File size: 16,296 Bytes
a8994db |
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 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Preparaci贸n del notebook con OpenAI API key"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"API key: sk-proj-****************************************************************************************************************************************************-amA_5sA\n"
]
}
],
"source": [
"import sys\n",
"import os\n",
"import json\n",
"import gradio as gr\n",
"sys.path.append('../src')\n",
"from procesador_de_cvs_con_llm import ProcesadorCV\n",
"from dotenv import load_dotenv\n",
"load_dotenv(\"../../../../../../../apis/.env\")\n",
"api_key = os.getenv(\"OPENAI_API_KEY\")\n",
"unmasked_chars = 8\n",
"masked_key = api_key[:unmasked_chars] + '*' * (len(api_key) - unmasked_chars*2) + api_key[-unmasked_chars:]\n",
"print(f\"API key: {masked_key}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prueba del m贸dulo de procesamiento"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Cliente inicializado como <openai.OpenAI object at 0x000001F3282AD0D0>\n",
"Respuesta:\n",
" {\n",
" \"puntuacion\": 100,\n",
" \"experiencia\": [\n",
" {\n",
" \"empresa\": \"Talking to Chatbots, by Reddgr\",\n",
" \"puesto\": \"Web Publisher and Generative AI Researcher\",\n",
" \"duracion\": 218\n",
" },\n",
" {\n",
" \"empresa\": \"IBM\",\n",
" \"puesto\": \"Relationship Manager | Cognitive Solutions SaaS\",\n",
" \"duracion\": 43\n",
" },\n",
" {\n",
" \"empresa\": \"Acoustic\",\n",
" \"puesto\": \"Principal Consultant | Martech SaaS\",\n",
" \"duracion\": 35\n",
" },\n",
" {\n",
" \"empresa\": \"IBM\",\n",
" \"puesto\": \"Engagement Manager, in support of Acoustic | B2B SaaS Retail Analytics\",\n",
" \"duracion\": 10\n",
" },\n",
" {\n",
" \"empresa\": \"IBM\",\n",
" \"puesto\": \"Engagement Manager | B2B SaaS Retail Analytics\",\n",
" \"duracion\": 9\n",
" },\n",
" {\n",
" \"empresa\": \"MBD Analytics\",\n",
" \"puesto\": \"Business Intelligence Consultant\",\n",
" \"duracion\": 10\n",
" }\n",
" ],\n",
" \"descripcion de la experiencia\": \"El candidato ha demostrado una experiencia excepcional en el campo de la inteligencia artificial generativa, acumulando m谩s de 18 a帽os en roles relevantes. Su posici贸n m谩s destacada como Web Publisher y Generative AI Researcher en 'Talking to Chatbots, by Reddgr' le ha proporcionado una base s贸lida en investigaci贸n y desarrollo de tecnolog铆as de IA. Adem谩s, su tiempo en IBM, donde ocup贸 m煤ltiples roles relacionados con soluciones cognitivas y an谩lisis de datos, ha reforzado su capacidad para manejar proyectos complejos en entornos SaaS. La combinaci贸n de estas experiencias, junto con su larga duraci贸n en cada puesto, justifica la puntuaci贸n m谩xima de 100, evidenciando su idoneidad para el rol de Generative AI Engineer.\"\n",
"}\n",
"Descripci贸n de la experiencia:\n",
"El candidato ha demostrado una experiencia excepcional en el campo de la inteligencia artificial generativa, acumulando\n",
"m谩s de 18 a帽os en roles relevantes. Su posici贸n m谩s destacada como Web Publisher y Generative AI Researcher en 'Talking\n",
"to Chatbots, by Reddgr' le ha proporcionado una base s贸lida en investigaci贸n y desarrollo de tecnolog铆as de IA. Adem谩s,\n",
"su tiempo en IBM, donde ocup贸 m煤ltiples roles relacionados con soluciones cognitivas y an谩lisis de datos, ha reforzado\n",
"su capacidad para manejar proyectos complejos en entornos SaaS. La combinaci贸n de estas experiencias, junto con su larga\n",
"duraci贸n en cada puesto, justifica la puntuaci贸n m谩xima de 100, evidenciando su idoneidad para el rol de Generative AI\n",
"Engineer.\n"
]
}
],
"source": [
"# Par谩metros de ejecuci贸n:\n",
"job_text = \"Generative AI engineer\"\n",
"cv_sample_path = '../../ejemplos_cvs/DavidGR_cv.txt' # Ruta al fichero de texto con un curr铆culo de ejemplo\n",
"with open(cv_sample_path, 'r') as file:\n",
" cv_text = file.read()\n",
"# Prompts:\n",
"with open('../prompts/ner_pre_prompt.txt', 'r', encoding='utf-8') as f:\n",
" ner_pre_prompt = f.read()\n",
"with open('../prompts/system_prompt.txt', 'r', encoding='utf-8') as f:\n",
" system_prompt = f.read()\n",
"with open('../prompts/user_prompt.txt', 'r', encoding='utf-8') as f:\n",
