自訂 Tool 教學

Kuwa 設計上支援串接各種非 LLM 的 Tool，最簡單的 Tool 可以參考 src/executor/debug.py，
以下是內容說明。

import os
import sys
import asyncio
import logging
import json
sys.path.append(os.path.dirname(os.path.abspath(__file__)))

from kuwa.executor import LLMExecutor, Modelfile

logger = logging.getLogger(__name__)

class DebugExecutor(LLMExecutor):
    def __init__(self):
        super().__init__()

    def extend_arguments(self, parser):
        """
        Override this method to add custom command-line arguments.
        """
        parser.add_argument('--delay', type=float, default=0.02, help='Inter-token delay')

    def setup(self):
        self.stop = False

    async def llm_compute(self, history: list[dict], modelfile:Modelfile):
        """
        Responsible for handling the requests, the input is chat history (in
        OpenAI format) and parsed Modelfile (you can refer to
        `genai-os/src/executor/src/kuwa/executor/modelfile.py`), it will return an
        Asynchronous Generators to represent the output stream.
        """
        try:
            self.stop = False
            for i in "".join([i['content'] for i in history]).strip():
                yield i
                if self.stop:
                    self.stop = False
                    break
                await asyncio.sleep(modelfile.parameters.get("llm_delay", self.args.delay))
        except Exception as e:
            logger.exception("Error occurs during generation.")
            yield str(e)
        finally:
            logger.debug("finished")

    async def abort(self):
        """
        This method is invoked when the user presses the interrupt generation button.
        """
        self.stop = True
        logger.debug("aborted")
        return "Aborted"

if __name__ == "__main__":
    executor = DebugExecutor()
    executor.run()