added config and count tokens

Docker/config.py

@@ -0,0 +1,49 @@
+from pathlib import Path
+from pydantic_settings import BaseSettings, SettingsConfigDict
+from dotenv import load_dotenv
+from datetime import timedelta
+import warnings
+
+load_dotenv()
+
+
+class Settings(BaseSettings):
+    raw_path_: str
+    processed_path_: str
+    models_path_:str
+    interim_path_:str
+    external_path_:str
+
+    model_config = SettingsConfigDict(
+        env_prefix="mrh_avap_",
+        env_file=".env",
+        env_file_encoding="utf-8",
+        case_sensitive=False,
+        extra="ignore",
+    )
+
+    @property
+    def raw_path(self) -> Path:
+        return Path(self.raw_path_)
+
+    @property
+    def processed_path(self) -> Path:
+        return Path(self.processed_path_)
+
+    @property
+    def proj_root(self) -> Path:
+        return Path(__file__).resolve().parents[1]
+
+    @property
+    def interim_path(self) -> Path:
+        return Path(self.interim_path_)
+    
+    @property
+    def external_path(self) -> Path:
+        return Path(self.external_path_)
+
+    @property
+    def models_path(self) -> Path:
+        return Path(self.models_path_)
+
+settings = Settings()

scratches/pseco/ingestion/n00 Count tokens.ipynb

@@ -0,0 +1,125 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ed60d28c",
+   "metadata": {},
+   "source": [
+    "# Libreries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "95cf533e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import AutoTokenizer\n",
+    "from Docker.config import settings\n",
+    "import os"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c9b7265a",
+   "metadata": {},
+   "source": [
+    "# Functions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "6fd7de78",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def load_text_from_file(file_path: str) -> str:\n",
+    "    \"\"\"\n",
+    "    Load text content from a specified file.\n",
+    "\n",
+    "    Args:\n",
+    "        file_path: Path to the .txt file to load.\n",
+    "\n",
+    "    Returns:\n",
+    "        The text content of the file.\n",
+    "\n",
+    "    Raises:\n",
+    "        FileNotFoundError: If the file does not exist.\n",
+    "        IOError: If the file cannot be read.\n",
+    "    \"\"\"\n",
+    "    try:\n",
+    "        with open(file_path, \"r\", encoding=\"utf-8\") as file:\n",
+    "            return file.read()\n",
+    "    except FileNotFoundError:\n",
+    "        raise FileNotFoundError(f\"El archivo '{file_path}' no existe.\")\n",
+    "    except IOError as error:\n",
+    "        raise IOError(f\"Error al leer '{file_path}': {error}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "22bcc0fe",
+   "metadata": {},
+   "source": [
+    "# Test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "19c815e4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model_name = os.getenv(\"HF_EMB_MODEL_NAME\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "4ff2484d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Número de tokens: 1073\n"
+     ]
+    }
+   ],
+   "source": [
+    "tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
+    "\n",
+    "text = load_text_from_file(settings.raw_path / '1_Introduction.txt')\n",
+    "\n",
+    "tokens = tokenizer.encode(text)\n",
+    "\n",
+    "print(\"Número de tokens:\", len(tokens))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "assistance-engine",
+   "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": "3.12.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}