Qdrant Hybrid Search Prefetches

Different Searches in One Query API Request

Each prefetch runs exactly one search per one query.

Understand if user wants to run several parallel searches on:

1. The same vector representations but different queries or filters.
2. Different vector representations but the same raw query.

If first, help user to design logic of constructing query or/and filters on application side and then check Combining Searches. Don't forget to create indices on filterable payload fields, immediately after collection creation, prior to building HNSW, so filterable HNSW could be constructed.

If second, use named vectors, which allow to store multiple vector types per point in one collection. On Qdrant 1.18 or newer, named vectors can be added to or removed from an existing collection without recreating it Update vector schema; on 1.17 or older, they can be configured only at collection creation. To choose vectors, check following recommendations.

Missed Keyword Matches

Use when: pure vector search misses exact term or keyword matches and you need lexical retrieval alongside semantic search.

Most likely you need a sparse vector for exact text search alongside the dense one. Qdrant uses sparse vectors for lexical searches, as payload filtering doesn't provide any ranking score.

Choose a Sparse Vector for Text

• BM25 statistical representations, built into Qdrant core (computed server-side). Good baseline, works out-of-domain, usually for long texts. Can be used for non-English content, but needs to be configured per language (tokenization, stemming, stopwords, etc) at indexing and retrieval time. More in Text Search Guide
• BM42 learned sparse, based on BM25, but better for small chunks of text & with meaning understanding. Works only on English. Requires fine-tuning for domain-specific retrieval. Requires FastEmbed (Python/REST only, not available in all SDKs). Not maintained.
• miniCOIL learned sparse, BM25 with additional understanding of words meaning in context. Works only on English. Requires fine-tuning for domain-specific retrieval. Requires FastEmbed. Usage shown in FastEmbed miniCOIL documentation.
• SPLADE++ learned sparse with term expansion. Heavier inference and resources usage but better performance due to term expansion. Requires fine-tuning for domain-specific retrieval. Provided in Qdrant Cloud Inference and FastEmbed versions work only on English. To use with FastEmbed, check FastEmbed SPLADE documentation.
• External learned sparse embeddings, for example BAAI/bge-m3.

What to remember when using sparse vectors for lexical search:

• tokenization and stemming affect exact matches, especially on custom codes, terms, etc.
• IDF statistics are computed over a corpus. On Qdrant 1.18 and older that corpus is the data in the whole shard being queried, which distorts scoring in multi-tenant collections: tenants with different vocabularies get merged into one statistic, so a term's IDF no longer reflects how rare it is inside either tenant's data. On 1.19+ you can narrow the corpus the statistics are computed over down to a single tenant, so IDF reflects term rarity within that tenant. See Per-tenant IDF statistics.

What to remember when using Qdrant BM25 and miniCOIL (based on BM25):

• avg_len in formula is not computed server-side, it is a user responsibility and passed as a parameter. Calibrate per field — defaults assume document-length text; short fields (titles, tags) need a much smaller value or BM25 scoring is skewed (avg_len=256 against a 10-word title overweights term frequency).
• BM25 might be not good for small chunks of text, as BM25 algorithm was initially created for search on long documents; consider adjusting document statistics in sparse vectors (TF & IDF, k, b).
• Qdrant BM25 vectors are configured per language, so consider customizing stop words, stemming & tokenization when users documents mix several languages or carefully configure vectors per point when they are monolingual. To disable text processing entirely for language-neutral content: on Qdrant 1.19 or newer, use stemmer: {"type": "none"} plus an empty stopwords set explicitly (by default, BM25 applies English stemming and stopword removal); on 1.18 or older, use language: none (deprecated as of 1.19).

More on Sparse Vectors for Text Search