How do you ensure the correct embedding function is used when reopening a persistent ChromaDB collection?

ChromaDB stores document text and vectors persistently, but it does not store which embedding function was used. When you reopen a PersistentClient, you must re-supply the same embedding function to the collection — otherwise ChromaDB may default to a different model, producing embedding mismatches.

import chromadb
from chromadb.utils import embedding_functions
import os

DB_PATH = "./persistent_ef_demo"

# === SESSION 1: Create and populate collection ===
client1 = chromadb.PersistentClient(path=DB_PATH)
ef_openai = embedding_functions.OpenAIEmbeddingFunction(
    api_key=os.environ["OPENAI_API_KEY"],
    model_name="text-embedding-3-small",
)
col1 = client1.get_or_create_collection(
    name="my_docs",
    embedding_function=ef_openai,                   # set the EF
    metadata={"hnsw:space": "cosine",
              "embedding_model": "text-embedding-3-small"},  # document it
)
col1.add(documents=["ChromaDB is great"], ids=["d1"])
print("Session 1 done, process exits...")
del client1, col1

# === SESSION 2: Reopen — MUST re-supply the same embedding function ===
client2 = chromadb.PersistentClient(path=DB_PATH)

# WRONG: ChromaDB defaults to all-MiniLM-L6-v2 (384-dim)
# Querying with a different model produces wrong results!
# col_wrong = client2.get_collection("my_docs")  # DO NOT DO THIS

# CORRECT: Re-supply the exact same embedding function
ef_openai_v2 = embedding_functions.OpenAIEmbeddingFunction(
    api_key=os.environ["OPENAI_API_KEY"],
    model_name="text-embedding-3-small",  # must match session 1
)
col2 = client2.get_collection(
    name="my_docs",
    embedding_function=ef_openai_v2,  # required!
)
results = col2.query(query_texts=["vector databases"], n_results=1)
print(results["documents"])  # correct result

# TIP: Read model name from collection metadata to avoid hardcoding
saved_model = col2.metadata.get("embedding_model", "all-MiniLM-L6-v2")
print(f"Using model: {saved_model}")