Update main.py

main.py

@@ -45,29 +45,26 @@ def get_skills():
 def health():
     return jsonify({'status': 'Worked'})
 
-@app.route('/compare', methods=['POST'])
-def compare():
-    employee_skills = request.json.get('employee_skills')
-    jobs_skills = request.json.get('jobs_skills')
+@app.route('/compare_job', methods=['POST'])
+def compare_job():
+    job_skills = request.json.get('post')
+    employee_skills = request.json.get('job_skills')
 
     # Validation
-    if not isinstance(jobs_skills, list) or not all(isinstance(skill, str) for skill in jobs_skills):
-        raise ValueError("jobs_skills must be a list of strings")
+    if not isinstance(employee_skills, list) or not all(isinstance(skill, str) for skill in employee_skills):
+        raise ValueError("employee_skills must be a list of strings")
 
     # Encoding skills into embeddings
-    job_embeddings = model.encode(jobs_skills)
-    employee_embeddings = model.encode(employee_skills)
+    job_embedding = model.encode(job_skills)
+    employee_embedding = model.encode(employee_skills)
 
-    # Computing cosine similarity between employee skills and each job
-    similarity_scores = []
-    employee_embeddings_tensor = torch.from_numpy(employee_embeddings).unsqueeze(0)
+    # Computing cosine similarity between employee skills and the job
+    employee_embedding_tensor = torch.from_numpy(employee_embedding).unsqueeze(0)
+    job_embedding_tensor = torch.from_numpy(job_embedding).unsqueeze(0)
+    similarity_score = cosine_similarity(employee_embedding_tensor, job_embedding_tensor, dim=1)
 
-    for i, job_e in enumerate(job_embeddings):
-        job_e_tensor = torch.from_numpy(job_e).unsqueeze(0)
-        similarity_score = cosine_similarity(employee_embeddings_tensor, job_e_tensor, dim=1)
-        similarity_scores.append({"job": jobs_skills[i], "similarity_score": similarity_score.item()})
+    return jsonify({"job": job_skills, "similarity_score": similarity_score.item()})
 
-    return jsonify(similarity_scores)
 
 
 if __name__ == '__main__':