By Brandon Miller
Search, make inferences in, and organize vectors, tensors, text and structured data, at serving time and any scale. A new release of Vespa is made from this repository's master branch every morning CET Monday through Thursday. This is hard to do, especially with large data sets that needs to be distributed over multiple nodes and evaluated in parallel. Use the following guide to set up a complete development environment using Docker for building Vespa, running unit tests and running system tests: Vespa development on AlmaLinux 8. Build Java modulesexport MAVEN_OPTS="-Xms128m -Xmx1024m" ./bootstrap.sh java mvn install --threads 1CUse this if you only need to build the Java modules, otherwise follow the complete development guide above.
Generative AILarge language models lack information that is recent, detailed, or private to a user or organization. That's why most generative AI systems combine the LLM with a component that surfaces the most useful information for the task at hand (RAG). By integrating vector, text and structured data search, machine-learned relevance models, and powerful tensor computations, Vespa lets you do this better than any other platform, and scale easily to any amount of data and traffic.
Vespa.ai - the open big data serving engine. Vespa.ai is used to make AI-driven decisions using big data, in real time, at any scale, with unbeatable performance. Organizations use vespa.ai to solve problems such as structured, text, and vector search, and real-time recommendation, personalization and targeting. The platform is open source under an Apache 2.0 license. It can be downloaded from vespa.ai, or used as a serverless managed service at cloud.vespa.ai.
Vespa sample applicationsFor operational sample applications, see examples/operations. Retrieval Augmented Generation (RAG)The retrieval-augmented-generation sample application demonstrates how to build an end-to-end RAG pipeline with API-based and local LLMs. Multilingual semantic searchThe multilingual sample application demonstrates multilingual semantic search with multilingual text embedding models. More advanced sample applicationsNews search and recommendation tutorialThe news sample application used in the Vespa tutorial. Contribute to the Vespa sample applications.
Featured ProductsSee for yourself how a graph database can make your life easier. Use Neo4j online for free. The database to transact, analyze and contextualize your data in real time. Vector database designed for GenAI, fully equipped for enterprise implementation. Try Managed Milvus for FreePresent your product here
