Skip to Content
ConceptsObjects

Objects

Objects are the fundamental data units stored in a collection. Each object has a unique ID, an embedding array, and optional metadata and filter fields.

Dense Object Fields

FieldRequiredDescription
IDYesUnique string identifier for the object
VectorYesDense embedding array (must match the collection dimension)
MetaNoArbitrary metadata object (returned in query results)
FilterNoKey-value pairs used to filter results during queries

meta vs filter: Use meta for data you want returned with results (titles, URLs, display text). Use filter for fields you intend to query against — any field not declared in filter at upsert time cannot be used in a filter expression later.

collection = client.get_collection(name="my_collection") collection.upsert([ { "id": "doc1", "vector": [0.12, -0.34, 0.89, ...], "meta": {"title": "Introduction to ML"}, "filter": {"category": "tech", "year": 2024} }, { "id": "doc2", "vector": [0.55, 0.21, -0.10, ...], "meta": {"title": "Deep Learning Basics"}, "filter": {"category": "tech", "year": 2023} } ])

BM25 sparse vectors are generated from text using term-frequency weighting. Endee’s endee-model library handles this automatically. See the Sparse Vectors (BM25) guide for setup and usage.

Hybrid Object Fields

For hybrid collections, include sparse vector field components alongside the dense vector field:

FieldRequiredDescription
Sparse IndicesYesNon-zero term positions in the sparse vector
Sparse ValuesYesBM25 weights corresponding to each index position
collection.upsert([ { "id": "doc1", "vector": [0.12, -0.34, 0.89, ...], "sparse_indices": [4821, 19043, 73201], "sparse_values": [1.42, 0.87, 1.15], "meta": {"title": "Introduction to ML"} } ])

Sparse fields and sparse_model

sparse_indices and sparse_values must have the same length — each position in sparse_indices maps to the weight at the same position in sparse_values. The sparse_model you set at collection creation controls how Endee interprets these values: use endee_bm25 to send TF weights only (Endee applies IDF server-side), or default to send final scores as-is for SPLADE or custom BM25 models.

Maximum batch size is 10,000 objects per upsert call.

Precision

The precision parameter controls how objects are stored internally. Lower precision reduces memory and speeds up search at the cost of some accuracy.

PrecisionBitsStorageSpeedAccuracy
BINARY1-bitSmallestFastestLower
INT88-bitSmallFastGood
INT1616-bit integerMediumMediumHigher
FLOAT1616-bit floatMediumMediumHigh
FLOAT3232-bit floatLargestSlowerHighest
from endee import Precision # INT16 — recommended for most use cases client.create_collection(name="my_collection", dimension=384, space_type="cosine", precision=Precision.INT16) # FLOAT32 — maximum accuracy client.create_collection(name="precise_collection", dimension=384, space_type="cosine", precision=Precision.FLOAT32) # BINARY — minimum memory client.create_collection(name="large_collection", dimension=384, space_type="cosine", precision=Precision.BINARY)

Recommendations:

  • INT16: best balance of speed, memory, and accuracy for most use cases (recommended)
  • INT8: faster than INT16 with slightly lower accuracy; good for latency-sensitive workloads (default)
  • FLOAT32: use when maximum recall accuracy is critical and memory is not a concern
  • BINARY: use for very large collections where memory is the primary constraint

Precision is set at collection creation time and cannot be changed without recreating the collection.


Get Object by ID

Retrieve a single object and its metadata by ID.

obj = collection.get_object("doc1")

Delete Object by ID

Deletion is irreversible.

collection.delete_object("doc1")

Delete Objects by Filter

Delete all objects matching specific filter conditions.

collection.delete_with_filter([/* filter expression */]) e.g: collection.delete_with_filter([{"tags": {"$eq": "important"}}])

For filter expression , see Filtering: Operators.