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

@@ -14,6 +14,7 @@ from pydantic import BaseModel, Field
 from metagpt.actions.action_node import ActionNode
 from metagpt.llm import LLM
 from metagpt.provider.base_gpt_api import BaseGPTAPI
+from metagpt.schema import CodingContext, CodeSummarizeContext, TestingContext, RunCodeContext
 
 
 action_subclass_registry = {}
@@ -22,7 +23,7 @@ action_subclass_registry = {}
 class Action(BaseModel):
     name: str = ""
     llm: BaseGPTAPI = Field(default_factory=LLM, exclude=True)
-    context = ""
+    context: dict | CodingContext | CodeSummarizeContext | TestingContext | RunCodeContext | str | None = ""
     prefix = ""  # aask*时会加上prefix，作为system_message
     desc = ""  # for skill manager
     node: ActionNode = Field(default_factory=ActionNode, exclude=True)

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/azure_tts.py

@@ -1,45 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-"""
-@Time    : 2023/6/9 22:22
-@Author  : Leo Xiao
-@File    : azure_tts.py
-"""
-from azure.cognitiveservices.speech import AudioConfig, SpeechConfig, SpeechSynthesizer
-
-from metagpt.actions.action import Action
-from metagpt.config import Config
-
-
-class AzureTTS(Action):
-    def __init__(self, name, context=None, llm=None):
-        super().__init__(name, context, llm)
-        self.config = Config()
-
-    # 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")
-        speech_config = SpeechConfig(subscription=subscription_key, region=region)
-
-        speech_config.speech_synthesis_voice_name = voice
-        audio_config = AudioConfig(filename=output_file)
-        synthesizer = SpeechSynthesizer(speech_config=speech_config, audio_config=audio_config)
-
-        # if voice=="zh-CN-YunxiNeural":
-        ssml_string = f"""
-            <speak version='1.0' xmlns='http://www.w3.org/2001/10/synthesis' xml:lang='{lang}' xmlns:mstts='http://www.w3.org/2001/mstts'>
-                <voice name='{voice}'>
-                    <mstts:express-as style='affectionate' role='{role}'>
-                        {text}
-                    </mstts:express-as>
-                </voice>
-            </speak>
-            """
-
-        synthesizer.speak_ssml_async(ssml_string).get()
-
-
-if __name__ == "__main__":
-    azure_tts = AzureTTS("azure_tts")
-    azure_tts.synthesize_speech("zh-CN", "zh-CN-YunxiNeural", "Boy", "Hello, I am Kaka", "output.wav")

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)