Update ChromaDB tutorial materials for ChromaDB 1.5 and openai 3.x

[realpython-bot]

Supporting code for the full update of Embeddings and Vector Databases With ChromaDB (CMS update draft: Post 2390, Trello card https://trello.com/c/e5bIvapv).

Changes

• Pin all dependencies to the tested versions: chromadb 1.5.9, spacy 3.8.16, sentence-transformers 6.0.1, polars 1.44.2, openai 3.14.0, numpy 2.5.3, python-dotenv 1.2.3 (Python 3.12+, tested on 3.14).
• chroma_utils.py: use configuration={"hnsw": {"space": ...}} instead of the old metadata={"hnsw:space": ...}, read the batch size from client.get_max_batch_size(), and fix the off-by-one (end_idx = batch[-1] + 1) that dropped the last document of every batch. Use itertools.batched() instead of more-itertools.
• car_data_etl.py: schema_overrides= (the dtypes= argument is deprecated in Polars 1.x) and maintain_order=True so the printed example review is reproducible.
• create_car_review_collection.py: load the collection through its persisted embedding-function configuration and print collection.count().
• llm_car_review_context.py: replace the removed openai.ChatCompletion interface with the OpenAI() client and the Responses API; load OPENAI_API_KEY from .env with python-dotenv (drops config.json).
• word_vectors.py: use en_core_web_lg, because the 3.8 medium model prunes its vectors so that dog and cat share one vector.
• README: updated title, install steps, and .env instructions.

Testing

All scripts ran end to end on Python 3.14 with the pinned versions, including the full 5,870-review collection build and live OpenAI calls. The outputs match the updated tutorial draft.

🤖 Generated with Claude Code