Understand the distributed architecture that executes the retrieval workflow. Here you'll find the core platform components that power retrieval, ranking, machine learning inference, and real-time serving.
Use the left and right arrows to browse the platform components below. Each section provides a high-level summary and links to a Technical Deep Dive for a more detailed architectural explanation.
Explore:
- Unified Data Model
- Distributed Serving
- Retrieval Pipeline
- Multi-phase Ranking
- Machine Learning Inference
- Real-Time Updates
Unified Data Model
Vespa brings structured data, full text, vectors, and tensors together into a single document model. Rather than storing different data types in separate systems and combining results later, applications can model, index, and retrieve them through a single schema and query pipeline.
This unified approach simplifies application architecture while enabling lexical search, semantic retrieval, filtering, ranking, and machine learning to work together over the same data.
Distributed Serving
Vespa distributes data across independent content nodes and executes retrieval, ranking, and machine learning inference where the data already resides. Rather than moving large volumes of data across the network for processing, queries are executed locally before results are combined into a final response. This minimizes network overhead while delivering high throughput, predictable latency, and efficient resource utilization as applications scale.
This shared-nothing architecture enables parallel query execution, local model inference, and linear scalability, making Vespa well-suited for large-scale AI applications where retrieval quality, response time, and availability directly affect user experience and business outcomes.
Retrieval Pipeline
Vespa supports a flexible retrieval pipeline that combines multiple retrieval techniques within a single query. Rather than relying on a single search method, applications can combine lexical search, vector search, metadata filtering, structured retrieval, and chunk-level passage retrieval to identify the most relevant information for each request.
AI search often retrieves passages rather than entire documents. Vespa supports chunking strategies that index documents as smaller, searchable passages, allowing retrieval and ranking to focus on the most relevant content while preserving links to the original document. This improves grounding, reduces unnecessary context, and helps AI applications generate more accurate responses.
This unified pipeline enables hybrid search, RAG, recommendations, conversational AI, and personalized search without requiring multiple retrieval systems. Queries progressively refine candidate sets before passing them to the ranking stages, balancing retrieval quality with efficiency and latency.
Multi-Phase Ranking
Retrieval identifies candidate documents. Ranking determines which of those candidates are most relevant. Vespa uses a multi-phase ranking pipeline that progressively applies increasingly sophisticated ranking models, allowing applications to improve relevance while controlling computational cost and query latency.
Each ranking stage can combine lexical signals, semantic similarity, business rules, personalization, and machine learning models, ensuring that expensive computations are performed only on the most promising candidates.
Machine Learning Inference
Vespa executes machine learning models directly within the retrieval pipeline, allowing inference to occur alongside retrieval and ranking rather than through separate model-serving infrastructure. This enables applications to enrich queries, rerank results, and execute machine learning inference without introducing additional network hops.
Vespa supports industry-standard model formats such as ONNX, as well as XGBoost models, custom ranking functions, and transformer-based rerankers, including cross-encoders. Executing inference close to the data reduces latency while simplifying the overall AI architecture.
Real-Time Updates
Modern AI applications depend on continuously changing information, from new documents and inventory changes to user interactions and behavioral signals. Vespa is designed for real-time serving, making newly ingested content and updates searchable almost immediately while maintaining predictable low-latency query performance.
Support for partial document updates enables individual fields to be modified without rebuilding entire documents, while the distributed architecture efficiently handles high ingestion rates alongside query traffic. This allows applications to maintain fresh retrieval results even as data changes continuously.
