Collections and indexes

Collection declarations make vector topology reviewable alongside the queries that use it. Define vectors first, add payload indexes for fields you filter or order by, and add shard keys only when Qdrant routing is part of the design.

Model the vector topology

Vector names are application-defined. dense, sparse, and colbert are useful conventions, but vector configuration determines the actual role. A dense definition is name VECTOR(size, distance) with distance COSINE, DOT, EUCLID, or MANHATTAN; a sparse definition is name SPARSE with optional WITH SPARSE (...) / WITH INDEX (...) config.

QQLDense, sparse, and multivector topologyTry in playground↗

CREATE COLLECTION research (
  dense VECTOR(384, COSINE),
  sparse SPARSE,
  colbert VECTOR(128, COSINE)
    WITH MULTIVECTOR (comparator = 'max_sim')
    WITH HNSW (m = 0)
)
WITH HNSW (
  m = 16,
  ef_construct = 100
);

Requirement	Schema choice
Semantic retrieval	A dense VECTOR(size, distance)
Lexical or sparse retrieval	A named SPARSE vector
Late interaction	A multivector with a comparator
Hybrid retrieval	Both a dense and sparse vector

Collection modes

A CREATE COLLECTION can name a mode instead of (or alongside) explicit vector definitions. Modes infer a conventional topology:

Mode	Resulting topology
(no mode)	Bare dense topology without a model hint
USING DENSE MODEL 'name'	Dense topology with dimension inference from the model
USING HYBRID	Conventional hybrid dense + sparse topology
HYBRID RERANK	Conventional rerank topology
HYBRID DENSE VECTOR semantic_v2 SPARSE VECTOR lexical_v2	Hybrid topology with arbitrary role names

Explicit dense and sparse vector definitions may coexist with the collection blocks below. Dense size must be positive.

Collection configuration blocks

Config blocks attach to the collection with WITH <BLOCK> (...) and to individual dense vectors (WITH HNSW, WITH VECTOR, WITH QUANTIZATION, WITH MULTIVECTOR). Keys are ASCII case-insensitive and unique.

Block	Accepted keys
HNSW	m, ef_construct, full_scan_threshold, max_indexing_threads, on_disk, payload_m, inline_storage
VECTOR	on_disk
OPTIMIZERS	deleted_threshold, vacuum_min_vector_number, default_segment_number, max_segment_size, memmap_threshold, indexing_threshold, flush_interval_sec, max_optimization_threads, prevent_unoptimized
PARAMS	replication_factor, write_consistency_factor, on_disk_payload, shard_number, sharding_method, shard_keys
QUANTIZATION	type (scalar/binary/product/turbo), disabled, always_ram, quantile, bits, compression, encoding, query_encoding
MULTIVECTOR	comparator (max_sim)
sparse INDEX/SPARSE	modifier, full_scan_threshold, on_disk, datatype

read_fan_out_factor and read_fan_out_delay_ms are ALTER-only PARAMS keys, and QUANTIZATION (disabled = true) is an ALTER form. ALTER COLLECTION applies any of the HNSW, VECTOR, OPTIMIZERS, PARAMS, or QUANTIZATION blocks to an existing collection.

QQLReplication, quantization, and alterTry in playground↗

CREATE COLLECTION sec10k (
  dense VECTOR(768, COSINE),
  sparse SPARSE
) WITH HNSW (m = 16, ef_construct = 100)
WITH PARAMS (
  replication_factor = 2,
  shard_number = 8,
  sharding_method = 'custom',
  shard_keys = ['honeywell', 'ge']
);

ALTER COLLECTION sec10k WITH QUANTIZATION (type = 'scalar');

Index the filter paths you use

Create payload indexes for fields used frequently in filters, tenant predicates, or ordering. Index design is a Qdrant performance decision, not a requirement for every payload field. The index TYPE is keyword, integer, float, geo, text, bool, datetime, or uuid.

QQLTenant and text payload indexesTry in playground↗

CREATE INDEX ON COLLECTION research
FOR tenant_id
TYPE keyword
WITH (
  is_tenant = true,
  on_disk = true
);

CREATE INDEX ON COLLECTION research
FOR content
TYPE text
WITH (
  tokenizer = 'multilingual',
  lowercase = true,
  phrase_matching = true
);

CREATE INDEX ... WITH (...) accepts the following options:

Option	Type
is_tenant, on_disk, enable_hnsw	boolean
lowercase, ascii_folding, phrase_matching, lookup, range, is_principal	boolean
min_token_len, max_token_len	non-negative integer
tokenizer	string
stemmer	string
stopwords	string list

DROP INDEX ON COLLECTION research FOR field removes an index.

Inspect resources with SHOW

SHOW has exactly three forms — there is no SHOW INDEXES.

Statement	Returns
SHOW COLLECTIONS;	All collection names
SHOW COLLECTION name;	A single collection's configuration
SHOW SHARD KEYS ON COLLECTION name;	The custom shard keys of a collection

Route a collection with custom shard keys

Shard-key DDL creates and manages routing partitions. It is separate from the tenant predicate your service must enforce.

QQLManage a custom shard keyTry in playground↗

CREATE SHARD KEY 'acme'
ON COLLECTION research
WITH (shards_number = 2);

SHOW SHARD KEYS
ON COLLECTION research;

DROP SHARD KEY 'acme'
ON COLLECTION research;

Remote-backend capability

Shard-key DDL is a Qdrant remote-backend capability. The in-process edge backend does not support shard keys, ALTER COLLECTION, or grouped queries.

Next: Data operations and Multitenancy.