Final QA (#457)

Author: gahjelle

embeddings-and-vector-databases-with-chromadb/README.md

@@ -1,6 +1,6 @@
 # Embeddings and Vector Databases With ChromaDB
 
-Supporting code for the Real Python tutorial [Embeddings and Vector Databases With ChromaDB](https://realpython.com/embeddings-and-vector-databases-with-chromadb/). 
+Supporting code for the Real Python tutorial [Embeddings and Vector Databases With ChromaDB](https://realpython.com/chromadb-vector-database/). 
 
 To run the code in this tutorial, you should have `numpy`, `spacy`, `sentence-transformers`, `chromadb`, `polars`, `more-itertools`,  and `openai` installed in your environment. 
 

embeddings-and-vector-databases-with-chromadb/car_data_etl.py

@@ -57,6 +57,4 @@ def prepare_car_reviews_data(
     documents = car_review_db_data["Review"].to_list()
     metadatas = car_review_db_data.drop("Review").to_dicts()
 
-    chroma_data = {"ids": ids, "documents": documents, "metadatas": metadatas}
-
-    return chroma_data
+    return {"ids": ids, "documents": documents, "metadatas": metadatas}

embeddings-and-vector-databases-with-chromadb/chroma_utils.py

@@ -8,7 +8,7 @@
 def build_chroma_collection(
     chroma_path: pathlib.Path,
     collection_name: str,
-    embbeding_func_name: str,
+    embedding_func_name: str,
     ids: list[str],
     documents: list[str],
     metadatas: list[dict],
@@ -19,7 +19,7 @@ def build_chroma_collection(
     chroma_client = chromadb.PersistentClient(chroma_path)
 
     embedding_func = embedding_functions.SentenceTransformerEmbeddingFunction(
-        model_name=embbeding_func_name
+        model_name=embedding_func_name
     )
 
     collection = chroma_client.create_collection(

embeddings-and-vector-databases-with-chromadb/cosine_similarity.py

@@ -4,4 +4,4 @@
 def compute_cosine_similarity(u: np.ndarray, v: np.ndarray) -> float:
     """Compute the cosine similarity between two vectors"""
 
-    return u.dot(v) / (np.linalg.norm(u) * np.linalg.norm(v))
+    return (u @ v) / (np.linalg.norm(u) * np.linalg.norm(v))

embeddings-and-vector-databases-with-chromadb/intro_to_vectors.py

@@ -20,4 +20,4 @@
 
 # Dot product
 print(np.sum(v1 * v2))
-print(v1.dot(v3))
+print(v1 @ v3)