File size: 10,251 Bytes
5cc1949
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Generative AI for Audio Application"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Restart Kernel (If needed)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'status': 'ok', 'restart': True}"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "ename": "",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31mThe Kernel crashed while executing code in the current cell or a previous cell. \n",
      "\u001b[1;31mPlease review the code in the cell(s) to identify a possible cause of the failure. \n",
      "\u001b[1;31mClick <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. \n",
      "\u001b[1;31mView Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
     ]
    }
   ],
   "source": [
    "import IPython\n",
    "\n",
    "app = IPython.Application.instance()\n",
    "app.kernel.do_shutdown(True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Import Libraries\n",
    "Most of the complexity for the chatbot is in [customizable_chatbot.py](./customizable_chatbot.py) that uses [audio.py](./audio.py) internally for the audio capabilities."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import gradio as gr\n",
    "from genai_voice.bots.chatbot import ChatBot\n",
    "from genai_voice.config.defaults import Config\n",
    "from genai_voice.logger.log_utils import log, LogLevels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "19:22:35 Configuration: \t\n",
      "        Default(MODEL_GPT_TURBO_NAME='gpt-4-turbo', \n",
      "        OPENAI_API_KEY='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', \n",
      "        TEMPERATURE=0.0, \n",
      "        TOP_P=0.97, \n",
      "        TOP_K=40, \n",
      "        MAX_OUTPUT_TOKENS=2048, \n",
      "        WEB_SCRAP_OUTPUT_DIR=data/context.txt)\n"
     ]
    }
   ],
   "source": [
    "log(f'Configuration: {Config()}', log_level=LogLevels.ON)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Set Current Working Directory  \n",
    "\n",
    "We want to simulate running this notebook from the project root just as it would work when using `Poetry` scripts."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "19:22:58 Before directory change: /Users/capturedbyace/sources/genai_voice/app\n",
      "19:22:58 Changing directory to root\n",
      "19:22:58 Before directory change: /Users/capturedbyace/sources/genai_voice\n"
     ]
    }
   ],
   "source": [
    "curr_wrk_dir = os.getcwd()\n",
    "log(f'Before directory change: {curr_wrk_dir}')\n",
    "if curr_wrk_dir.endswith('app'):\n",
    "    log(f'Changing directory to root')\n",
    "    os.chdir('..')\n",
    "    curr_wrk_dir = os.getcwd()\n",
    "log(f'Before directory change: {curr_wrk_dir}')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Create Data for LLM Context  \n",
    "\n",
    "`Poetry` scripts allow us to install our code as a package and run functions executables. \n",
    "\n",
    "We will use the `ExtractWebPagesAndSaveData` script, that is defined in `pyproject.toml` to scrape, extract and generate the file that the LLM will use as context data.\n",
    "\n",
    "`SAMPLE_URLS` have been defined under provided under `genai_voice.data_utils.urls.py`. Feel free to modify the links in that file to customize the source of data. \n",
    "\n",
    "> **DISCLAIMER:** Be responsible when scraping data that is not yours, complying with the EULA of the sites and conducting it in a legal fashion. Also remember that most sites will throttle scrapes, so do this with caution.  \n",
    "\n",
    "> **NOTE:** This is an optional step. It just shows you have you can get custom data for your LLM context. We have provided the data for this project. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "19:23:25 Starting the web scraper...\n",
      "19:23:25 Creating the AsyncChromiumLoader with #10 urls...\n",
      "19:23:25 Starting scraping...\n",
      "19:23:28 Content scraped\n",
