Update career_data.py

career_data.py

@@ -1,50 +1,31 @@
-from transformers import AutoModel, AutoTokenizer
+import json
+from model2vec import StaticModel
 import torch
 
-# Load model and tokenizer
-model_name = "minishlab/M2V_base_output"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModel.from_pretrained(model_name)
+# Load the Model2Vec pretrained model
+model = StaticModel.from_pretrained("minishlab/M2V_base_output")
 
-# Career options with precomputed skills and interests
-career_options = {
-    "Software Engineer": {
-        "skills": "programming, problem-solving",
-        "interests": "technology, innovation"
-    },
-    "Graphic Designer": {
-        "skills": "design, creativity",
-        "interests": "art, visual communication"
-    },
-    "Project Manager": {
-        "skills": "management, organization",
-        "interests": "leadership, strategy"
-    },
-    # Add more careers as needed
-}
-
-# Generate embeddings for career options
-def get_embedding(text):
-    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
-    with torch.no_grad():
-        embedding = model(**inputs).last_hidden_state.mean(dim=1).squeeze()
-    return embedding
+# Load career options from JSON file
+with open("career_options.json", "r") as file:
+    career_options = json.load(file)
 
+# Precompute embeddings for career options
 career_embeddings = {}
 for career, attributes in career_options.items():
     combined_text = attributes["skills"] + ", " + attributes["interests"]
-    career_embeddings[career] = get_embedding(combined_text)
+    career_embeddings[career] = model.encode([combined_text])[0]
 
-# Function to recommend careers based on skills and interests
+# Function to generate career recommendations
 def get_career_recommendations(skills: str, interests: str):
     user_input = skills + ", " + interests
-    user_embedding = get_embedding(user_input)
-    
+    user_embedding = model.encode([user_input])[0]
+
     recommendations = []
     for career, career_embedding in career_embeddings.items():
-        similarity = torch.cosine_similarity(user_embedding, career_embedding, dim=0).item()
+        similarity = torch.cosine_similarity(torch.tensor(user_embedding), torch.tensor(career_embedding), dim=0).item()
         recommendations.append((career, similarity))
     
+    # Sort by similarity score
     recommendations.sort(key=lambda x: x[1], reverse=True)
     
     return [f"{career} (Similarity: {similarity:.2f})" for career, similarity in recommendations[:5]]