Spaces:
Sleeping
Sleeping
File size: 13,066 Bytes
5fdb69e |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 |
{
"cells": [
{
"cell_type": "markdown",
"id": "05432987-80bc-4aa5-8c05-277861e19307",
"metadata": {},
"source": [
"## Adds docstrings/comments to code and generates code summary"
]
},
{
"cell_type": "markdown",
"id": "e706f175-1e83-4d2c-8613-056b2e532624",
"metadata": {},
"source": [
"### Model Usage \n",
"\n",
"- **Open Source Models:**\n",
"\n",
" - Deployed via Endpoint: Hosted on a server and accessed remotely (Qwen 1.5-7)\n",
" - Run Locally on Machine: Executed directly on a local device (Ollama running Llama 3.2-1B)\n",
"\n",
"- **Closed Source Models:** \n",
" - Accessed through API key authentication: (OpenAI, Anthropic). \n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9ed667df-6660-4ba3-80c5-4c1c8f7e63f3",
"metadata": {},
"outputs": [],
"source": [
"# imports\n",
"\n",
"import os\n",
"import io\n",
"import sys \n",
"import json\n",
"import requests\n",
"from dotenv import load_dotenv\n",
"from openai import OpenAI\n",
"import google.generativeai\n",
"import anthropic\n",
"import ollama\n",
"from IPython.display import Markdown, display, update_display\n",
"import gradio as gr\n",
"from huggingface_hub import login, InferenceClient\n",
"from transformers import AutoTokenizer, pipeline"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c9dd4bf1-48cf-44dc-9d04-0ec6e8189a3c",
"metadata": {},
"outputs": [],
"source": [
"# environment\n",
"\n",
"load_dotenv()\n",
"os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY')\n",
"os.environ['ANTHROPIC_API_KEY'] = os.getenv('ANTHROPIC_API_KEY')\n",
"CODE_QWEN_URL = os.environ['CODE_QWEN_URL'] \n",
"BIGBIRD_PEGASUS_URL = os.environ['BIGBIRD_PEGASUS_URL']\n",
"HF_TOKEN = os.environ['HF_TOKEN']"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "71f671d6-50a7-43cf-9e04-52a159d67dab",
"metadata": {},
"outputs": [],
"source": [
"!ollama pull llama3.2:1b"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8e6f8f35-477d-4014-8fe9-874b5aee0061",
"metadata": {},
"outputs": [],
"source": [
"openai = OpenAI()\n",
"claude = anthropic.Anthropic()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ae34b79c-425a-4f04-821a-8f1d9868b146",
"metadata": {},
"outputs": [],
"source": [
"OPENAI_MODEL = \"gpt-4o-mini\"\n",
"CLAUDE_MODEL = \"claude-3-haiku-20240307\"\n",
"LLAMA_MODEL = \"llama3.2:1b\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "80e6d920-3c94-48c4-afd8-518f415ab777",
"metadata": {},
"outputs": [],
"source": [
"code_qwen = \"Qwen/CodeQwen1.5-7B-Chat\"\n",
"bigbird_pegasus = \"google/bigbird-pegasus-large-arxiv\"\n",
"login(HF_TOKEN, add_to_git_credential=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "314cd8e3-2c10-4149-9818-4e6b0c05b871",
"metadata": {},
"outputs": [],
"source": [
"# Uses Llama to Check Which Language the Code is Written In\n",
"system_message_comments = \"You are an assistant designed to add docstrings and helpful comments to code for documentation purposes.\"\n",
"system_message_comments += \"Respond back with properly formatted code, including docstrings and comments. Keep comments concise. \"\n",
"system_message_comments += \"Do not respond with greetings, or any such extra output\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "66fa09e4-1b79-4f53-9bb7-904d515b2f26",
"metadata": {},
"outputs": [],
"source": [
"system_message_summary = \"You are an assistant designed to summarise code for documentation purposes. You are not to display code again.\"\n",
