Master's student in Language Technologies at University of Turin. Graduating soon.
Background in recommendation engines, search relevance, and demand forecasting.
Retrieval-Augmented Generation (RAG)
Building a RAG system to query FOMC documents. Currently implementing semantic chunking with vLLM for better retrieval.
An Open Invitation
This project is a work in progress, and I value fresh eyes to help refine the flow. If you have a moment to glance through the repository, I'd love to know what you see. A smoother path? or a bottleneck I missed?
- Turning messy data into structured insight
- Information retrieval and knowledge systems
- LLM orchestration and agent design
The Noise of the Information Age
graph LR
%% 1. The World of Noise
subgraph Context [ ]
A(Data Bombardment)
B(Infinite Inputs)
C(Fragmented Signals)
end
%% 2. The Tinkerer's Process
subgraph Process [Selection & Placement]
D{Deciphering}
E[Selection: Finding Components]
F[Placement: Weaving Connections]
end
%% 3. The Result
subgraph Outcome [The Coherent Whole]
G((CLARITY))
H[Insight]
I[Orchestrated Systems]
end
%% Connections
%% By connecting A, B, and C to D individually,
%% Mermaid naturally stacks them vertically to save space.
A -.-> D
B -.-> D
C -.-> D
D -->|Filtering| E
E -->|Arranging| F
F ==>|Transformation| G
G --> H
G --> I
%% Styling
style G fill:#f9f,stroke:#333,stroke-width:4px
style D fill:#fff,stroke:#333,stroke-width:2px
style E fill:#fff,stroke:#333,stroke-width:2px
style F fill:#fff,stroke:#333,stroke-width:2px
style Context fill:#f9f9f9,stroke:#ddd,stroke-dasharray: 5 5