update0720

app.py

@@ -3,30 +3,30 @@ import nltk
 import openai
 import time
 import gradio as gr
-from threading import Thread
+from threading import Thread #线程  用于定时器
 
-from assets.char_poses_base64 import (
+from assets.char_poses_base64 import ( #角色动作
     CHAR_IDLE_HTML, CHAR_THINKING_HTML, CHAR_TALKING_HTML)
 
 from app_utils import (
     get_chat_history, initialize_knowledge_base, 
     text_to_speech_gen, logging, buzz_user)
 
-global FUNC_CALL
+global FUNC_CALL #全局变量 用于判断角色动作
 FUNC_CALL = 0
 
-global BUZZ_TIMEOUT
+global BUZZ_TIMEOUT #全局变量 用于定时器
 BUZZ_TIMEOUT = 60
 
 GENERAL_RSPONSE_TRIGGERS = ["I don't understand the question.", "I don't know", "Hello, my name is", "mentioned in the context provided"]
-MESSAGES = [{"role": "system", "content": "You are a helpful assistant.."}]
+MESSAGES = [{"role": "system", "content": "You are a helpful assistant.You accompany me to practice English and engage in scene dialogue. As a hotel attendant, I am checking in. You introduce the hotel to me and recommend hotel services to me. After receiving my needs, arrange for the service personnel to work. Please remember, my English is not very good. Please have a conversation with me in simple English. After you ask questions in English, please give me some English prompts so that I know how to answer you. Let's start the conversation. You first say hello to me."}]
 
-LOGGER = logging.getLogger('voice_agent')
+LOGGER = logging.getLogger('voice_agent') #日志
 AUDIO_HTML = ''
 
 # Uncomment If this is your first Run: 
-nltk.download('averaged_perceptron_tagger')
-conv_model, voice_model = initialize_knowledge_base()
+nltk.download('averaged_perceptron_tagger')  #下载语料库
+conv_model, voice_model = initialize_knowledge_base()  #初始化知识库
 
 
 def idle_timer():

app_utils.py

@@ -1,18 +1,18 @@
 import os
 import whisper
-from io import BytesIO
-import base64
-import boto3
-from pydub import AudioSegment
-from pydub.playback import play
+from io import BytesIO #   BytesIO is a class in the io module that implements an in-memory file-like object.
+import base64 
+import boto3 # AWS Polly
+from pydub import AudioSegment #    AudioSegment is a class in the pydub module that can be used to manipulate audio files.
+from pydub.playback import play  #  play is a function in the pydub.playback module that can be used to play audio files.
 import logging
 
 from langchain import OpenAI
-from langchain.chains import RetrievalQA
-from langchain.vectorstores import Chroma
-from langchain.document_loaders import DirectoryLoader
-from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain.text_splitter import CharacterTextSplitter
+from langchain.chains import RetrievalQA #  RetrievalQA is a class in the langchain.chains module that can be used to build a retrieval-based question answering system.
+from langchain.vectorstores import Chroma # Chroma is a class in the langchain.vectorstores module that can be used to store vectors.
+from langchain.document_loaders import DirectoryLoader #       
+from langchain.embeddings.openai import OpenAIEmbeddings # OpenAIGPTEmbeddings
+from langchain.text_splitter import CharacterTextSplitter #     CharacterTextSplitter is a class in the langchain.text_splitter module that can be used to split text into chunks.
 
 
 OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')
@@ -35,7 +35,7 @@ def buzz_user():
 
 def initialize_knowledge_base():
     
-    loader = DirectoryLoader('profiles', glob='**/*.txt')
+    loader = DirectoryLoader('profiles', glob='**/*.txt') #文件夹加载器 profiles文件夹下的所有txt文件
     docs = loader.load()
 
     char_text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
@@ -56,7 +56,7 @@ def initialize_knowledge_base():
     return conv_model, voice_model
 
 
-def text_to_speech_gen(answer):
+def text_to_speech_gen(answer):  #文字转语音
 
     polly = boto3.client('polly',
                 aws_access_key_id=AWS_ACCESS_KEY_ID,
@@ -75,7 +75,7 @@ def text_to_speech_gen(answer):
     return audio_html
     
 
-def audio_to_html(audio_bytes):
+def audio_to_html(audio_bytes):       #音频转html
     audio_io = BytesIO(audio_bytes)
     audio_io.seek(0)
     audio_base64 = base64.b64encode(audio_io.read()).decode("utf-8")

profiles/john.txt

@@ -3,7 +3,7 @@ you were born in 12th March 1958
 John is at the shop
 Brian is on holiday
 Sarah is coming home soon
-Sarah is net door and has left
+Sarah is net door and has left 
 You have granddaughters, jennny and michelle, they are 7 and 10
 Your cousin Arthur is in Australia, he’s back next July
 Your neighbuor Steven passed away a few days ago