Automatic unstructured PDF ingestion on GCP

The scope of this session is to show how it is possible to create a Question Answering agent on GCP starting from complex documents, like technical handbooks. This will be done by using the following passages:

1. Document Segmentation
Semantic structures (like title, sections, tables...) will be inferred with State-of-the-Art models.

2. Optical Character Recognition (OCR)
Google OCR will be applied to the previously-determined structures in order to determine their content.

3. Vectorization
The text will be saved in a vector store in order to allow a fast information retrieval.

4. Large Language Model (LLM) Connection
The vector store will be connected to an LLM that will be used to provide the user with suitable answers for his/her questions.

This project will showcase the capabilities of State-of-the-Art models and technologies in the field of Generative AI.

Speaker Bio:

Ivano Donadi is an AI Engineer at Ennova-Research, where he designs and develops innovative artificial intelligence solutions for diverse projects.

He earned his Bachelor's degree in Information Engineering from the University of Padua in 2020, followed by a Master's degree in Computer Engineering in 2022. He collaborated with the University of Padua for a year as a research fellow, working on sonar localization methods and 3D stereo object pose estimation. Since 2023, he has been working as an AI Engineer at Ennova-Research, actively participating in Natural Language Processing (NLP) projects.