How do you control what data ChromaDB returns in query and get results using include?

Both query() and get() accept an include parameter — a list of strings specifying which fields to return. Omitting fields you don't need reduces network payload and memory, which matters for large result sets.

import chromadb

client = chromadb.Client()
col = client.create_collection("demo")
col.add(
    documents=["Alpha document", "Beta document", "Gamma document"],
    metadatas=[{"tag": "a"}, {"tag": "b"}, {"tag": "c"}],
    ids=["id1", "id2", "id3"],
)

# Default include: documents, metadatas, distances (for query)
# Default include for get(): documents, metadatas (no distances)
results = col.query(query_texts=["document"], n_results=2)
print(results.keys())
# dict_keys(["ids", "distances", "metadatas", "embeddings", "documents", "uris", "data"])
# embeddings, uris, data are None by default

# Only return IDs and distances — smallest possible response
results = col.query(
    query_texts=["alpha"],
    n_results=2,
    include=["distances"],  # ids are always returned
)
print(results["documents"])   # None
print(results["distances"])   # [[0.05, 0.72]]

# Include raw embedding vectors (large! use only when needed)
results = col.query(
    query_texts=["beta"],
    n_results=1,
    include=["documents", "metadatas", "distances", "embeddings"],
)
print(len(results["embeddings"][0][0]))  # 384 floats per vector

# get() include — embeddings must be explicitly requested
all_data = col.get(
    include=["documents", "metadatas", "embeddings"],
)
print(len(all_data["embeddings"]))  # 3

# get() without include — minimal response
ids_only = col.get()
print(ids_only["ids"])         # ["id1", "id2", "id3"]
print(ids_only["documents"])   # ["Alpha...", "Beta...", "Gamma..."]