"system_message_summary += \"Respond back with a properly crafted summary, mentioning key details regarding to the code, such as workflow, code language.\"\n",
"system_message_summary += \"Do not respond with greetings, or any such extra output. Do not respond in Markdown. Be thorough, keep explanation level at undergraduate level.\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ea405820-f9d1-4cf1-b465-9ae5cd9016f6",
"metadata": {},
"outputs": [],
"source": [
"def user_prompt_for(code):\n",
" user_prompt = \"Rewrite this code to include helpful comments and docstrings. \"\n",
" user_prompt += \"Respond only with code.\\n\"\n",
" user_prompt += code\n",
" return user_prompt"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "26c9be56-1d4f-43e5-9bc4-eb5b76da8071",
"metadata": {},
"outputs": [],
"source": [
"def user_prompt_for_summary(code):\n",
" user_prompt = \"Return the summary of the code.\\n\"\n",
" user_prompt += code\n",
" return user_prompt"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c0ac22cb-dc96-4ae1-b00d-2747572f6945",
"metadata": {},
"outputs": [],
"source": [
"def messages_for(code):\n",
" messages = [\n",
" {\"role\": \"system\", \"content\": system_message_comments},\n",
" {\"role\":\"user\", \"content\" : user_prompt_for(code)}\n",
" ]\n",
" return messages"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "eae1a8b4-68a8-4cd5-849e-0ecabd166a0c",
"metadata": {},
"outputs": [],
"source": [
"def messages_for_summary(code):\n",
" messages = [\n",
" {\"role\": \"system\", \"content\": system_message_summary},\n",
" {\"role\":\"user\", \"content\" : user_prompt_for_summary(code)}\n",
" ]\n",
" return messages"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5eb726dd-e09e-4011-8eb6-4d20f2830ff5",
"metadata": {},
"outputs": [],
"source": [
"func = \"\"\"\n",
"import time\n",
"\n",
"def calculate(iterations, param1, param2):\n",
" result = 1.0\n",
" for i in range(1, iterations+1):\n",
" j = i * param1 - param2\n",
" result -= (1/j)\n",
" j = i * param1 + param2\n",
" result += (1/j)\n",
" return result\n",
"\n",
"start_time = time.time()\n",
"result = calculate(100_000_000, 4, 1) * 4\n",
"end_time = time.time()\n",
"\n",
"print(f\"Result: {result:.12f}\")\n",
"print(f\"Execution Time: {(end_time - start_time):.6f} seconds\")\n",
"\"\"\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f61943b2-c939-4910-a670-58abaf464bb6",
"metadata": {},
"outputs": [],
"source": [
"def call_llama(code):\n",
" # commented code\n",
" messages = messages_for(code)\n",
" response1 = ollama.chat(model=LLAMA_MODEL, messages=messages)\n",
"\n",
" # summary\n",
" messages = messages_for_summary(code)\n",
" response2 = ollama.chat(model=LLAMA_MODEL, messages=messages)\n",
" \n",
" return response1['message']['content'],response2['message']['content']"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "696fb97e-807e-40ed-b0e1-beb82d1108a6",
"metadata": {},
"outputs": [],
"source": [
"def call_claude(code):\n",
" # commented code\n",
" message1 = claude.messages.create(\n",
" model=CLAUDE_MODEL,\n",
" system=system_message_comments,\n",
" messages=([{\"role\": \"user\", \"content\":user_prompt_for(code)}]),\n",
" max_tokens=500\n",
" )\n",
"\n",
" # summary\n",
" message2 = claude.messages.create(\n",
" model=CLAUDE_MODEL,\n",
" system=system_message_summary,\n",
" messages=([{\"role\": \"user\", \"content\":user_prompt_for_summary(code)}]),\n",
" max_tokens=500\n",
" )\n",
" \n",
" return message1.content[0].text,message2.content[0].text"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4bf1db64-86fa-42a1-98dd-3df74607f8db",
"metadata": {},
