update

src/similarity_model/semantic_search.py

@@ -1,5 +1,3 @@
-# src/semantic_search.py
-
 import re
 import ast
 import logging
@@ -15,25 +13,17 @@ from Data.database.sql_connector import (
     load_preprocessed_projects
 )
 
-# =====================================================
-# Logging
-# =====================================================
 logging.basicConfig(
     level=logging.INFO,
     format="%(asctime)s | %(levelname)s | %(message)s"
 )
 logger = logging.getLogger(__name__)
 
-# =====================================================
-# Config
-# =====================================================
 DEFAULT_MODEL = "all-MiniLM-L6-v2"
 
 TITLE_COL = "project_title"
 TECH_COL = "technologies"
 
-# Resolve paths relative to the project root (3 levels up from this file:
-# src/similarity_model/semantic_search.py -> src/similarity_model -> src -> project root)
 _PROJECT_ROOT = Path(__file__).resolve().parents[2]
 
 INDEX_PATH = _PROJECT_ROOT / "models" / "faiss_index.bin"
@@ -43,9 +33,6 @@ EMBED_PATH = _PROJECT_ROOT / "models" / "project_embeddings.npy"
 TOP_K = 20
 MIN_SCORE = 0.35
 
-# =====================================================
-# Text Helpers
-# =====================================================
 def normalize_text(text: str) -> str:
     """
     Normalize user query to match preprocessing style.
@@ -61,23 +48,17 @@ def normalize_text(text: str) -> str:
 
     return text
 
-
 def tokenize(text: str) -> set:
     """
     Tokenize normalized text.
     """
     return set(normalize_text(text).split())
 
-
-# =====================================================
-# Cached Loaders
-# =====================================================
 @lru_cache(maxsize=1)
 def load_model():
     logger.info(f"Loading model: {DEFAULT_MODEL}")
     return SentenceTransformer(DEFAULT_MODEL)
 
-
 @lru_cache(maxsize=1)
 def load_faiss_index():
     if not INDEX_PATH.exists():
@@ -86,7 +67,6 @@ def load_faiss_index():
     logger.info("Loading FAISS index...")
     return faiss.read_index(str(INDEX_PATH))
 
-
 @lru_cache(maxsize=1)
 def load_metadata():
 
@@ -98,7 +78,6 @@ def load_metadata():
 
     return df.reset_index(drop=True)
 
-
 @lru_cache(maxsize=1)
 def load_embeddings():
     if not EMBED_PATH.exists():
@@ -107,10 +86,6 @@ def load_embeddings():
     logger.info("Loading embeddings...")
     return np.load(str(EMBED_PATH))
 
-
-# =====================================================
-# Core Result Builder
-# =====================================================
 def build_results(
     df: pd.DataFrame,
     ids,
@@ -133,8 +108,7 @@ def build_results(
         final_score = float(score)
 
         # ---------------------------------------------
-        # Keyword Boosting
-        # ---------------------------------------------
+                # ---------------------------------------------
         if query_words:
 
             title_words = tokenize(row[TITLE_COL])
@@ -149,8 +123,7 @@ def build_results(
             if overlap > 0:
                 final_score += 0.02 * overlap
 
-        # cap score
-        final_score = min(final_score, 1.0)
+                final_score = min(final_score, 1.0)
 
         if final_score < min_score:
             continue
@@ -174,10 +147,6 @@ def build_results(
         .reset_index(drop=True)
     )
 
-
-# =====================================================
-# Search by Free Text
-# =====================================================
 def search_by_text(
     query_text: str,
     k: int = TOP_K,
@@ -206,10 +175,6 @@ def search_by_text(
         min_score=min_score
     )
 
-
-# =====================================================
-# Search Similar to Existing Project
-# =====================================================
 def search_by_project_id(
     project_id: int,
     k: int = TOP_K,
@@ -270,10 +235,6 @@ def search_by_project_id(
 
     return pd.DataFrame(rows)
 
-
-# =====================================================
-# Compare Two Ideas
-# =====================================================
 def compare_two_ideas(
     text_a: str,
     text_b: str
@@ -293,33 +254,3 @@ def compare_two_ideas(
     score = float(np.dot(vecs[0], vecs[1]))
 
     return round(score, 4)
-
-
-# =====================================================
-# Example Run
-# =====================================================
-if __name__ == "__main__":
-
-    print("\n=== Search by Text ===")
-    print(
-        search_by_text(
-            "mobile app for expense tracking using flutter",
-            k=5
-        )
-    )
-
-    print("\n=== Similar Projects ===")
-    print(
-        search_by_project_id(
-            project_id=0,
-            k=5
-        )
-    )
-
-    print("\n=== Compare Two Ideas ===")
-    print(
-        compare_two_ideas(
-            "AI Medical Chatbot",
-            "Healthcare Assistant with AI"
-        )
-    )