" user_prompt = f.read()\n",
"# Esquemas JSON:\n",
"with open('../json/ner_schema.json', 'r', encoding='utf-8') as f:\n",
" ner_schema = json.load(f)\n",
"with open('../json/response_schema.json', 'r', encoding='utf-8') as f:\n",
" response_schema = json.load(f)\n",
"\n",
"\n",
"procesador_cvs_prueba_final = ProcesadorCV(api_key, cv_text, job_text, ner_pre_prompt, \n",
" system_prompt, user_prompt, ner_schema, response_schema)\n",
"req_experience = 48 # Experiencia requerida en meses\n",
"positions_cap=10 # N煤mero m谩ximo de puestos a considerar\n",
"dist_threshold_low=0.5 # Distancia l铆mite para considerar un puesto equivalente\n",
"dist_threshold_high=0.7 # Distancia l铆mite para considerar un puesto no relevante\n",
"dict_respuesta = procesador_cvs_prueba_final.procesar_cv_completo(req_experience=req_experience,\n",
" positions_cap=positions_cap,\n",
" dist_threshold_low=dist_threshold_low,\n",
" dist_threshold_high=dist_threshold_high\n",
" )"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prueba de la aplicaci贸n Gradio"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Funci贸n de carga de la aplicaci贸n de \"backend\" para la interfaz Gradio:"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"def process_cv(job_text, cv_text, req_experience, positions_cap, dist_threshold_low, dist_threshold_high):\n",
" if dist_threshold_low >= dist_threshold_high:\n",
" return {\"error\": \"dist_threshold_low debe ser m谩s bajo que dist_threshold_high.\"}\n",
" \n",
" if not isinstance(cv_text, str) or not cv_text.strip():\n",
" return {\"error\": \"Por favor, introduce el CV o sube un fichero.\"}\n",
"\n",
" try:\n",
" procesador = ProcesadorCV(api_key, cv_text, job_text, ner_pre_prompt, \n",
" system_prompt, user_prompt, ner_schema, response_schema)\n",
" dict_respuesta = procesador.procesar_cv_completo(\n",
" req_experience=req_experience,\n",
" positions_cap=positions_cap,\n",
" dist_threshold_low=dist_threshold_low,\n",
" dist_threshold_high=dist_threshold_high\n",
" )\n",
" return dict_respuesta\n",
" except Exception as e:\n",
" return {\"error\": f\"Error en el procesamiento: {str(e)}\"}"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Interfaz de Gradio:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running on local URL: http://127.0.0.1:7860\n",
"\n",
"To create a public link, set `share=True` in `launch()`.\n"
]
},
{
"data": {
"text/html": [
"<div><iframe src=\"http://127.0.0.1:7860/\" 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": [
"c:\\Users\\david\\anaconda3\\Lib\\site-packages\\gradio\\analytics.py:106: UserWarning: IMPORTANT: You are using gradio version 4.44.0, however version 4.44.1 is available, please upgrade. \n",
"--------\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Cliente inicializado como <openai.OpenAI object at 0x000001F328980E10>\n",
"Respuesta:\n",
" {\n",
" \"puntuacion\": 54.75,\n",
" \"experiencia\": [\n",
" {\n",
" \"empresa\": \"bar de tapas\",\n",
" \"puesto\": \"charcutero\",\n",
" \"duracion\": 47\n",
" },\n",
" {\n",
" \"empresa\": \"\",\n",
" \"puesto\": \"camarero\",\n",
" \"duracion\": 2\n",
" }\n",
" ],\n",
" \"descripcion de la experiencia\": \"El candidato cuenta con una experiencia total de 47 meses como charcutero en un bar de tapas, lo que le proporciona habilidades relevantes en atenci贸n al cliente y manejo de productos alimenticios. Sin embargo, su experiencia como camarero es limitada, con solo 2 meses, lo que no contribuye significativamente a su perfil para el puesto de cajero de supermercado. La puntuaci贸n de 54.75 refleja que, aunque tiene una experiencia considerable en un rol relacionado, no cumple completamente con el requisito de 48 meses de experiencia espec铆fica en el 谩rea de caja o supermercado.\"\n",
"}\n",
"Descripci贸n de la experiencia:\n",
"El candidato cuenta con una experiencia total de 47 meses como charcutero en un bar de tapas, lo que le proporciona\n",
"habilidades relevantes en atenci贸n al cliente y manejo de productos alimenticios. Sin embargo, su experiencia como\n",
"camarero es limitada, con solo 2 meses, lo que no contribuye significativamente a su perfil para el puesto de cajero de\n",
