qql-edge
Zero-network QQL executor. Combines qdrant-edge (in-process HNSW) with the
QQL runtime for fully local vector search — no external Qdrant, no network
hops, no API keys.
Three embedding strategies produce an [Executor] backed by [EdgeQdrant]:
| Constructor | Embedder | Use case |
|---|---|---|
local_executor() |
FastEmbedder (ONNX, default BGE small 384-d) |
Fully offline |
local_executor_with_options() |
FastEmbedder + model/cache selection |
Pick ONNX model |
http_executor() |
HttpEmbedder (OpenAI-compatible) |
Local model, remote API |
custom_executor() |
Any Arc<dyn Embedder> |
GPU, ensemble, caching |
list_embedding_models() |
— | Discover ONNX models + dims |
Quick start
use local_executor;
use OnError;
let mut executor = local_executor?;
let resp = executor.execute.await?;
let resp = executor.execute.await?;
let resp = executor.execute.await?;
executor.close.await?; // flush before deleting the data directory
EdgeQdrant backend
[EdgeQdrant] implements QdrantOps (the unified backend trait from qql-runtime)
using qdrant-edge's in-memory HNSW index. Collection data persists to disk at the
configured base_path.
Supported operations
The supported point, mutation, collection, index, query, and batch operations
use the same response envelope as REST and gRPC: { "result": ..., "status": "ok", "time": 0.0 }.
Unsupported clustered or server-only operations return an explicit
QqlError; they are never acknowledged as no-ops.
Response normalization
Mutations return:
Queries return normalized hit arrays with id, payload, and vector keys.
Batch operations return arrays under "result" — cardinality is verified
against the operation count.
Features
fastembed-local: ONNX-based local embedding viafastembed-rs(default)http-embedding: HTTP-based embedding viareqwest(forhttp_executor)
When neither feature is enabled, only custom_executor() is available.
fastembed-local supports Linux x86-64, Windows x86-64, and Apple Silicon
macOS. ONNX Runtime does not publish the required macOS Intel artifact, so
Intel Mac users should disable default features and use http-embedding or
custom_executor().
Boundaries
- No
UPDATE ... SET VECTORvia batch — uses individual route dispatch - gRPC is not available in edge mode (no protobuf dependency)
- Edge uses qdrant-edge's native query engine for nearest, sparse, MMR,
recommendation (
best_score/sum_scores), context, discover, sample, formula, relevance-feedback, and order-by queries; point-reference and text inputs that cannot be embedded locally are rejected - Shard keys are not supported in edge mode (no sharding in qdrant-edge)
GROUP BY,ALTER COLLECTION, collectionPARAMS, and shard DDL are rejected explicitly in edge mode- Recommendation's
average_vectorstrategy is not available in qdrant-edge; usebest_scoreorsum_scores
Verification
# Edge tests require the fastembed-local feature and ~1 GB model download
# HTTP executor only