mirror of
https://github.com/zhenxun-org/zhenxun_bot.git
synced 2026-10-11 06:39:59 +08:00
♻️ refactor!: 重构LLM服务架构并统一Pydantic兼容性处理 (#2002)
检查bot是否运行正常 / bot check (push) Waiting to run
Sequential Lint and Type Check / ruff-call (push) Waiting to run
Sequential Lint and Type Check / pyright-call (push) Blocked by required conditions
Release Drafter / Update Release Draft (push) Waiting to run
Force Sync to Aliyun / sync (push) Waiting to run
Update Version / update-version (push) Waiting to run
CodeQL Code Security Analysis / Analyze (${{ matrix.language }}) (none, javascript-typescript) (push) Has been cancelled
CodeQL Code Security Analysis / Analyze (${{ matrix.language }}) (none, python) (push) Has been cancelled
检查bot是否运行正常 / bot check (push) Waiting to run
Sequential Lint and Type Check / ruff-call (push) Waiting to run
Sequential Lint and Type Check / pyright-call (push) Blocked by required conditions
Release Drafter / Update Release Draft (push) Waiting to run
Force Sync to Aliyun / sync (push) Waiting to run
Update Version / update-version (push) Waiting to run
CodeQL Code Security Analysis / Analyze (${{ matrix.language }}) (none, javascript-typescript) (push) Has been cancelled
CodeQL Code Security Analysis / Analyze (${{ matrix.language }}) (none, python) (push) Has been cancelled
* ♻️ refactor(pydantic): 提取 Pydantic 兼容函数到独立模块 * ♻️ refactor!(llm): 重构LLM服务,引入现代化工具和执行器架构 🏗️ **架构变更** - 引入ToolProvider/ToolExecutable协议,取代ToolRegistry - 新增LLMToolExecutor,分离工具调用逻辑 - 新增BaseMemory抽象,解耦会话状态管理 🔄 **API重构** - 移除:analyze, analyze_multimodal, pipeline_chat - 新增:generate_structured, run_with_tools - 重构:chat, search, code变为无状态调用 🛠️ **工具系统** - 新增@function_tool装饰器 - 统一工具定义到ToolExecutable协议 - 移除MCP工具系统和mcp_tools.json --------- Co-authored-by: webjoin111 <455457521@qq.com>
This commit is contained in:
@@ -27,23 +27,19 @@ from .llm import (
|
||||
LLMException,
|
||||
LLMGenerationConfig,
|
||||
LLMMessage,
|
||||
analyze,
|
||||
analyze_multimodal,
|
||||
chat,
|
||||
clear_model_cache,
|
||||
code,
|
||||
create_multimodal_message,
|
||||
embed,
|
||||
generate,
|
||||
generate_structured,
|
||||
get_cache_stats,
|
||||
get_model_instance,
|
||||
list_available_models,
|
||||
list_embedding_models,
|
||||
pipeline_chat,
|
||||
search,
|
||||
search_multimodal,
|
||||
set_global_default_model_name,
|
||||
tool_registry,
|
||||
)
|
||||
from .log import logger
|
||||
from .plugin_init import PluginInit, PluginInitManager
|
||||
@@ -60,8 +56,6 @@ __all__ = [
|
||||
"Model",
|
||||
"PluginInit",
|
||||
"PluginInitManager",
|
||||
"analyze",
|
||||
"analyze_multimodal",
|
||||
"chat",
|
||||
"clear_model_cache",
|
||||
"code",
|
||||
@@ -69,16 +63,14 @@ __all__ = [
|
||||
"disconnect",
|
||||
"embed",
|
||||
"generate",
|
||||
"generate_structured",
|
||||
"get_cache_stats",
|
||||
"get_model_instance",
|
||||
"list_available_models",
|
||||
"list_embedding_models",
|
||||
"logger",
|
||||
"pipeline_chat",
|
||||
"scheduler_manager",
|
||||
"search",
|
||||
"search_multimodal",
|
||||
"set_global_default_model_name",
|
||||
"tool_registry",
|
||||
"with_db_timeout",
|
||||
]
|
||||
|
||||
Reference in New Issue
Block a user