Semilab

Searchable Enterprise Knowledge Base With Chatbot Integration

Semilab provides metrology solutions for semiconductor device manufacturers worldwide and is a strategic supplier to leaders in the More-than-Moore market segment. Their roots directly stem from the Hungarian Academy of Sciences, driving a strong motivation for R&D and continuous innovation. To stay ahead of the curve, they partnered with Hiflylabs to integrate state-of-the-art AI into their processes.

10% improvement

in preprocessing efficiency.

Challenge

With the hype around generative AI’s integrability with enterprise data, Semilab wanted to test whether a LLM-powered chatbot would enable its employees to improve access to relevant information across their extensive knowledge pool. Their hope was to increase internal work efficiency.

Solution

Hiflylabs created a Microsoft Azure pipeline that enables OpenAI’s model to be fed corporate information and answer user questions in real time—while complying with all corporate safety and privacy standards. Existing data preprocessing techniques were updated—improving their efficiency by 10% on average. With a new chunking strategy, we got more coherent content blocks and better text recognition. Retrieval augmented generation was implemented, improving searchability. An automated evaluation system was developed as well to save time on iterative cycles. The successful proof-of-concept initially turned into a multi-sprint project with the intent of developing a customized model with full access and integration into the company data infrastructure.

Service

Industries

Semiconductor

Manufacturing

Technologies

Python

PDF Plumber

Cognitive Search

OpenAI

Azure