feat: good code

src/notebook/notebook.ipynb

@@ -2,65 +2,22 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Requirement already satisfied: roboflow in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (1.1.44)\n",
-      "Requirement already satisfied: certifi in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from roboflow) (2024.7.4)\n",
-      "Requirement already satisfied: idna==3.7 in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from roboflow) (3.7)\n",
-      "Requirement already satisfied: cycler in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from roboflow) (0.12.1)\n",
-      "Requirement already satisfied: kiwisolver>=1.3.1 in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from roboflow) (1.4.5)\n",
-      "Requirement already satisfied: matplotlib in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from roboflow) (3.9.2)\n",
-      "Requirement already satisfied: numpy>=1.18.5 in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from roboflow) (1.26.4)\n",
-      "Requirement already satisfied: opencv-python-headless==4.10.0.84 in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from roboflow) (4.10.0.84)\n",
-      "Requirement already satisfied: Pillow>=7.1.2 in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from roboflow) (10.4.0)\n",
-      "Requirement already satisfied: python-dateutil in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from roboflow) (2.9.0.post0)\n",
-      "Requirement already satisfied: python-dotenv in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from roboflow) (1.0.1)\n",
-      "Requirement already satisfied: requests in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from roboflow) (2.31.0)\n",
-      "Requirement already satisfied: six in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from roboflow) (1.16.0)\n",
-      "Requirement already satisfied: urllib3>=1.26.6 in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from roboflow) (2.2.3)\n",
-      "Requirement already satisfied: tqdm>=4.41.0 in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from roboflow) (4.66.4)\n",
-      "Requirement already satisfied: PyYAML>=5.3.1 in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from roboflow) (6.0.1)\n",
-      "Requirement already satisfied: requests-toolbelt in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from roboflow) (1.0.0)\n",
-      "Requirement already satisfied: filetype in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from roboflow) (1.2.0)\n",
-      "Requirement already satisfied: colorama in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from tqdm>=4.41.0->roboflow) (0.4.4)\n",
-      "Requirement already satisfied: contourpy>=1.0.1 in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from matplotlib->roboflow) (1.2.1)\n",
-      "Requirement already satisfied: fonttools>=4.22.0 in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from matplotlib->roboflow) (4.53.1)\n",
-      "Requirement already satisfied: packaging>=20.0 in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from matplotlib->roboflow) (24.1)\n",
-      "Requirement already satisfied: pyparsing>=2.3.1 in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from matplotlib->roboflow) (3.1.2)\n",
-      "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\htbqn\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (from requests->roboflow) (3.3.2)\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "WARNING: Ignoring invalid distribution ~angchain (C:\\Users\\htbqn\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages)\n",
-      "WARNING: Ignoring invalid distribution ~ip (C:\\Users\\htbqn\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages)\n",
-      "WARNING: Ignoring invalid distribution ~angchain (C:\\Users\\htbqn\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages)\n",
-      "WARNING: Ignoring invalid distribution ~ip (C:\\Users\\htbqn\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages)\n",
-      "WARNING: Ignoring invalid distribution ~angchain (C:\\Users\\htbqn\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages)\n",
-      "WARNING: Ignoring invalid distribution ~ip (C:\\Users\\htbqn\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "loading Roboflow workspace...\n",
-      "loading Roboflow project...\n",
-      "Dependency ultralytics==8.0.196 is required but found version=8.2.90, to fix: `pip install ultralytics==8.0.196`\n"
+      "loading Roboflow project...\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Downloading Dataset Version Zip in annotation-2 to yolov8:: 100%|██████████| 92659/92659 [00:06<00:00, 14429.98it/s]"
+      "Downloading Dataset Version Zip in cvparsing-2 to yolov9:: 100%|██████████| 63864/63864 [00:04<00:00, 15236.33it/s]"
      ]
     },
     {
@@ -75,7 +32,7 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "Extracting Dataset Version Zip to annotation-2 in yolov8:: 100%|██████████| 3376/3376 [00:00<00:00, 3563.34it/s]\n"
+      "Extracting Dataset Version Zip to cvparsing-2 in yolov9:: 100%|██████████| 2344/2344 [00:00<00:00, 5118.00it/s]\n"
      ]
     }
    ],
@@ -147,7 +104,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -158,10 +115,6 @@
     "nc: 14\n",
     "names: ['Achievement', 'Certifications', 'Community', 'Contact', 'Education', 'Experience', 'Interests', 'Languages', 'Name', 'Profil', 'Projects', 'image', 'resume', 'skills']\"\"\"\n",
     "\n",
-    "#  3 + 8  -> 3\n",
-    "#  5 + 10 + 1 -> 5\n",
-    "# 13 + 7 -> 13\n",
-    "\n",
     "with open(\"./data.yaml\", 'w') as file:\n",
     "    file.write(yaml_text),\n",
     "\n",
@@ -169,77 +122,6 @@
     "# %cat /kaggle/working/data.yaml\n"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Labels mapped and saved to ./test.txt\n"
-     ]
-    }
-   ],
-   "source": [
-    "import os\n",
-    "\n",
-    "def map_yolo_labels(file_path, label_mapping, output_file=None):\n",
-    "    \"\"\"\n",
-    "    Remaps the class labels in a YOLOv8 label file and saves the updated labels.\n",
-    "    \n",
-    "    Parameters:\n",
-    "    - file_path: Path to the YOLOv8 label file.\n",
-    "    - label_mapping: Dictionary for remapping labels (e.g., {3: 3, 8: 3, 5: 5, 10: 5, 1: 5, 13: 13, 7: 13}).\n",
-    "    - output_file: Path to save the remapped labels (optional). If not provided, it overwrites the original file.\n",
-    "    \n",
-    "    Returns:\n",
-    "    - None\n",
-    "    \"\"\"\n",
-    "    with open(file_path, 'r') as file:\n",
-    "        lines = file.readlines()\n",
-    "\n",
-    "    # Process each line and remap the class label\n",
-    "    updated_lines = []\n",
-    "    for line in lines:\n",
-    "        parts = line.strip().split()\n",
-    "        class_id = int(parts[0])  # The first part is the class label\n",
-    "        \n",
-    "        # Remap the class label using the mapping\n",
-    "        new_class_id = label_mapping.get(class_id, class_id)\n",
-    "        \n",
-    "        # Reconstruct the line with the new class label\n",
-    "        updated_line = f\"{new_class_id} {' '.join(parts[1:])}\\n\"\n",
-    "        updated_lines.append(updated_line)\n",
-    "    \n",
-    "    # Write to the output file (overwrite original file if output_file is not provided)\n",
-    "    if output_file is None:\n",
-    "        output_file = file_path\n",
-    "\n",
-    "    with open(output_file, 'w') as file:\n",
-    "        file.writelines(updated_lines)\n",
-    "    \n",
-    "    print(f\"Labels mapped and saved to {output_file}\")\n",
-    "\n",
-    "# Example usage:\n",
-    "label_mapping = {\n",
-    "    3: 3,    # Map 3 -> 3\n",
-    "    8: 3,    # Map 8 -> 3\n",
-    "    5: 5,    # Map 5 -> 5\n",
-    "    10: 5,   # Map 10 -> 5\n",
-    "    1: 5,    # Map 1 -> 5\n",
-    "    13: 13,  # Map 13 -> 13\n",
-    "    7: 13    # Map 7 -> 13\n",
-    "}\n",
-    "\n",
-    "# Path to your YOLOv8 label file\n",
-    "label_file = \"./test.txt\"\n",
-    "\n",
-    "# Call the function to remap labels\n",
-    "map_yolo_labels(label_file, label_mapping)\n"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 20,
@@ -551,7 +433,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": ".venv",
    "language": "python",
    "name": "python3"
   },

