 获取增量内容
|
||||
delta_content = delta.get('content', '')
|
||||
reasoning_content = delta.get('reasoning_content', '')
|
||||
|
||||
# 处理 reasoning_content
|
||||
if reasoning_content:
|
||||
# accumulated_reasoning += reasoning_content
|
||||
# 如果设置了 remove_think，跳过 reasoning_content
|
||||
if remove_think:
|
||||
chunk_idx += 1
|
||||
continue
|
||||
|
||||
# 第一次出现 reasoning_content，添加 <think> 开始标签
|
||||
if not thinking_started:
|
||||
thinking_started = True
|
||||
delta_content = '<think>\n' + reasoning_content
|
||||
else:
|
||||
# 继续输出 reasoning_content
|
||||
delta_content = reasoning_content
|
||||
elif thinking_started and not thinking_ended and delta_content:
|
||||
# reasoning_content 结束，normal content 开始，添加 </think> 结束标签
|
||||
thinking_ended = True
|
||||
delta_content = '\n</think>\n' + delta_content
|
||||
|
||||
# 处理工具调用增量
|
||||
if delta.get('tool_calls'):
|
||||
for tool_call in delta['tool_calls']:
|
||||
if tool_call['id'] != '':
|
||||
tool_id = tool_call['id']
|
||||
if tool_call['function']['name'] is not None:
|
||||
tool_name = tool_call['function']['name']
|
||||
|
||||
if tool_call['type'] is None:
|
||||
tool_call['type'] = 'function'
|
||||
tool_call['id'] = tool_id
|
||||
tool_call['function']['name'] = tool_name
|
||||
tool_call['function']['arguments'] = (
|
||||
'' if tool_call['function']['arguments'] is None else tool_call['function']['arguments']
|
||||
)
|
||||
|
||||
# 跳过空的第一个 chunk（只有 role 没有内容）
|
||||
if chunk_idx == 0 and not delta_content and not reasoning_content and not delta.get('tool_calls'):
|
||||
chunk_idx += 1
|
||||
continue
|
||||
|
||||
# 构建 MessageChunk - 只包含增量内容
|
||||
chunk_data = {
|
||||
'role': role,
|
||||
'content': delta_content if delta_content else None,
|
||||
'tool_calls': delta.get('tool_calls'),
|
||||
'is_final': bool(finish_reason),
|
||||
}
|
||||
|
||||
# 移除 None 值
|
||||
chunk_data = {k: v for k, v in chunk_data.items() if v is not None}
|
||||
|
||||
yield provider_message.MessageChunk(**chunk_data)
|
||||
chunk_idx += 1
|
||||
# return
|
||||
Reference in New Issue
Block a user