added unit tests

config.py

@@ -19,7 +19,7 @@ supabase = create_client(SUPABASE_URL, SUPABASE_KEY)
 embedding_model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
 
 HF_MODELS = {
-    "gemma": "https://router.huggingface.co/hf-inference/models/Falconsai/text_summarization"
+    "bart": "https://router.huggingface.co/hf-inference/models/facebook/bart-large-cnn"
 }
 
 HF_API_TOKEN = os.getenv("HF_API_TOKEN")
@@ -28,18 +28,18 @@ if not HF_API_TOKEN:
 
 HF_HEADERS = {"Authorization": f"Bearer {HF_API_TOKEN}"}
 
-def query(payload, model="gemma", retries=3, delay=5):
+def query(payload, model="bart", retries=3, delay=5):
     """
     Sends a request to the Hugging Face API with retries.
     
     :param payload: The input data for inference.
-    :param model: The model name ('gemma' for summarization).
+    :param model: The model name ('bart' for summarization).
     :param retries: Number of times to retry if the request fails.
     :param delay: Delay in seconds before retrying.
     :return: The model's response in JSON format, or None if all retries fail.
     """
     if model not in HF_MODELS:
-        raise ValueError("Invalid model name. Choose 'gemma' for summarization.")
+        raise ValueError("Invalid model name. Choose 'bart' for summarization.")
 
     api_url = HF_MODELS[model]
 

test_module.py

@@ -0,0 +1,67 @@
+import pytest
+import fitz  # PyMuPDF
+import re
+from io import BytesIO
+import torch
+from unittest.mock import MagicMock, patch
+from config import SUPABASE_URL, SUPABASE_KEY, HF_API_TOKEN, HF_HEADERS, supabase, HF_MODELS, query, embedding_model
+from utils import (
+    evaluate_resumes, parse_resume, extract_email, score_candidate, 
+    summarize_resume, store_in_supabase, generate_pdf_report
+)
+
+def test_parse_resume():
+    pdf_content = BytesIO()
+    doc = fitz.open()
+    page = doc.new_page()
+    page.insert_text((50, 50), "Sample Resume Text")
+    doc.save(pdf_content)
+    pdf_content.seek(0)
+    
+    extracted_text = parse_resume(pdf_content)
+    assert "Sample Resume Text" in extracted_text
+
+def test_extract_email():
+    text = "Contact me at test@example.com for details."
+    assert extract_email(text) == "test@example.com"
+    
+    text_no_email = "No email here."
+    assert extract_email(text_no_email) is None
+
+@patch("test_module.embedding_model.encode")
+def test_score_candidate(mock_encode):
+    # Mock embeddings as tensors with the same shape as actual embeddings
+    mock_encode.return_value = torch.tensor([0.1, 0.2, 0.3])  
+
+    score = score_candidate("Resume text", "Job description")
+
+    assert isinstance(score, float)
+    assert 0 <= score <= 1  # Ensure score is within valid range
+
+@patch("test_module.query")
+def test_summarize_resume(mock_query):
+    mock_query.return_value = [{"generated_text": "This is a summary."}]
+    summary = summarize_resume("Long resume text")
+    assert summary == "This is a summary."
+    
+    mock_query.return_value = None
+    assert summarize_resume("Long resume text") == "Summary could not be generated."
+
+@patch("test_module.supabase.table")
+def test_store_in_supabase(mock_table):
+    mock_insert = mock_table.return_value.insert.return_value.execute
+    mock_insert.return_value = {"status": "success"}
+    
+    response = store_in_supabase("Resume text", 0.8, "John Doe", "john@example.com", "Summary")
+    assert response["status"] == "success"
+
+def test_generate_pdf_report():
+    candidates = [{
+        "name": "John Doe",
+        "email": "john@example.com",
+        "score": 0.9,
+        "summary": "A skilled developer."
+    }]
+    pdf = generate_pdf_report(candidates)
+    assert isinstance(pdf, BytesIO)
+    assert pdf.getvalue()  # Check that the PDF is not empty

utils.py

@@ -65,17 +65,21 @@ def score_candidate(resume_text, job_description):
     except Exception as e:
         print(f"Error computing similarity score: {e}")
         return 0  # Return 0 if scoring fails
+    
+    # create multiple agents for different scoring
+    # agent_experience, agent_programming_language, agent_education, agent_soft_skills, etc etc
+    # Scoring from 1-5
 
 def summarize_resume(resume_text):
     """
-    Summarizes a resume using the Google gemma model.
+    Summarizes a resume using the Google bart model.
     
     :param resume_text: The resume text to summarize.
     :return: A summarized version of the resume.
     """
     payload = {"inputs": f"Summarize this resume: {resume_text}"}
     
-    response = query(payload, model="gemma")  # Use gemma for summarization
+    response = query(payload, model="bart")  # Use bart for summarization
 
     if response is None:
         print("Error: API response is None")