here<\/i><\/a>.<\/p>\nProject Walkthrough<\/h3>\n
The project is structured into several Python modules. In the following sections, we\u2019ll understand the purpose of each file and its context in the project.<\/p>\n
src\/audio_transcriber.py<\/h4>\n
Resumes may not always be in text format. In cases where you receive an audio resume, the AudioTranscriber class comes into play. This file uses OpenAI\u2019s Whisper model to transcribe audio files into text. The transcription is then used by the analyzer to extract resume details.<\/p>\n
import whisper\n\nclass AudioTranscriber:\n \"\"\"Transcribe audio files using OpenAI Whisper.\"\"\"\n def __init__(self, model_size: str = \"base\"):\n \"\"\"\n Initializes the Whisper model for transcription.\n \n Args:\n model_size (str): The size of the Whisper model to load. Defaults to \"base\".\n \"\"\"\n self.model_size = model_size \n self.model = whisper.load_model(self.model_size)\n\n def transcribe(self, audio_path: str) -> str:\n \"\"\"\n Transcribes the given audio file and returns the text.\n \n Args:\n audio_path (str): The path to the audio file to be transcribed.\n \n Returns:\n str: The transcribed text.\n \n Raises:\n Exception: If transcription fails.\n \"\"\"\n try:\n result = self.model.transcribe(audio_path)\n return result[\"text\"]\n except Exception as e:\n print(f\"Error transcribing audio: {e}\")\n return \"\"<\/code><\/pre>\nMost resumes are available in PDF format. The PDFExtractor class is responsible for extracting text from PDF files using the PyPDF2 library. This module loops through all pages of a PDF document, extracts the text, and compiles it into a single string for further analysis.<\/p>\n
import PyPDF2\n\nclass PDFExtractor:\n \"\"\"Extract text from PDF files using PyPDF2.\"\"\"\n\n def __init__(self):\n \"\"\"Initialize the PDFExtractor.\"\"\"\n pass\n\n def extract_text(self, pdf_path: str) -> str:\n \"\"\"\n Extract text content from a given PDF file.\n\n Args:\n pdf_path (str): Path to the PDF file.\n\n Returns:\n str: Extracted text from the PDF.\n\n Raises:\n FileNotFoundError: If the file does not exist.\n Exception: For other unexpected errors.\n \"\"\"\n text = \"\"\n try:\n with open(pdf_path, \"rb\") as file:\n reader = PyPDF2.PdfReader(file)\n for page in reader.pages:\n page_text = page.extract_text()\n if page_text:\n text += page_text + \"\\n\"\n except FileNotFoundError:\n print(f\"Error: The file '{pdf_path}' was not found.\")\n except Exception as e:\n print(f\"An error occurred while extracting text: {e}\")\n \n return text <\/code><\/pre>\nsrc\/resume_pipeline.py<\/h4>\n
The ResumePipeline module acts as the orchestrator for processing resumes. It integrates both the PDF extractor and the audio transcriber. Based on the file type provided by the user, it directs the resume to the correct processor and returns the extracted text. This modular design allows for easy expansion if additional resume formats need to be supported in the future.<\/p>\n
from src.pdf_extractor import PDFExtractor\nfrom src.audio_transcriber import AudioTranscriber\n\nclass ResumePipeline:\n \"\"\"\n Process resume files (PDF or audio) and return extracted text.\n \"\"\"\n\n def __init__(self):\n \"\"\"Initialize the ResumePipeline with PDFExtractor and AudioTranscriber.\"\"\"\n self.pdf_extractor = PDFExtractor()\n self.audio_transcriber = AudioTranscriber()\n\n def process_resume(self, file_path: str, file_type: str) -> str:\n \"\"\"\n Process a resume file and extract text based on its type.\n\n Args:\n file_path (str): Path to the resume file.\n file_type (str): Type of the file ('pdf' or 'audio').\n\n Returns:\n str: Extracted text from the resume.\n\n Raises:\n ValueError: If the file type is unsupported.\n FileNotFoundError: If the specified file does not exist.\n Exception: For other unexpected errors.\n \"\"\"\n try:\n file_type_lower = file_type.lower()\n if file_type_lower == \"pdf\":\n return self.pdf_extractor.extract_text(file_path)\n elif file_type_lower in [\"audio\", \"wav\", \"mp3\"]:\n return self.audio_transcriber.transcribe(file_path)\n else:\n raise ValueError(\"Unsupported file type. Use 'pdf' or 'audio'.\")\n except FileNotFoundError:\n print(f\"Error: The file '{file_path}' was not found.\")\n return \"\"\n except ValueError as ve:\n print(f\"Error: {ve}\")\n return \"\"\n except Exception as e:\n print(f\"An unexpected error occurred: {e}\")\n return \"\"<\/code><\/pre>\nsrc\/analyzer.py<\/h4>\n
