refine code. move azure tts to tool, refactor actions

metagpt/actions/__init__.py

@@ -13,7 +13,6 @@ from metagpt.actions.add_requirement import UserRequirement
 from metagpt.actions.debug_error import DebugError
 from metagpt.actions.design_api import WriteDesign
 from metagpt.actions.design_api_review import DesignReview
-from metagpt.actions.design_filenames import DesignFilenames
 from metagpt.actions.project_management import AssignTasks, WriteTasks
 from metagpt.actions.research import CollectLinks, WebBrowseAndSummarize, ConductResearch
 from metagpt.actions.run_code import RunCode
@@ -33,7 +32,6 @@ class ActionType(Enum):
     WRITE_PRD_REVIEW = WritePRDReview
     WRITE_DESIGN = WriteDesign
     DESIGN_REVIEW = DesignReview
-    DESIGN_FILENAMES = DesignFilenames
     WRTIE_CODE = WriteCode
     WRITE_CODE_REVIEW = WriteCodeReview
     WRITE_TEST = WriteTest

metagpt/actions/action.py

@@ -13,7 +13,7 @@ from typing import Optional
 
 from metagpt.actions.action_node import ActionNode
 from metagpt.llm import LLM
-from metagpt.schema import BaseContext
+from metagpt.schema import CodingContext, CodeSummarizeContext, TestingContext, RunCodeContext
 
 
 class Action(ABC):
@@ -21,7 +21,8 @@ class Action(ABC):
 
     name: str
     llm: LLM
-    context: dict | BaseContext | str | None
+    # FIXME: simplify context
+    context: dict | CodingContext | CodeSummarizeContext | TestingContext | RunCodeContext | str | None
     prefix: str
     desc: str
     node: ActionNode | None

metagpt/actions/analyze_dep_libs.py

@@ -1,37 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-"""
-@Time    : 2023/5/19 12:01
-@Author  : alexanderwu
-@File    : analyze_dep_libs.py
-"""
-
-from metagpt.actions import Action
-
-PROMPT = """You are an AI developer, trying to write a program that generates code for users based on their intentions.
-
-For the user's prompt:
-
----
-The API is: {prompt}
----
-
-We decide the generated files are: {filepaths_string}
-
-Now that we have a file list, we need to understand the shared dependencies they have.
-Please list and briefly describe the shared contents between the files we are generating, including exported variables, 
-data patterns, id names of all DOM elements that javascript functions will use, message names and function names.
-Focus only on the names of shared dependencies, do not add any other explanations.
-"""
-
-
-class AnalyzeDepLibs(Action):
-    def __init__(self, name, context=None, llm=None):
-        super().__init__(name, context, llm)
-        self.desc = "Analyze the runtime dependencies of the program based on the context"
-
-    async def run(self, requirement, filepaths_string):
-        # prompt = f"Below is the product requirement document (PRD):\n\n{prd}\n\n{PROMPT}"
-        prompt = PROMPT.format(prompt=requirement, filepaths_string=filepaths_string)
-        design_filenames = await self._aask(prompt)
-        return design_filenames

metagpt/actions/design_filenames.py

@@ -1,30 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-"""
-@Time    : 2023/5/19 11:50
-@Author  : alexanderwu
-@File    : design_filenames.py
-"""
-from metagpt.actions import Action
-from metagpt.logs import logger
-
-PROMPT = """You are an AI developer, trying to write a program that generates code for users based on their intentions.
-When given their intentions, provide a complete and exhaustive list of file paths needed to write the program for the user.
-Only list the file paths you will write and return them as a Python string list.
-Do not add any other explanations, just return a Python string list."""
-
-
-class DesignFilenames(Action):
-    def __init__(self, name, context=None, llm=None):
-        super().__init__(name, context, llm)
-        self.desc = (
-            "Based on the PRD, consider system design, and carry out the basic design of the corresponding "
-            "APIs, data structures, and database tables. Please give your design, feedback clearly and in detail."
-        )
-
-    async def run(self, prd):
-        prompt = f"The following is the Product Requirement Document (PRD):\n\n{prd}\n\n{PROMPT}"
-        design_filenames = await self._aask(prompt)
-        logger.debug(prompt)
-        logger.debug(design_filenames)
-        return design_filenames

metagpt/actions/generate_questions.py

@@ -3,19 +3,11 @@
 """
 @Time    : 2023/9/12 17:45
 @Author  : fisherdeng
-@File    : detail_mining.py
+@File    : generate_questions.py
 """
 from metagpt.actions import Action
 from metagpt.actions.action_node import ActionNode
 
-CONTEXT_TEMPLATE = """
-## TOPIC
-{topic}
-
-## RECORD
-{record}
-"""
-
 QUESTIONS = ActionNode(
     key="Questions",
     expected_type=list[str],
@@ -25,11 +17,9 @@ QUESTIONS = ActionNode(
 )
 
 
-class DetailMining(Action):
+class GenerateQuestions(Action):
     """This class allows LLM to further mine noteworthy details based on specific "##TOPIC"(discussion topic) and
     "##RECORD" (discussion records), thereby deepening the discussion."""
 
