The Qdrant Output Connector

Qdrant, the Rust-based vector database, has been integrated into OpenCrawling's event-driven microservice architecture via a new Qdrant Output Connector that enables sub-millisecond ACL pre-filtering for enterprise RAG, ensuring users only retrieve documents they have explicit rights to see. The connector, which uses the gRPC Java SDK over port 6334, automatically provisions collections and creates KEYWORD payload indexes on security fields such as security_allowed_read and security_denied_read, and is configurable via Spring Boot YAML properties or environment variables.

01. Why Qdrant for Enterprise Vector Search? As AI applications expand across enterprise ecosystems, vector storage demands extreme query throughput, low memory footprint, and strict security guarantees. While vector databases excel at similarity search, enterprise content repositories like SharePoint, Alfresco, and Iceberg require document-level Access Control Lists ACLs to ensure users only retrieve information they have explicit rights to see. Qdrant is engineered in Rust with SIMD hardware acceleration, making it one of the fastest vector engines in existence. But what truly sets Qdrant apart for enterprise RAG is its Payload Index Engine . By supporting KEYWORD payload indexes directly alongside vector points, Qdrant allows filtering by payload attributes such as user security SIDs before distance calculations occur, preventing security leaks without sacrificing search performance. Sub-Millisecond ACL Pre-Filtering: Qdrant's payload index allows OpenCrawling's McpVectorServer to inject document ACL filters directly into similarity queries, ensuring zero unauthorized vector returns. 02. Architecture & Decoupled Data Flow The oc-qdrant-output-connector integrates directly into OpenCrawling's event-driven decoupled microservice architecture: Qdrant Output Connector gRPC Repository Ingestion: Repository connectors Filesystem, Alfresco, Flowable, Camunda, S3 discover documents and publish lightweight claim-check messages to Kafka. Text Extraction & Chunking: IngestionConsumer extracts clean text via Apache Tika and generates chunked payloads with associated document ACL security SIDs. Scalable Embedding: oc-embedding-service dynamically computes vector embeddings via Ollama or OpenAI and pushes embedded chunks to Kafka. High-Speed Binary Upsert: QdrantStoreWriterConsumer receives the embedded chunks and uses the gRPC Java SDK io.qdrant:client to upsert PointStruct batches into Qdrant over port 6334 . 03. Automated Collection Provisioning & Payload ACL Indexing Upon startup, QdrantCollectionInitializer verifies whether the configured target collection e.g. enterprise kb exists. If not, it automatically provisions the collection with the desired vector dimensions and distance metric COSINE , DOT , or EUCLID . Simultaneously, the connector creates KEYWORD payload indexes on the security payload fields: security allowed read : List of user/group SIDs permitted to access the document. security denied read : Explicit deny SIDs taking precedence over allow rules. // Example Qdrant Point Payload Structure generated by oc-qdrant-output-connector { "id": "c8a912e4-712d-4b92-b2fa-1092a9f1a091", "vector": 0.0142, -0.0521, 0.0892, ... , "payload": { "text": "Enterprise quarterly financial report and forecasts...", "uri": "file:///data/finance/q3 report.pdf", "security allowed read": "ROLE FINANCE", "USER S-1-5-21-3623811015" , "security denied read": "ROLE EXTERN" , "lastModified": "2026-07-29T18:00:00Z" } } 04. Configuration & Deployment The Qdrant Output Connector is fully configurable via standard Spring Boot YAML properties or environment variables: | Property | Environment Variable | Default | Description | |---|---|---|---| spring.opencrawling.output.qdrant.host | SPRING OPENCRAWLING OUTPUT QDRANT HOST | localhost | Hostname of self-hosted Qdrant or Qdrant Cloud instance | spring.opencrawling.output.qdrant.port | SPRING OPENCRAWLING OUTPUT QDRANT PORT | 6334 | High-performance gRPC port default: 6334 | spring.opencrawling.output.qdrant.api-key | SPRING OPENCRAWLING OUTPUT QDRANT API KEY | "" | Optional API key for Qdrant Cloud or Enterprise cluster | spring.opencrawling.output.qdrant.collection-name | SPRING OPENCRAWLING OUTPUT QDRANT COLLECTION NAME | enterprise kb | Target Qdrant vector collection name | spring.opencrawling.output.qdrant.dimensions | SPRING OPENCRAWLING OUTPUT QDRANT DIMENSIONS | 1024 | Vector dimension size e.g. 1024 for mxbai-embed-large | spring.opencrawling.output.qdrant.distance | SPRING OPENCRAWLING OUTPUT QDRANT DISTANCE | COSINE | Vector distance metric COSINE , DOT , EUCLID | spring.opencrawling.output.qdrant.quantization | SPRING OPENCRAWLING OUTPUT QDRANT QUANTIZATION | NONE | Quantization mode NONE , SCALAR , BINARY | Automated Integration Test: You can test the end-to-end Qdrant pipeline locally with one command: ./scripts/test-qdrant-decoupled.sh . The script spins up Qdrant, Ollama, Kafka, and OpenCrawling microservices, injects a test document, and verifies point count in Qdrant. 05. Get Started Today The Qdrant Output Connector is available starting in OpenCrawling 1.0.0-SNAPSHOT . Check out the documentation or run the Docker Compose environment to start building secure, low-latency RAG pipelines with Qdrant Ready to Supercharge Your RAG Architecture with Qdrant? Explore the source code on GitHub, read the Wiki configuration guide, or join our community discussions.