File size: 3,235 Bytes
e6c45ad
 
ddef685
 
 
 
 
e6c45ad
 
 
ddef685
 
 
 
 
e6c45ad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ddef685
e6c45ad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ddef685
e6c45ad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ddef685
e6c45ad
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
import os
import whisper
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 #  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')
AWS_ACCESS_KEY_ID = os.getenv('AWS_ACCESS_KEY_ID')
AWS_SECRET_ACCESS_KEY = os.getenv('AWS_SECRET_ACCESS_KEY')
AWS_REGION_NAME = 'ap-south-1'


logging.basicConfig(level="INFO",
                    filename='conversations.log',
                    filemode='a',
                    format='%(asctime)s %(message)s',
                    datefmt='%H:%M:%S')


def buzz_user():
    input_prompt = AudioSegment.from_mp3('assets/timeout_audio.mp3')
    play(input_prompt)
    

def initialize_knowledge_base():
    
    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)
    doc_texts = char_text_splitter.split_documents(docs)

    openAI_embeddings = OpenAIEmbeddings()
    vStore = Chroma.from_documents(doc_texts, openAI_embeddings)

    conv_model = RetrievalQA.from_chain_type(
        llm=OpenAI(), 
        chain_type="stuff", 
        retriever=vStore.as_retriever(
            search_kwargs={"k": 1}
            )
        )
    voice_model = whisper.load_model("tiny")

    return conv_model, voice_model


def text_to_speech_gen(answer):  #文字转语音

    polly = boto3.client('polly',
                aws_access_key_id=AWS_ACCESS_KEY_ID,
                aws_secret_access_key=AWS_SECRET_ACCESS_KEY,
                region_name=AWS_REGION_NAME)

    response = polly.synthesize_speech(
        Text=answer, 
        VoiceId='Matthew', 
        OutputFormat='mp3', 
        Engine = "neural")
    
    audio_stream = response['AudioStream'].read()
    audio_html = audio_to_html(audio_stream)

    return audio_html
    

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")
    audio_html = f'<audio src="data:audio/mpeg;base64,{audio_base64}" controls autoplay></audio>'

    return audio_html


def get_chat_history(user_message, history):
    return "", history + [[user_message, None]]