This module is the backbone of the resume analyzer. It initializes the connection to DeepInfra\u2019s API using the DeepSeek-R1 model. The main function in this file is analyze_text, which takes resume text as input and returns analysis summarizing key details from the resume. This file ensures that our resume text is processed by an AI model tailored for resume analysis.<\/p>\n
import os\nfrom openai import OpenAI \nfrom dotenv import load_dotenv\n\n# Load environment variables from .env file\nload_dotenv()\n\nclass DeepInfraAnalyzer:\n \"\"\"\n Calls DeepSeek-R1 model on DeepInfra using an OpenAI-compatible interface.\n This class processes resume text and extracts structured information using AI.\n \"\"\" \n def __init__(\n self,\n api_key: str= os.getenv(\"DEEPINFRA_TOKEN\"),\n model_name: str = \"deepseek-ai\/DeepSeek-R1\"\n ):\n \"\"\"\n Initializes the DeepInfraAnalyzer with API key and model name.\n\n :param api_key: API key for authentication \n :param model_name: The name of the model to use \n \"\"\"\n try:\n self.openai_client = OpenAI(\n api_key=api_key, \n base_url=\"https:\/\/api.deepinfra.com\/v1\/openai\",\n )\n self.model_name = model_name \n except Exception as e:\n raise RuntimeError(f\"Failed to initialize OpenAI client: {e}\")\n \n\n def analyze_text(self, text: str) -> str:\n \"\"\"\n Processes the given resume text and extracts key information in JSON format.\n The response will contain structured details about key skills, experience, education, etc.\n\n :param text: The resume text to analyze\n :return: JSON string with structured resume analysis\n \"\"\"\n prompt = (\n \"You are an AI job resume matcher assistant. \"\n \"DO NOT show your chain of thought. \"\n \"Respond ONLY in English. \"\n \"Extract the key skills, experiences, education, achievements, etc. from the following resume text. \"\n \"Then produce the final output as a well-structured JSON with a top-level key called \\\"analysis\\\". \"\n \"Inside \\\"analysis\\\", you can have subkeys like \\\"key_skills\\\", \\\"experiences\\\", \\\"education\\\", etc. \"\n \"Return ONLY the final JSON, with no extra commentary.\\n\\n\"\n f\"Resume Text:\\n{text}\\n\\n\"\n \"Required Format (example):\\n\"\n \"```\\n\"\n \"{\\n\"\n \" \\\"analysis\\\": {\\n\"\n \" \\\"key_skills\\\": [...],\\n\"\n \" \\\"experiences\\\": [...],\\n\"\n \" \\\"education\\\": [...],\\n\"\n \" \\\"achievements\\\": [...],\\n\"\n \" ...\\n\"\n \" }\\n\"\n \"}\\n\"\n \"```\\n\"\n ) \n try:\n response = self.openai_client.chat.completions.create(\n model=self.model_name,\n messages=[{\"role\": \"user\", \"content\": prompt}], \n )\n return response.choices[0].message.content\n except Exception as e:\n raise RuntimeError(f\"Error processing resume text: {e}\") <\/code><\/pre>\nsrc\/feedback_generator.py<\/h4>\n
After extracting details from the resume, the next step is to compare the resume against a specific job description. The FeedbackGenerator module takes the analysis from the resume and provides a match score along with recommendations for improvement. This module is crucial for job seekers aiming to refine their resumes to better align with job descriptions, increasing their chances of passing through ATS systems.<\/p>\n
from src.analyzer import DeepInfraAnalyzer \n\nclass FeedbackGenerator:\n \"\"\"\n Generates feedback for resume improvement based on a job description \n using the DeepInfraAnalyzer.\n \"\"\"\n\n def __init__(self, analyzer: DeepInfraAnalyzer):\n \"\"\"\n Initializes the FeedbackGenerator with an instance of DeepInfraAnalyzer.\n\n Args:\n analyzer (DeepInfraAnalyzer): An instance of the DeepInfraAnalyzer class.\n \"\"\"\n self.analyzer = analyzer \n\n def generate_feedback(self, resume_text: str, job_description: str) -> str:\n \"\"\"\n Generates feedback on how well a resume aligns with a job description.\n\n Args:\n resume_text (str): The extracted text from the resume.\n job_description (str): The job posting or job description.\n\n Returns:\n str: A JSON-formatted response containing:\n - \"match_score\" (int): A score from 0-100 indicating job match quality.\n - \"job_alignment\" (dict): Categorization of strong and weak matches.