Create app.py

app.py

@@ -0,0 +1,102 @@
+import gradio as gr
+import pandas as pd
+import matplotlib.pyplot as plt
+from transformers import pipeline
+from sentence_transformers import SentenceTransformer, util
+from langdetect import detect
+
+#information about job descriptions
+data = {
+    'Company': ['Google', 'Amazon', 'Microsoft', 'Facebook', 'Tesla'],
+    'Job_Description': [
+        "We are looking for a Senior Software Engineer with extensive experience in Python, Java, and cloud computing. The candidate should have experience working in an Agile environment and a deep understanding of machine learning.",
+        "The Data Analyst will analyze large datasets to uncover trends, patterns, and insights. Proficiency in SQL, Python, and data visualization tools like PowerBI or Tableau is required.",
+        "Hiring a Cloud Architect with experience in Azure, AWS, and cloud infrastructure design. The ideal candidate should have experience with Docker, Kubernetes, and network security.",
+        "AI Research Scientist with expertise in machine learning, deep learning, and natural language processing (NLP). Experience with TensorFlow, PyTorch, and data-driven research.",
+        "Looking for an Electrical Engineer with experience in circuit design, power electronics, and embedded systems. Proficiency in CAD tools and simulation software is a must."
+    ]
+}
+
+# Load the job descriptions into a pandas DataFrame
+df = pd.DataFrame(data)
+# Load the Hugging Face model for semantic similarity
+model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
+translator = pipeline(task="translation", model="facebook/nllb-200-distilled-600M")
+lang_code_mapping = {
+    'ar': 'arb_Arab',  # Arabic
+    'fr': 'fra_Latn',  # French
+    'es': 'spa_Latn',  # Spanish
+    'de': 'deu_Latn',  # German
+}
+
+# Take CV and translate it to English if not in English to compare to job descriptions and return English CV and detected language
+def translate_to_english(cv_text):
+    detected_lang = lang_code_mapping.get(detect(cv_text), "eng_Latn")
+
+    # Translate to English if not already in English
+    if detected_lang != 'eng_Latn':
+        translation = translator(cv_text, src_lang=detected_lang, tgt_lang="eng_Latn")[0]['translation_text']
+        return translation, detected_lang
+    else:
+        return cv_text, detected_lang 
+
+#if an entered cv is not in English return the job description in the entered cv language 
+def translate_job_description_if_needed(job_description, target_lang):
+    if target_lang != 'en':
+        return translator(job_description, src_lang="eng_Latn", tgt_lang=target_lang)[0]['translation_text']
+    return job_description 
+
+# Function to find top 3 job descriptions matching the CV using semantic similarity
+def find_top_matches(cv_text):
+    if not cv_text:
+        return "Error: CV is empty", None
+
+    # Translate CV to English if it contains Arabic text
+    cv_text, detected_lang = translate_to_english(cv_text)
+    # Get job descriptions from the DataFrame
+    descriptions = df['Job_Description'].tolist()
+
+    # Encode both the CV and job descriptions
+    descriptions_embeddings = model.encode(descriptions, convert_to_tensor=True)
+    cv_embedding = model.encode([cv_text], convert_to_tensor=True)
+    # Calculate cosine similarities between the CV and all job descriptions
+    similarities = util.pytorch_cos_sim(cv_embedding, descriptions_embeddings)[0]
+
+    # Get the top 3 matches based on similarity scores
+    top_3_indices = similarities.argsort(descending=True)[:3]  # Get the indices of the top 3 matches
+    top_3_matches = df.iloc[top_3_indices]
+    top_3_similarities = similarities[top_3_indices].numpy()
+
+    #create vertical bar
+    plt.bar(top_3_matches['Company'], top_3_similarities, color='skyblue')
+
+    # Set the labels and title
+    plt.ylabel('Similarity Score')
+    plt.xlabel('Company')
+    plt.title('Top 3 Job Description Matches')
+    # Create a detailed summary for the top 3 job descriptions
+    job_summaries = ""
+    for _, row in top_3_matches.iterrows():
+        # Translate job description if the detected language is not English
+        job_desc_translated = translate_job_description_if_needed(row['Job_Description'], detected_lang)
+
+        # Show job description only in the detected language if it's not English
+        job_summaries += f"<strong>Company:</strong> {row['Company']}<br>"
+        job_summaries += f"<strong>Job Description :</strong> {job_desc_translated}<br><br>"
+
+    return job_summaries, plt
+
+# Define Gradio interface
+demo = gr.Interface(
+    fn=find_top_matches,
+    inputs=gr.Textbox(lines=15, placeholder="Enter your CV text here...", label="CV Text"),
+    outputs=[
+        gr.HTML(label="Job Summaries"),
+        gr.Plot(label="Top 3 Matching Job Descriptions")
+    ],
+    title="'Match CV to Job Description",
+    description="Upload your CV to find the top 3 job descriptions that match from the available companies using semantic similarity."
+)
+
+# Launch the Gradio interface in Colab
+demo.launch()