Aspected Blog

Use Case: Intelligent Enterprise Document Retrieval with Aspected

Aran.Montero-Salvado@Xillio.com (Aran Montero Salvadó) — Thu, 30 Apr 2026 16:54:56 GMT

How context-aware retrieval helps enterprise AI find the right documents by combining content and context in a single representation.

TL;DR

Enterprise document retrieval rarely depends on content alone. Instead, file relevance is shaped by context: when a document was created, who it is for, whether it is valid, and how it relates to ongoing work. Traditional vector search systems handle this context through filters and additional search pipeline stages, which increases complexity and often degrades real relevance.

Aspected approaches this differently. Built around the Aspect Database, a context-aware retrieval engine for AI systems, it encodes both content and context into a unified representation. This allows a single query to retrieve documents that are not only semantically similar but also aligned across time, domain, role, and other constraints, without requiring multi-stage pipelines.

This article analyzes a real enterprise retrieval use case to demonstrate how this approach improves existing systems, including already established RAG pipelines and enterprise search architectures. The search performance offered by the Aspected approach represents the next step toward greater retrieval efficiency.

From Filters to Features: Aspect Database vs Vector Databases

Aran.Montero-Salvado@Xillio.com (Aran Montero Salvadó) — Thu, 02 Apr 2026 07:00:00 GMT

A comparison of how vector databases handle contextual constraints and how multi-aspect embeddings enable unified similarity search.

TL;DR

Most vector databases are designed to perform similarity search over embeddings derived from text or other unstructured data. Contextual constraints such as timestamps, document types, or ownership are typically handled as external filters applied before or after the vector search step. This architecture works well for many applications, but becomes limiting when contextual signals should influence ranking rather than simply restrict the search space. This article examines how traditional vector database architectures handle filtering and retrieval, and introduces an alternative design approach implemented by Aspected through the Aspect Database: a context-aware retrieval engine for AI systems, where contextual attributes are encoded directly into the representation used for similarity computation through multi-aspect embeddings.

Metadata Enrichment as a First-Class AI Capability

Aran.Montero-Salvado@Xillio.com (Aran Montero Salvadó) — Mon, 09 Mar 2026 08:00:00 GMT

How AI-generated metadata is reshaping enterprise retrieval and turning enriched metadata into a core component of relevance.

TL;DR

Most retrieval problems attributed to AI models are actually relevance problems. While AI-driven metadata enrichment has improved how systems describe documents, retrieval architectures still rely on hard filters and heuristic ranking that cannot fully exploit this enriched information. Aspect Search introduces a different retrieval primitive, where relevance is calculated across multiple semantic aspects, including enriched metadata, directly in vector space. This shifts retrieval from rigid filtering to unified, multi-dimensional similarity computation that better reflects real-world context and user intent.

It Wasn’t a Hallucination. It Was a Retrieval Failure.

Aran.Montero-Salvado@Xillio.com (Aran Montero Salvadó) — Thu, 19 Feb 2026 08:00:00 GMT

An analysis of the root causes of hallucinations in RAG systems, and a relevance-first approach that reduces them by design.

TL;DR

Many of the flaws of LLMs are attributed to “hallucinations”, which are in fact the result of retrieval failures in retrieval-augmented generation systems [1, 2]. When AI systems work on incomplete or poorly structured context, incorrect answers are an expected outcome. Aspect search proposes a different way of thinking about retrieval, where relevance is computed across multiple semantic aspects directly in vector space. By embedding context into relevance itself, Aspected reduces “hallucinations” by design rather than by external mitigation strategies.

Introducing Aspects: A New Vector Search Paradigm

Aran.Montero-Salvado@Xillio.com (Aran Montero Salvadó) — Thu, 15 Jan 2026 08:00:00 GMT

A unified vector search approach that embeds both meaning and metadata into a single representation, making relevance more natural, expressive, and efficient.

TL;DR

Vector search made it possible to retrieve documents by meaning rather than keywords, but most systems still embed only unstructured text and treat metadata as external filters. Historically, metadata was introduced to compensate for the limits of keyword search, yet it never truly became part of relevance itself. With vector search, the same happened again. Aspect search bridges this gap by transforming meaningful document properties into vectors and combining them with semantic embeddings into a single representation. The result is a unified, weighted, multi-dimensional search that runs in one query, expresses relevance more naturally, and scales efficiently.