\n - \"missing_skills\" (list): Skills missing from the resume.\n - \"recommendations\" (list): Actionable suggestions for improvement.\n\n Raises:\n Exception: If an unexpected error occurs during analysis.\n \"\"\"\n try:\n prompt = (\n \"You are an AI job resume matcher assistant. \"\n \"DO NOT show your chain of thought. \"\n \"Respond ONLY in English. \"\n \"Compare the following resume text with the job description. \"\n \"Calculate a match score (0-100) for how well the resume matches. \"\n \"Identify keywords from the job description that are missing in the resume. \"\n \"Provide bullet-point recommendations to improve the resume for better alignment.\\n\\n\"\n f\"Resume Text:\\n{resume_text}\\n\\n\"\n f\"Job Description:\\n{job_description}\\n\\n\"\n \"Return JSON ONLY in this format:\\n\"\n \"{\\n\"\n \" \\\"job_match\\\": {\\n\"\n \" \\\"match_score\\\": ,\\n\"\n \" \\\"job_alignment\\\": {\\n\"\n \" \\\"strong_match\\\": [...],\\n\"\n \" \\\"weak_match\\\": [...]\\n\"\n \" },\\n\"\n \" \\\"missing_skills\\\": [...],\\n\"\n \" \\\"recommendations\\\": [\\n\"\n \" \\\"\\\",\\n\"\n \" \\\"\\\",\\n\"\n \" ...\\n\"\n \" ]\\n\"\n \" }\\n\"\n \"}\"\n ) \n return self.analyzer.analyze_text(prompt)\n\n except Exception as e:\n print(f\"Error in generating feedback: {e}\")\n return \"{}\" # Returning an empty JSON string in case of failure<\/actionable><\/actionable><\/integer><\/code><\/pre>\napp.py<\/h4>\n
The app.py file is the main entry point of the JobFitAI project. It integrates all the modules described above and builds an interactive web interface using Gradio. Users can upload a resume\/CV file (PDF or audio) and input a job description. The application then processes the resume, runs the analysis, generates feedback, and returns a structured JSON response with both the analysis and recommendations.<\/p>\n
import os\nfrom dotenv import load_dotenv\nload_dotenv()\n\nimport gradio as gr \nfrom src.resume_pipeline import ResumePipeline\nfrom src.analyzer import DeepInfraAnalyzer\nfrom src.feedback_generator import FeedbackGenerator\n\n# Pipeline for PDF\/audio\nresume_pipeline = ResumePipeline()\n\n# Initialize the DeepInfra analyzer \nanalyzer = DeepInfraAnalyzer()\n\n# Feedback generator\nfeedback_generator = FeedbackGenerator(analyzer) \n \ndef analyze_resume(resume_path, job_desc):\n \"\"\"\n Gradio callback function to analyze a resume against a job description.\n\n Args:\n resume_path (str): Path to the uploaded resume file (PDF or audio).\n job_desc (str): The job description text for comparison.\n \n \"\"\" \n try:\n if not resume_path or not job_desc:\n return {\"error\": \"Please upload a resume and enter a job description.\"}\n\n # Determine file type from extension\n lower_name = resume_path.lower()\n file_type = \"pdf\" if lower_name.endswith(\".pdf\") else \"audio\"\n\n # Extract text from the resume\n resume_text = resume_pipeline.process_resume(resume_path, file_type)\n\n # Analyze extracted text\n analysis_result = analyzer.analyze_text(resume_text)\n\n # Generate feedback and recommendations\n feedback = feedback_generator.generate_feedback(resume_text, job_desc)\n\n # Return structured response\n return {\n \"analysis\": analysis_result,\n \"recommendations\": feedback\n }\n except ValueError as e:\n return {\"error\": f\"Unsupported file type or processing error: {str(e)}\"}\n except Exception as e:\n return {\"error\": f\"An unexpected error occurred: {str(e)}\"}\n \n# Define Gradio interface\ndemo = gr.Interface(\n fn=analyze_resume,\n inputs=[\n gr.File(label=\"Resume (PDF\/Audio)\", type=\"filepath\"),\n gr.Textbox(lines=5, label=\"Job Description\"),\n ],\n outputs=\"json\",\n title=\"JobFitAI: AI Resume Analyzer\",\n description=\"\"\"\nUpload your resume\/cv (PDF or audio) and paste the job description to get a match score,\nmissing keywords, and actionable recommendations.\"\"\",\n)\n\nif __name__ == \"__main__\": \n demo.launch(server_name=\"0.0.0.0\", server_port=8000) <\/code><\/pre>\nRunning the Application with Gradio<\/h2>\n
After setting up your environment and reviewing all code components, you\u2019re ready to run the application.<\/p>\n
\n- Start the Application: <\/strong>In your terminal, navigate to your project directory and execute the below code<\/li>\n<\/ul>\n
python app.py\n<\/code><\/pre>\n\n