Add train_dataset.py

train_dataset.py

@@ -0,0 +1,17 @@
+from langchain_community.embeddings.sentence_transformer import (
+    SentenceTransformerEmbeddings,
+)
+from langchain_community.vectorstores import Chroma
+
+# create the open-source embedding function
+embedding_function = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+
+# load Chroma
+db = Chroma(embedding_function=embedding_function, persist_directory="./chroma_db")
+
+print("There are", db._collection.count(), " docs in the collection")
+
+docs = db._collection.peek(10)
+
+for doc in docs['documents']:
+  print(doc)