Back to directory

QQL — Qdrant Query Language

A SQL-like query language and command-line shell for the Qdrant vector database, letting a developer write insert, search and filter statements instead of calling the Qdrant Python client directly.

QQL — Qdrant Query Language

QQL is a translation layer between a SQL-like language and the Qdrant Python client. Statements such as INSERT, SELECT, SEARCH, SCROLL, RECOMMEND, UPDATE, DELETE and CREATE COLLECTION are tokenized by a lexer, parsed into a typed AST, and mapped by an executor onto the corresponding Qdrant client call.

It supports hybrid dense and sparse vector search, with a dense vector generated automatically through Fastembed on insert and, in hybrid mode, a sparse BM25 vector generated alongside it; searches merge the two retrieval methods using reciprocal rank fusion by default, or a distribution-based score fusion method. Other supported features include grouped search, cross-encoder reranking, scalar, turbo, binary and product quantization, SQL-style WHERE filters, and collection dump and restore.

Beyond the interactive shell, QQL exposes a programmatic Python API for use inside an application without the CLI. It requires Python 3.12 or newer and a running Qdrant instance, installs from PyPI, and is MIT licensed.

More in RAG

See all 540
  • ai·rete·rag

    ai-rete-rag.com

    A platform that pairs a Rete rule engine with retrieval-augmented generation, so deterministic rules decide an outcome and grounded retrieval explains the decision in plain language.

  • Xtriever

    github.com

    A hybrid retrieval engine for retrieval-augmented generation, written in Rust to run on-device on a phone or a laptop, combining lexical BM25 search, dense embedding search, reciprocal-rank fusion and cross-encoder re-ranking with no server.

  • FileFlux

    github.com

    A .NET library that turns PDF, DOCX, HWP and other documents into optimized chunks for RAG systems, through a five-stage pipeline built on high-performance Rust FFI readers.