src/prompt/promt.py

@@ -19,38 +19,31 @@ Output must be in JSON format following the same structure as the input.
         ("human", "{user_input}"),
     ]
 )
-
-
-prompt_experience = ChatPromptTemplate.from_messages(
+matching_jd_prompt = ChatPromptTemplate.from_messages(
     [
         (
             "system",
-            """
-# Role: You are an expert at extracting key information about projects from the "experience" section of an OCR'd resume.
-
-# Instruction:
-You are given a JSON object containing extracted resume data from an OCR model. This data likely contains errors like misspellings, merged words, and extracted noise. Your task is to:
-
-1. **Pre-process the "experience" field:**
-    * Correct misspellings using your knowledge of common resume terms and English vocabulary.
-    * Separate merged words and remove any obvious OCR noise.
-
-2. **Identify the "experience" field:** Locate the field labeled "experience" (or a similar label) within the JSON object.
-
-3. **Extract project information:** 
-    * Identify project mentions: Look for keywords and phrases that indicate a project, such as "project," "developed," "implemented," "designed," "contributed to," etc.
-    * Extract project details: For each project mentioned:
-        * Project name or description
-        * Role and contributions
-        * Technologies used
-        * Outcomes and achievements
-
-4. **Structure the output:** Return a JSON object with a "projects" field containing an array of extracted project details. The exact format can be flexible to accommodate variations in the input data.
-
-
-
+"""
+Role: Expert resume analyzer matching qualifications with the following job requirements:
+{job_description}
+
+Tasks:
+1. Analyze resume experience and skills against job requirements:
+- Match skills/experience to job requirements
+- Score relevance (0-100%)
+- Identify key matching qualifications
+2. Provide concise reasoning explaining the score based on:
+  - Key matching skills and experiences
+  - Notable gaps
+  - Level of experience alignment
+Output JSON format:
+Output JSON:
+{{
+   "score": float,  # Overall match percentage 
+   "reasoning": str  # Clear 2-3 sentence explanation of the score
+}}
 """,
         ),
-        ("human", "{user_input}"),
+        ("human", "{resume_input}"),
     ]
 )

src/utils/utils_segment.py

@@ -4,8 +4,6 @@ import cv2
 from typing import Tuple
 from pytesseract import pytesseract
 
-# path_to_tesseract = r"C:\Program Files\Tesseract-OCR\tesseract.exe"
-# pytesseract.tesseract_cmd = path_to_tesseract
 class_names = [
     "Community",
     "Contact",