AI in Action Technology
Talk to Your Graph Client for GraphDB
Learn how to develop a Talk to Your Graph (TTYG) client by integrating GraphDB and the OpenAI Assistants API
Pavel MihaylovAI in Action
Pavel Mihaylov
AI in Action Technology
How Far We Can Go with GenAI as an Information Extraction Tool
How we used Ontotext GraphDB and LLMs to improve CV selection
Anna Aksenova
Petar Mitankin
Filip Dimitrov
Stefan Nikolov
AI in Action Technology
My Dear Watson, it is Great to Have Someone to Talk to
Join us to learn how we empower users to sift through a large pool of data with the help of a trusted assistant – the GraphDB 10.8 Talk To Your Graph agent.
Nedelina Mitankina
Andrey Tagarev
AI in Action Technology
A Triple Store RAG Retriever
How we used Ontotext GraphDB’s vector capabilities to build a simple RAG retriever over a Knowledge Graph, using open, offline LLM models
Matteo Casu
AI in Action Technology
Okay, RAG… We Have a Problem
We compare how the different Graph RAG patterns can address the problem of lacking background knowledge that the naive “chunky” RAG hits, including the use of NLQ and external context derived from Wikidata via entity linking
Neli Hateva
AI in Action Technology
Using GraphDB’s Natural Language Interface to Talk with Your Content
Explore our innovative “Talk to Your Graph” feature for natural language data querying in OTKG and learn about integration with vector databases for enhanced data retrieval.
Bob DuCharme
AI in Action Technology
Event Extraction Based on Fine-Tuned Text2Event Transformer Speeds up the Fact-checking Process
Learn about EDNA (Event Detector for Narrative Analysis) extracts events from text to find out who did what, when, where, and why. EDNA untangles patterns in disinformation related to a particular event and uncovers links between events based on actors, places, time, and concepts.
Petar Ivanov
AI in Action Technology
Multilingual Question Answering in Medicine based on XLM-RoBERTa
Learn how to gain flexibility in structuring your data in any language or domain with a focus on multilingual extractive question answering to medical records.
Anna Aksenova
AI in Action Technology
Gaining Global Insights with Multilingual Entity Linking
Read about how state-of-the-art AI models for multilingual entity linking enable working with concepts in 105 languages and helps connect and analyze linguistically diverse content.
Ivelina BozhinovaAndrey Tagarev
Eneya Georgieva