Tutorials and use cases

Text search

• Tutorial: Text Search. A text search tutorial and introduction to text ranking with Vespa using traditional information retrieval techniques like BM25.
• Tutorial: Improving Text Search with Machine Learning. This tutorial builds on the text search tutorial but introduces Learning to Rank to improve relevance.

Vector Search

Learn how to use Vespa Vector Search in the practical nearest neighbor search guide. It uses Vespa's support for nearest neighbor search, there is also support for fast approximate nearest neighbor search in Vespa. The guide covers combining vector search with filters and how to perform hybrid search, combining retrieval over inverted index structures with vector search.

Hybrid Search

Tutorial: Hybrid Text Search. A search tutorial and introduction to hybrid text ranking with Vespa, combining BM25 with text embedding models.

RAG (Retrieval-Augmented Generation)

• Tutorial: The RAG Blueprint. A tutorial that provides a blueprint for building high-quality RAG applications with Vespa. Includes evaluation and learning-to-rank (LTR).
• Retrieval-augmented generation (RAG) in Vespa.

Combining search and recommendation: The News tutorial

Follow this series to learn how to build a complete application supporting both content recommendation/personalization, navigation, and search.

• News 1: Getting Started
• News 2: Application Packages, Feeding, Query
• News 3: Sorting, Grouping and Ranking
• News 4: Embeddings
• News 5: Partial Updates, ANNs, Filtering
• News 6: Custom Searchers, Document Processors
• News 7: Parent-Child, Tensor Ranking

ML Model Serving

Learn how to use Vespa for ML model serving in Stateless Model Evaluation. Vespa supports running inference with models from many popular ML frameworks, which can be used for ranking, query classification, question answering, multi-modal retrieval, and more.

• Ranking with ONNX models. Export models from popular deep learning frameworks such as PyTorch to ONNX format for serving in Vespa. Vespa integrates with ONNX-Runtime for accelerated inference. Many ML frameworks support exporting models to ONNX, including sklearn.
• Ranking with LightGBM models
• Ranking with XGBoost models
• Ranking with TensorFlow models

Embedding Model Inference

Vespa supports integrating embedding models, which avoids transferring large amounts of embedding vector data over the network and allows for efficient serving of embedding models.

• Huggingface Embedder Use single-vector embedding models from Hugging face
• ColBERT Embedder Use multi-vector embedding models
• Splade Embedder Use sparse learned single vector embedding models

E-Commerce

The e-commerce shopping sample application demonstrates Vespa grouping, true in-place partial updates, custom ranking, and more.

More examples and sample applications

There are many examples and starting applications on GitHub and Pyvespa examples.