"outputs": [],
"source": [
"def call_gpt(code):\n",
" # commented code\n",
" completion1 = openai.chat.completions.create(\n",
" model=OPENAI_MODEL,\n",
" messages=messages_for(code),\n",
" )\n",
"\n",
" #summary\n",
" completion2 = openai.chat.completions.create(\n",
" model=OPENAI_MODEL,\n",
" messages=messages_for_summary(code),\n",
" )\n",
" \n",
" return completion1.choices[0].message.content,completion2.choices[0].message.content"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6863dc42-cbcd-4a95-8b0a-cfbcbfed0764",
"metadata": {},
"outputs": [],
"source": [
"def call_codeqwen(code):\n",
" # commented code\n",
" tokenizer = AutoTokenizer.from_pretrained(code_qwen)\n",
" messages = messages_for(code)\n",
" text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)\n",
" client = InferenceClient(CODE_QWEN_URL, token=HF_TOKEN)\n",
" response1 = client.text_generation(text, details=True, max_new_tokens=1000)\n",
"\n",
" # summary\n",
" tokenizer = AutoTokenizer.from_pretrained(code_qwen)\n",
" messages = messages_for_summary(code)\n",
" text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)\n",
" client = InferenceClient(CODE_QWEN_URL, token=HF_TOKEN)\n",
" response2 = client.text_generation(text, details=True, max_new_tokens=1000)\n",
" \n",
" return response1.generated_text ,response2.generated_text "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "06d05c02-45e4-47da-b70b-cf433dfaca4c",
"metadata": {},
"outputs": [],
"source": [
"def create_docs(code,model):\n",
" if model == \"Llama\":\n",
" comments,summary = call_llama(code)\n",
" elif model == \"Claude\":\n",
" comments,summary = call_claude(code)\n",
" elif model == \"GPT\":\n",
" comments,summary = call_gpt(code)\n",
" elif model == \"CodeQwen\":\n",
" comments,summary = call_codeqwen(code)\n",
" else:\n",
" raise ValueError(\"Unknown Model\")\n",
" return comments,summary"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1b4ea289-5da9-4b0e-b4d4-f8f01e466839",
"metadata": {},
"outputs": [],
"source": [
"css = \"\"\"\n",
".comments {background-color: #00599C;}\n",
".summary {background-color: #008B8B;}\n",
"\"\"\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "89ad7c7b-b881-45d3-aadc-d7206af578fb",
"metadata": {},
"outputs": [],
"source": [
"with gr.Blocks(css=css) as ui:\n",
" gr.Markdown(\"### Code Documentation and Formatting\")\n",
" with gr.Row():\n",
" code = gr.Textbox(label=\"Input Code: \", value=func, lines=10)\n",
" with gr.Row():\n",
" model = gr.Dropdown([\"GPT\",\"Claude\",\"Llama\",\"CodeQwen\"],label=\"Select model\",value=\"GPT\")\n",
" with gr.Row():\n",
" docs = gr.Button(\"Add Comments and Sumarise Code\")\n",
" with gr.Row():\n",
" commented_code = gr.Textbox(label= \"Formatted Code\", lines=10,elem_classes=[\"comments\"])\n",
" code_summary = gr.Textbox(label = \"Code Summary\", lines=10,elem_classes=[\"summary\"])\n",
" docs.click(create_docs,inputs=[code,model],outputs=[commented_code,code_summary]),"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1a9e3b1c-bfe6-4b71-aac8-fa36a491c157",
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"ui.launch(inbrowser=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ac895aa9-e044-4598-b715-d96d1c158656",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "5a96877c-22b7-4ad5-b235-1cf8f8b200a1",
"metadata": {},
"outputs": [],
"source": [
"print(call_llama(func))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f11de1a2-52c0-41c7-ad88-01ef5f8bc628",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.11.11"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|