File size: 7,159 Bytes
6ada4db
0b44946
7a68ac2
 
 
8424213
e5662a0
c497020
549a3e5
e5662a0
7e46608
bb242b8
2bb53ee
 
bb242b8
 
2bb53ee
bb242b8
e5662a0
7a68ac2
e5662a0
026617c
 
0b44946
026617c
 
 
41fc166
 
 
 
 
 
 
 
 
 
 
 
 
 
026617c
 
 
 
c497020
fbef3c3
41fc166
 
 
 
 
 
 
 
239e9de
 
bb242b8
 
315c6c1
0b44946
8f3461e
0b44946
 
 
 
 
 
 
 
 
a9193e2
0b44946
8f3461e
c497020
026617c
8f3461e
c497020
026617c
de6c220
 
580c975
8f3461e
e5e07f8
4b7b809
7736b91
7e46608
10ce5d4
fbd4f88
 
 
 
 
87f3d05
fbd4f88
03197fd
87f3d05
fbd4f88
 
 
 
 
c3d2200
fbc2041
 
 
5429fac
794c36d
a2b15c1
7be963e
177b631
0b44946
8424213
 
 
 
 
 
 
fbc2041
 
 
c497020
b6b87c5
 
c497020
e5662a0
7a68ac2
 
 
 
 
 
 
 
 
c497020
 
 
 
 
bb242b8
 
c497020
0b44946
 
026617c
0b44946
c497020
 
 
 
0b44946
 
74af6f5
0b44946
 
c497020
0b44946
c497020
 
 
 
8424213
8f3461e
a4b1544
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
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167

import gradio as gr
import openai
import os
from gtts import gTTS
# from langdetect import detect

# Initialize the OpenAI API with your key and organization ID
openai.api_key = os.getenv('OPEN_API_KEY')

# all_messages = []  # List to store all conversation messages
all_messages = [{"role": "system", "content": 'You are an AI chatbot. Respond to all input in 25 words or less'}]


# def initialize_session():
#     return [{"role": "system", "content": 'You are an AI chatbot. Respond to all input in 25 words or less'}]

# all_messages = initialize_session()

open("output_audio.mp3", "wb").close()


def transcribe(audio, text):
    global all_messages
    language = 'en'

    transcript = {}
    # if audio:
    #     audio_filename_with_extension = audio + '.wav'
    #     os.rename(audio, audio_filename_with_extension)
    #     audio_file = open(audio_filename_with_extension, "rb")
    #     # Transcribe the audio file using the whisper-1 model
    #     transcript = openai.audio.transcriptions.create(model="whisper-1", file=audio_file)
    #     print("Transcription:", transcript)    
    # # user_input = transcript("text") if isinstance(transcript, dict) else ""
    # # user_input = transcript.text if isinstance(transcript, dict) else ""
    # user_input = transcript.get("text", "") if isinstance(transcript, dict) else ""
    # user_input = transcript.text
    # print("Transcription:", user_input) 
    # else :
    #     user_input = text  
    if audio:
        audio_filename_with_extension = audio + '.wav'
        os.rename(audio, audio_filename_with_extension)
        audio_file = open(audio_filename_with_extension, "rb")
        # Transcribe the audio file using the whisper-1 model
        transcript = openai.audio.transcriptions.create(model="whisper-1", file=audio_file)
        print("Transcription:", transcript)
        # user_input = transcript("text") if isinstance(transcript, dict) else ""
        # user_input = transcript.text if isinstance(transcript, dict) else ""
        user_input = transcript.get("text", "") if isinstance(transcript, dict) else ""
        user_input = transcript.text
        print("Transcription:", user_input)
    else:
        user_input = text


    # if not all_messages or (len(all_messages) == 1 and all_messages[0]["role"] == "system"):
    #     all_messages = initialize_session()
        
    conversation_tokens = sum(len(message['content'].split()) for message in all_messages)

    # Limit the conversation tokens to the model's maximum limit (4096 - a safety margin)
    max_conversation_tokens = 4000
    while conversation_tokens > max_conversation_tokens:
        oldest_message_tokens = len(all_messages[0]['content'].split())
        if conversation_tokens - oldest_message_tokens > max_conversation_tokens:
            all_messages.pop(0)
            conversation_tokens -= oldest_message_tokens
        else:
            break
    # all_messages.append = [{"role": "system", "content": 'You are an AI chatbot. Respond to all input in 25 words or less'}]
    all_messages.append({"role": "user", "content": user_input})

