Update ingest_data.py

ingest_data.py

@@ -18,12 +18,12 @@ underlying_embeddings = OpenAIEmbeddings(api_key=openai_api_key)
 
 def download_data_and_create_embedding():
   # Download an IMDB datset from Hugging Face Hub, load the ShubhamChoksi/IMDB_Movies dataset
-  dataset = load_dataset("ShubhamChoksi/IMDB_Movies")
-  print(dataset)
+  # dataset = load_dataset("ShubhamChoksi/IMDB_Movies")
+  # print(dataset)
 
   # store imdb.csv from ShubhamChoksi/IMDB_Movies
-  dataset_dict = dataset
-  dataset_dict["train"].to_csv("imdb.csv")
+  # dataset_dict = dataset
+  # dataset_dict["train"].to_csv("imdb.csv")
 
   # load the csv file exported into a document
   loader = CSVLoader("imdb.csv")  # TODO
@@ -85,20 +85,4 @@ def download_data_and_create_embedding():
   # save our vector store locally
   vector_store.save_local("faiss_index")
 
-  query_embedding(vector_store=vector_store)
-
   return vector_store
-
-def query_embedding(vector_store) -> None:
-    # Ask your RAG system a question!
-    query = "What are some good sci-fi movies from the 1980s?"
-
-    # embed our query
-    embedded_query = underlying_embeddings.embed_query(query)
-    similar_documents = vector_store.similarity_search_by_vector(
-        embedded_query
-    )  # TODO: How do we do a similarity search to find documents similar to our query?
-
-    for page in similar_documents:
-        # Print the similar documents that the similarity search returns?
-        print(page.page_content)