-    async def run(self, topic, record):
-        context = CONTEXT_TEMPLATE.format(topic=topic, record=record)
-        rsp = await QUESTIONS.fill(context=context, llm=self.llm)
-        return rsp
+    async def run(self, context):
+        return await QUESTIONS.fill(context=context, llm=self.llm)

metagpt/schema.py

@@ -18,6 +18,7 @@ import asyncio
 import json
 import os.path
 import uuid
+from abc import ABC
 from asyncio import Queue, QueueEmpty, wait_for
 from json import JSONDecodeError
 from pathlib import Path
@@ -265,7 +266,7 @@ class MessageQueue:
 T = TypeVar("T", bound="BaseModel")
 
 
-class BaseContext(BaseModel):
+class BaseContext(BaseModel, ABC):
     @classmethod
     @handle_exception
     def loads(cls: Type[T], val: str) -> Optional[T]:

metagpt/tools/azure_tts.py

@@ -7,19 +7,16 @@
 """
 from azure.cognitiveservices.speech import AudioConfig, SpeechConfig, SpeechSynthesizer
 
-from metagpt.actions.action import Action
-from metagpt.config import Config
+from metagpt.config import CONFIG
 
 
-class AzureTTS(Action):
-    def __init__(self, name, context=None, llm=None):
-        super().__init__(name, context, llm)
-        self.config = Config()
+class AzureTTS:
+    """https://learn.microsoft.com/zh-cn/azure/cognitive-services/speech-service/language-support?tabs=tts#voice-styles-and-roles"""
 
-    # Parameters reference: https://learn.microsoft.com/zh-cn/azure/cognitive-services/speech-service/language-support?tabs=tts#voice-styles-and-roles
-    def synthesize_speech(self, lang, voice, role, text, output_file):
-        subscription_key = self.config.get("AZURE_TTS_SUBSCRIPTION_KEY")
-        region = self.config.get("AZURE_TTS_REGION")
+    @classmethod
+    def synthesize_speech(cls, lang, voice, role, text, output_file):
+        subscription_key = CONFIG.get("AZURE_TTS_SUBSCRIPTION_KEY")
+        region = CONFIG.get("AZURE_TTS_REGION")
         speech_config = SpeechConfig(subscription=subscription_key, region=region)
 
         speech_config.speech_synthesis_voice_name = voice
@@ -41,5 +38,5 @@ class AzureTTS(Action):
 
 
 if __name__ == "__main__":
-    azure_tts = AzureTTS("azure_tts")
+    azure_tts = AzureTTS()
     azure_tts.synthesize_speech("zh-CN", "zh-CN-YunxiNeural", "Boy", "Hello, I am Kaka", "output.wav")

tests/metagpt/actions/test_azure_tts.py

@@ -5,11 +5,11 @@
 @Author  : alexanderwu
 @File    : test_azure_tts.py
 """
-from metagpt.actions.azure_tts import AzureTTS
+from metagpt.tools.azure_tts import AzureTTS
 
 
 def test_azure_tts():
-    azure_tts = AzureTTS("azure_tts")
+    azure_tts = AzureTTS()
     azure_tts.synthesize_speech("zh-CN", "zh-CN-YunxiNeural", "Boy", "你好，我是卡卡", "output.wav")
 
     # 运行需要先配置 SUBSCRIPTION_KEY

tests/metagpt/actions/test_detail_mining.py

@@ -3,20 +3,26 @@
 """
 @Time    : 2023/9/13 00:26
 @Author  : fisherdeng
-@File    : test_detail_mining.py
+@File    : test_generate_questions.py
 """
 import pytest
 
-from metagpt.actions.detail_mining import DetailMining
+from metagpt.actions.generate_questions import GenerateQuestions
 from metagpt.logs import logger
 
+context = """
+## topic
+如何做一个生日蛋糕
+
+## record
+我认为应该先准备好材料，然后再开始做蛋糕。
+"""
+
 
 @pytest.mark.asyncio
-async def test_detail_mining():
-    topic = "如何做一个生日蛋糕"
-    record = "我认为应该先准备好材料，然后再开始做蛋糕。"
-    detail_mining = DetailMining("detail_mining")
-    rsp = await detail_mining.run(topic=topic, record=record)
+async def test_generate_questions():
+    detail_mining = GenerateQuestions()
+    rsp = await detail_mining.run(context)
     logger.info(f"{rsp.content=}")
 
     assert "Questions" in rsp.content