    # Generate a chat response using the gpt-3.5-turbo model
    response = openai.chat.completions.create(model="gpt-3.5-turbo", messages=all_messages)

    # Get the generated chat response from the model
    system_message = response.choices[0].message.content
    # all_messages.append(system_message.to_dict())
    all_messages.append({"role": "assistant", "content": system_message})




    chatbot_responses = []  # Initialize the list outside the loop
    # user_input = "" 
    for message in all_messages:
        print(f"Message: {message}")
        # print(f"role: {message['role']}")
        if 'role' in message and 'content' in message:
            # print(f"role: {message['role']}")
            if message['role'] == 'user':
                user_input = message['content']
                print(f"ui: {user_input}")
            elif message['role'] == 'assistant':
                chatbot_responses.append([user_input, message['content']])
                # chatbot_responses.append(message['content'])
                # print(f"hdjdkdkksdk: {message['content']}")
                print(f"Assistant response appended: {message['content']}")
    
    print(f"cbr: {chatbot_responses}")

  # For English input, use English language voice
    tts = gTTS(text=chatbot_responses[-1][1], lang='en', slow=False)
    tts.save("output_audio.mp3")


    

    
    # tts = gTTS(text=chatbot_responses[-1][1], lang=language, slow=False)
    # detected_language = detect(user_input)

    # if detected_language == 'hi':
    #     # For Hindi input, use the Hindi language voice
    #     tts = gTTS(text=chatbot_responses[-1][1], lang='hi', slow=False, lang_check=False)
    #     tts.save("output_audio.mp3")
    # else:
    # #     # For English input, use English language voice
    #     tts = gTTS(text=chatbot_responses[-1][1], lang='en', slow=False)
    #     tts.save("output_audio.mp3")

    return [chatbot_responses[-1]], "output_audio.mp3"  # Wrap the chatbot response in a list 
    # return chatbot_responses, "output_audio.mp3"

# out1 = gr.Audio("output_audio.mp3")

css_styles = """
footer { visibility:hidden; }
.audio_container { height: 100px; }
.svelte-1e89no8 { padding: 10px; }
.input_text_container { height: 100px; }
@media only screen and (max-width: 450px) { .input_text_container { display: none; } }
"""

with gr.Blocks(theme=gr.themes.Monochrome(font=[gr.themes.GoogleFont("Inter"), "sans-serif"],
                                           spacing_size=gr.themes.sizes.spacing_md,
                                           radius_size=gr.themes.sizes.radius_md),
              css=css_styles,
              title="NanoAI Voice Assistant") as demo:
    # chatbot = gr.Chatbot().style(height=450)  # Pass the all_messages list to the Chatbot widget
    chatbot = gr.Chatbot(clear_on_refresh=True).style(height=450)
    out1 = gr.Audio("output_audio.mp3", autoplay=True, label="Voice Response  ")
    with gr.Row():
        with gr.Column(scale=0.35):
            audio_input = gr.Audio(source="microphone", type="filepath", label="Record your question (Voice)", elem_classes="audio_container")
        with gr.Column(scale=0.65):
            text_input = gr.Textbox(label="Or Type your question here (Chat)",
                                    placeholder="What would you like to ask the bot...",
                                    elem_classes="input_text_container")    

    with gr.Row():
        with gr.Column(scale=0.50):
            text_button = gr.Button("Send a Message")
        with gr.Column(scale=0.50):
            reset_button = gr.Button("Clear ❌")
    text_button.click(transcribe, [audio_input, text_input], [chatbot, out1])
    text_button.click(lambda x: gr.update(value=''), [], [text_input])
    text_button.click(lambda: None, None, audio_input),
    text_button.click(lambda: None, None, out1),
    reset_button.click(lambda: None, None, chatbot),
    reset_button.click(lambda: None, None, out1)
    # audio_input = gr.Audio(source="microphone", type="filepath")

demo.launch()