Feat: Support tool calling in Generate component (#7572)

### What problem does this PR solve?

Hello, our use case requires LLM agent to invoke some tools, so I made a
simple implementation here.

This PR does two things:

1. A simple plugin mechanism based on `pluginlib`:

This mechanism lives in the `plugin` directory. It will only load
plugins from `plugin/embedded_plugins` for now.

A sample plugin `bad_calculator.py` is placed in
`plugin/embedded_plugins/llm_tools`, it accepts two numbers `a` and `b`,
then give a wrong result `a + b + 100`.

In the future, it can load plugins from external location with little
code change.

Plugins are divided into different types. The only plugin type supported
in this PR is `llm_tools`, which must implement the `LLMToolPlugin`
class in the `plugin/llm_tool_plugin.py`.
More plugin types can be added in the future.

2. A tool selector in the `Generate` component:

Added a tool selector to select one or more tools for LLM:


![image](https://github.com/user-attachments/assets/74a21fdf-9333-4175-991b-43df6524c5dc)

And with the `bad_calculator` tool, it results this with the `qwen-max`
model:


![image](https://github.com/user-attachments/assets/93aff9c4-8550-414a-90a2-1a15a5249d94)


### Type of change

- [ ] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):

Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>

agent/component/generate.py

@@ -16,15 +16,29 @@
 import json
 import re
 from functools import partial
+from typing import Any
 import pandas as pd
 from api.db import LLMType
 from api.db.services.conversation_service import structure_answer
 from api.db.services.llm_service import LLMBundle
 from api import settings
 from agent.component.base import ComponentBase, ComponentParamBase
+from plugin import GlobalPluginManager
+from plugin.llm_tool_plugin import llm_tool_metadata_to_openai_tool
+from rag.llm.chat_model import ToolCallSession
 from rag.prompts import message_fit_in
 
 
+class LLMToolPluginCallSession(ToolCallSession):
+    def tool_call(self, name: str, arguments: dict[str, Any]) -> str:
+        tool = GlobalPluginManager.get_llm_tool_by_name(name)
+
+        if tool is None:
+            raise ValueError(f"LLM tool {name} does not exist")
+
+        return tool().invoke(**arguments)
+
+
 class GenerateParam(ComponentParamBase):
     """
     Define the Generate component parameters.
@@ -41,6 +55,7 @@ class GenerateParam(ComponentParamBase):
         self.frequency_penalty = 0
         self.cite = True
         self.parameters = []
+        self.llm_enabled_tools = []
 
     def check(self):
         self.check_decimal_float(self.temperature, "[Generate] Temperature")
@@ -133,6 +148,15 @@ class Generate(ComponentBase):
 
     def _run(self, history, **kwargs):
         chat_mdl = LLMBundle(self._canvas.get_tenant_id(), LLMType.CHAT, self._param.llm_id)
+
+        if len(self._param.llm_enabled_tools) > 0:
+            tools = GlobalPluginManager.get_llm_tools_by_names(self._param.llm_enabled_tools)
+
+            chat_mdl.bind_tools(
+                LLMToolPluginCallSession(),
+                [llm_tool_metadata_to_openai_tool(t.get_metadata()) for t in tools]
+            )
+
         prompt = self._param.prompt
 
         retrieval_res = []