Update app.py

app.py

@@ -1,3 +1,6 @@
+# Author : Justin 
+# Program : Vectorizer for Hybrid Search
+# Instructions : Check README.md
 import torch
 from fastapi import FastAPI
 from pydantic import BaseModel
@@ -32,7 +35,7 @@ splade_model = None
 app = FastAPI(
     title="Hybrid Vector Generation API",
     description="An API to generate dense and sparse vectors for a given text query.",
-    version="1.0.0"
+    version="1.2.0"
 )
 
 # --- Pydantic Models for API ---
@@ -46,7 +49,7 @@ class SparseVectorResponse(BaseModel):
     values: list[float]
 
 class VectorResponse(BaseModel):
-    """The final JSON response model containing both vectors."""
+    """Final JSON response model containing both vectors."""
     dense_vector: list[float]
     sparse_vector: SparseVectorResponse
 
@@ -64,10 +67,10 @@ async def load_models():
         dense_model = SentenceTransformer(DENSE_MODEL_ID, device=DEVICE)
         splade_tokenizer = AutoTokenizer.from_pretrained(SPLADE_QUERY_MODEL_ID)
         splade_model = AutoModelForMaskedLM.from_pretrained(SPLADE_QUERY_MODEL_ID).to(DEVICE)
-        logger.info("Great news! All models have been loaded successfully.")
+        logger.info("YAaay! All models have been loaded successfully.")
     except Exception as e:
         logger.critical(f"Oh no, a critical error occurred while loading models: {e}", exc_info=True)
-        # In a real-world scenario, you might want the app to fail startup if models don't load.
+        # In a real-world scenario, you might want the app to fail startup if models don't load
         raise e
 
 def compute_splade_vector(text: str) -> models.SparseVector:
@@ -119,7 +122,7 @@ async def vectorize_query(request: QueryRequest):
     logger.info(f"The incoming search query from n8n is: '{request.query_text}'")
     
     # 1. Generate Dense Vector
-    logger.info("First, I'm generating the dense vector for semantic meaning...")
+    logger.info("First, generating the dense vector for semantic meaning...")
     dense_query_vector = dense_model.encode(request.query_text).tolist()
     logger.info("Done with the dense vector. It has %d dimensions.", len(dense_query_vector))
     logger.info("Here's a small sample of the dense vector: %s...", str(dense_query_vector[:4]))
@@ -131,8 +134,8 @@ async def vectorize_query(request: QueryRequest):
     logger.info("Here's a sample of the sparse vector indices: %s...", str(sparse_query_vector.indices[:4]))
 
     # 3. Construct and return the response
-    logger.info("Everything looks good. I'm packaging up the vectors to send back.")
-    logger.info("=========================================================")
+    logger.info("Everything looks good. Packaging up the vectors to send back.")
+    logger.info("-----------------------------------------------------------------")
     
     final_response = VectorResponse(
         dense_vector=dense_query_vector,