"supermercado. La puntuaci贸n de 54.75 refleja que, aunque tiene una experiencia considerable en un rol relacionado, no\n",
"cumple completamente con el requisito de 48 meses de experiencia espec铆fica en el 谩rea de caja o supermercado.\n"
]
}
],
"source": [
"# Fichero de ejemplo para autocompletar (opci贸n que aparece en la parte de abajo de la interfaz de usuario):\n",
"with open('../cv_examples/reddgr_cv.txt', 'r') as file:\n",
" cv_example = file.read()\n",
"\n",
"default_parameters = [48, 10, 0.5, 0.7] # Par谩metros por defecto para el reinicio de la interfaz y los ejemplos predefinidos \n",
"\n",
"# C贸digo CSS para truncar el texto de ejemplo en la interfaz (bloque \"Examples\" en la parte de abajo):\n",
"css = \"\"\"\n",
" table tbody tr {\n",
" height: 2.5em; /* Set a fixed height for the rows */\n",
" overflow: hidden; /* Hide overflow content */\n",
" }\n",
"\n",
" table tbody tr td {\n",
" overflow: hidden; /* Ensure content within cells doesn't overflow */\n",
" text-overflow: ellipsis; /* Add ellipsis for overflowing text */\n",
" white-space: nowrap; /* Prevent text from wrapping */\n",
" vertical-align: middle; /* Align text vertically within the fixed height */\n",
" }\n",
" \"\"\"\n",
"\n",
"# Interfaz Gradio:\n",
"with gr.Blocks(css=css) as interface:\n",
" # Inputs\n",
" job_text_input = gr.Textbox(label=\"T铆tulo oferta de trabajo\", lines=1, placeholder=\"Introduce el t铆tulo de la oferta de trabajo\")\n",
" cv_text_input = gr.Textbox(label=\"CV en formato texto\", lines=5, max_lines=5, placeholder=\"Introduce el texto del CV\")\n",
" \n",
" # Opciones avanzadas ocultas en un objeto \"Accordion\"\n",
" with gr.Accordion(\"Opciones avanzadas\", open=False):\n",
" req_experience_input = gr.Number(label=\"Experiencia requerida (en meses)\", value=default_parameters[0], precision=0)\n",
" positions_cap_input = gr.Number(label=\"N煤mero m谩ximo de puestos a extraer\", value=default_parameters[1], precision=0)\n",
" dist_threshold_low_slider = gr.Slider(\n",
" label=\"Umbral m铆nimo de distancia de embeddings (puesto equivalente)\", \n",
" minimum=0, maximum=1, value=default_parameters[2], step=0.05\n",
" )\n",
" dist_threshold_high_slider = gr.Slider(\n",
" label=\"Umbral m谩ximo de distancia de embeddings (puesto irrelevante)\", \n",
" minimum=0, maximum=1, value=default_parameters[3], step=0.05\n",
" )\n",
" \n",
" submit_button = gr.Button(\"Procesar\")\n",
" clear_button = gr.Button(\"Limpiar\")\n",
" \n",
" output_json = gr.JSON(label=\"Resultado\")\n",
"\n",
" # Ejemplos:\n",
" examples = gr.Examples(\n",
" examples=[\n",
" [\"Cajero de supermercado\", \"Trabajo de charcutero desde 2021. Antes trabaj茅 2 meses de camarero en un bar de tapas.\"] + default_parameters,\n",
" [\"Generative AI Engineer\", cv_example] + default_parameters\n",
" ],\n",
" inputs=[job_text_input, cv_text_input, req_experience_input, positions_cap_input, dist_threshold_low_slider, dist_threshold_high_slider]\n",
" )\n",
"\n",
" # Bot贸n \"Procesar\"\n",
" submit_button.click(\n",
" fn=process_cv,\n",
" inputs=[\n",
" job_text_input, \n",
" cv_text_input, \n",
" req_experience_input, \n",
" positions_cap_input, \n",
" dist_threshold_low_slider, \n",
" dist_threshold_high_slider\n",
" ],\n",
" outputs=output_json\n",
" )\n",
"\n",
" # Bot贸n \"Limpiar\"\n",
" clear_button.click(\n",
" fn=lambda: (\"\",\"\",*default_parameters),\n",
" inputs=[],\n",
" outputs=[\n",
" job_text_input, \n",
" cv_text_input, \n",
" req_experience_input, \n",
" positions_cap_input, \n",
" dist_threshold_low_slider, \n",
" dist_threshold_high_slider\n",
" ]\n",
" )\n",
"\n",
" # Footer\n",
" gr.Markdown(\"\"\"\n",
" <footer>\n",
" <p>Puedes consultar el c贸digo completo de esta app y los notebooks explicativos en \n",
" <a href='https://github.com/reddgr' target='_blank'>GitHub</a></p>\n",
" <p>漏 2024 <a href='https://talkingtochatbots.com' target='_blank'>talkingtochatbots.com</a></p>\n",
" </footer>\n",
" \"\"\")\n",
"\n",
"# Lanzar la aplicaci贸n:\n",
"if __name__ == \"__main__\":\n",
" interface.launch()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"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": "3.11.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|