Finder: A Multimodal AI-Powered Search Framework for Pharmaceutical Data Retrieval

TL;DR

Finder is an innovative multimodal AI framework that enhances pharmaceutical data retrieval by integrating diverse content types and advanced search techniques, significantly improving accuracy and contextual relevance across multiple languages and formats.

Contribution

The paper introduces a scalable, modular AI-powered framework that unifies multimodal content retrieval using hybrid vector search and reasoning-aware natural language processing.

Findings

Processed over 291,400 documents and 31,070 videos

Improved search precision and contextual relevance

Supports multiple languages and diverse content formats

Abstract

AI is transforming pharmaceutical search, where traditional systems struggle with multimodal content and manual curation. Finder is a scalable AI-powered framework that unifies retrieval across text, images, audio, and video using hybrid vector search, combining sparse lexical and dense semantic models. Its modular pipeline ingests diverse formats, enriches metadata, and stores content in a vector-native backend. Finder supports reasoning-aware natural language search, improving precision and contextual relevance. The system has processed over 291,400 documents, 31,070 videos, and 1,192 audio files in 98 languages. Techniques like hybrid fusion, chunking, and metadata-aware routing enable intelligent access across regulatory, research, and commercial domains.