RECENT POSTS

Multimodal Embeddings

Multimodal embedding models are designed to process and relate information from different data types, such as text, images, audio, and video. The main goal is to create vector representations, generally in a shared space, allowing semantically related information to be represented close to each other, regardless of their original modality. This ability to relate information…

RAG: Pre-Filtering

In real-world applications, semantic similarity search alone is not always sufficient to meet information retrieval requirements. Beyond semantic relevance, results often need to satisfy specific constraints, such as belonging to a particular category or excluding certain values. When performing similarity search across the entire dataset, the retrieved results may be semantically relevant to the query…

Vector Databases: HNSW Algorithm

To perform a search in a vector database containing millions or even billions of high-dimensional vectors, it would be necessary to compute the similarity between the query vector and every stored vector and then return the top-k nearest vectors. This approach is known as exact search and, although it guarantees exact results, it becomes computationally…