      "19:23:29 Starting scraping...\n",
      "19:23:33 Content scraped\n",
      "19:23:33 Starting scraping...\n",
      "19:23:36 Content scraped\n",
      "19:23:36 Starting scraping...\n",
      "19:23:39 Content scraped\n",
      "19:23:39 Starting scraping...\n",
      "19:23:41 Content scraped\n",
      "19:23:41 Starting scraping...\n",
      "19:23:45 Content scraped\n",
      "19:23:45 Starting scraping...\n",
      "19:23:49 Content scraped\n",
      "19:23:49 Starting scraping...\n",
      "19:23:53 Content scraped\n",
      "19:23:53 Starting scraping...\n",
      "19:23:57 Content scraped\n",
      "19:23:57 Starting scraping...\n",
      "19:24:00 Content scraped\n",
      "19:24:00 Documents scraped.\n",
      "19:24:00 Using BeautifulSoutTransformer to extract ['h1', 'h2', 'h3', 'p'].\n",
      "19:24:02 Transformed #10 urls.\n",
      "19:24:02 Writing to output file.\n",
      "19:24:02 Successfully written data to data/context.txt\n"
     ]
    }
   ],
   "source": [
    "!poetry run ExtractWebPagesAndSaveData"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Gradio Interface\n",
    "This launches the UI, you will probably need to allow the browser to use the microphone to enable the audio functions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "19:27:45 Context file: travel_bot_context.txt\n",
      "19:27:45 Creating the OpenAI Model Client.\n",
      "19:27:45 Initialized OpenAI model: gpt-4-turbo\n",
      "19:27:45 HTTP Request: GET http://127.0.0.1:7861/startup-events \"HTTP/1.1 200 OK\"\n",
      "19:27:45 HTTP Request: HEAD http://127.0.0.1:7861/ \"HTTP/1.1 200 OK\"\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7861\n",
      "\n",
      "To create a public link, set `share=True` in `launch()`.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"http://127.0.0.1:7861/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "19:27:46 HTTP Request: GET https://api.gradio.app/pkg-version \"HTTP/1.1 200 OK\"\n"
     ]
    },
    {
     "data": {
      "text/plain": []
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Getting prompt from audio device: (44100, array([ 9, 12, 10, ...,  0,  0,  0], dtype=int16))\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/capturedbyace/sources/genai_voice/venv/lib/python3.10/site-packages/transformers/models/whisper/generation_whisper.py:496: FutureWarning: The input name `inputs` is deprecated. Please make sure to use `input_features` instead.\n",
      "  warnings.warn(\n",
      "19:28:23 Transcribed prompt:  Hello, how are you?\n",
      "19:28:23 Empty history. Creating a state list to track histories.\n",
      "19:28:23 {'temperature': 0.0, 'top_p': 0.97, 'top_k': 40, 'max_output_tokens': 2048, 'seed': 0, 'response_format': {'type': 'text'}}\n",
      "19:28:25 HTTP Request: POST https://api.openai.com/v1/chat/completions \"HTTP/1.1 200 OK\"\n",
      "19:28:25 Chatbot response: Hello! I'm just a virtual assistant, but thank you for asking. How can I assist you with your travel plans today?\n"
     ]
    }
   ],
   "source": [
    "\"\"\"Run Chatbot app\"\"\"\n",
    "chatbot = ChatBot(enable_speakers=True, threaded=True)\n",
    "history = []\n",
    "\n",
    "def get_response(audio):\n",
    "    \"\"\"Get Audio Response From Chatbot\"\"\"\n",
    "    if not audio:\n",
    "        raise ValueError(\"No audio file provided.\")\n",
    "    prompt = chatbot.get_prompt_from_gradio_audio(audio)\n",
    "    log(f\"Transcribed prompt: {prompt}\", log_level=LogLevels.ON)\n",
    "    response = chatbot.respond(prompt, history)\n",
    "    log(f\"Chatbot response: {response}\", log_level=LogLevels.ON)\n",
    "    history.append([prompt, response])\n",
    "    return response\n",
    "\n",
    "demo = gr.Interface(\n",
    "        get_response,\n",
    "        gr.Audio(sources=\"microphone\"),\n",
    "        None,\n",
    "        title=\"Wanderwise Travel Assistant\"\n",
    ")\n",
    "demo.launch()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}