Simple Query Engine
vector-searchLlamaIndexvector-databaseretrieval-augmented-generationllm-frameworksfunction-callingsimple-query-engineweaviate-recipesintegrationsPythongenerative-aillm-agent-frameworks
Export
[ ]
[3]
[ ]
[5]
[6]
[7]
Number of nodes: 9 Node ID: 99fbe400-8ca8-4ed3-8ada-13bb9c428967 Text: title: What is Ref2Vec and why you need it for your recommendation system Weaviate 1.16 introduced the [Ref2Vec](/developers/weaviate/modules/retriever-vectorizer- modules/ref2vec-centroid) module. In this article, we give you an overview of what Ref2Vec is and some examples in which it can add value such as recommendations or representing long ...
[8]
[9]
The intersection between LLMs and search lies in the challenge of finding suitable representations for long objects, particularly text documents that exceed the input limit of Deep Transformer Neural Networks. This motivates the interest in Hybrid Search techniques that combine Vector Search with algorithms like BM25, which is well-suited for handling text sequences longer than 512 tokens. Ref2Vec can play a role in addressing this challenge by helping to represent long documents effectively in search applications.