Pinned Loading

1. GraphRagPart1DataPipeline GraphRagPart1DataPipeline Public

   This is the part 1 of a GraphRAG system, in which I show how the GraphRAG pattern works. Part 1 is a basic Data Pipeline made with Dagster, which orchestrates the data ingestion from multiple sourc…

   Python

2. GraphRagPart2RetrievalAndChatbot GraphRagPart2RetrievalAndChatbot Public

   This is the part 2 of a GraphRAG system, in which the user interacts with the data through 2 data structures: vector database (Chroma DB) and graph database (Neo4j). I exploit the probabilism of ve…

   Python

3. annotationNLP annotationNLP Public

   An Ad-hoc application developed for building datasets as part of my PhD thesis. There are two tools in the app: (1) allows selecting and annotating text passages and (2) the other clean and label s…

   JavaScript

4. stance_classification stance_classification Public

   Toolkit for the paper "Explainable Subjective Stance Classification with SetFit in Political Discourse". The project leverages the SetFit few-shot learning framework, Sentence Transformers architec…

   Jupyter Notebook

5. topic-continuity topic-continuity Public

   Toolkit for the paper "Explainable Topic Continuity in Political Discourse: A Sentence Pair BERT Model Analysis". The project leverages Sentence Pair Modeling (SPM), BERT, and the Transformers Inte…

   Python

6. webCrawler webCrawler Public

   This Crawler was built as part of my PhD thesis to collect a huge corpus of political discourse by politicians in the USA.

   Python