<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>LLM | Mohammadhossein (Rastin) Akbari Moafi</title><link>https://r4stin.github.io/tag/llm/</link><atom:link href="https://r4stin.github.io/tag/llm/index.xml" rel="self" type="application/rss+xml"/><description>LLM</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Sat, 20 Dec 2025 00:00:00 +0000</lastBuildDate><image><url>https://r4stin.github.io/media/icon_hu2b06ce7dbfc98605c45fb34b724f1004_70123_512x512_fill_lanczos_center_3.png</url><title>LLM</title><link>https://r4stin.github.io/tag/llm/</link></image><item><title>Translation RAG Service</title><link>https://r4stin.github.io/project/_translation_rag/</link><pubDate>Sat, 20 Dec 2025 00:00:00 +0000</pubDate><guid>https://r4stin.github.io/project/_translation_rag/</guid><description>&lt;p>A lightweight Retrieval-Augmented Generation (RAG) backend for translation prompts. The service exposes a FastAPI REST API that stores translation pairs in SQLite — kept idempotent through database-level deduplication — retrieves the most relevant examples with TF-IDF cosine similarity, and assembles them into retrieval-augmented prompts for LLM-based translation. An additional heuristic component detects stammering in translated sentences, and the whole system ships Dockerized for easy deployment.&lt;/p></description></item><item><title>KG-Research-Agent</title><link>https://r4stin.github.io/project/_kg_agent/</link><pubDate>Sat, 01 Nov 2025 00:00:00 +0000</pubDate><guid>https://r4stin.github.io/project/_kg_agent/</guid><description>&lt;p>Built a multi-agent, evidence-grounded research system that ingests scientific PDFs, retrieves context with RAG (ChromaDB + Gemini), extracts structured claims and evidence, and stores them in a Neo4j knowledge graph. Features a Planner → Retriever → Evidence → Answer pipeline with session memory, citation-grounded responses, and end-to-end PDF ingestion, querying, and multi-turn reasoning.&lt;/p></description></item><item><title>Support Memory Weave</title><link>https://r4stin.github.io/project/_memory_agent/</link><pubDate>Sat, 01 Nov 2025 00:00:00 +0000</pubDate><guid>https://r4stin.github.io/project/_memory_agent/</guid><description>&lt;p>Built an LLM-powered pipeline for transforming unstructured customer support messages into structured tickets using FastAPI, LangGraph, and PostgreSQL. Features automated conversation ingestion, multi-step ticket structuring, semantic vector retrieval with SentenceTransformers, and evidence-based reply suggestions backed by realistic conversational datasets.&lt;/p></description></item><item><title>Provenance-Aware Metadata (Phase 3)</title><link>https://r4stin.github.io/project/_provenance_aware_metadata/</link><pubDate>Mon, 01 Sep 2025 00:00:00 +0000</pubDate><guid>https://r4stin.github.io/project/_provenance_aware_metadata/</guid><description>&lt;p>Developed a provenance-aware metadata workflow for digital assets using JSON-LD (Dublin Core, PROV-O, Schema.org) with SHACL validation, C2PA signing, and a FastAPI service exposing IIIF Presentation 3.0 manifests and verification endpoints. Implemented Wikimedia Commons integration, extended EDM/PREMIS validation policies, CI/CD pipelines, and container publishing via GHCR.&lt;/p></description></item><item><title>Reviews Dashboard</title><link>https://r4stin.github.io/project/_review_dashboard/</link><pubDate>Mon, 01 Sep 2025 00:00:00 +0000</pubDate><guid>https://r4stin.github.io/project/_review_dashboard/</guid><description>&lt;p>Built a modern dashboard for property managers to analyze and manage guest reviews across properties, integrating Hostaway and Google Reviews APIs with trend analysis, approval workflows, modular UI components, and extensible LLM-based review analysis for sentiment and insights.&lt;/p></description></item><item><title>Knowledge-Guided Visual Analytics for Scientific Image Annotation</title><link>https://r4stin.github.io/project/_kg_wikidata_annotation/</link><pubDate>Sun, 01 Jun 2025 00:00:00 +0000</pubDate><guid>https://r4stin.github.io/project/_kg_wikidata_annotation/</guid><description>&lt;p>A deep learning pipeline for automatic annotation and retrieval of scientific figures. The system builds on CLIP and BiomedCLIP — including fine-tuned variants — to embed biomedical images and text into a shared semantic space, and integrates Wikidata-based knowledge graphs to enrich that space with structured domain knowledge. The result is stronger semantic alignment between figures and their descriptions, along with interpretable visualisations that make the annotation and retrieval behaviour of the models easier to inspect.&lt;/p></description></item><item><title>Text-Guided Medical Image Denoising with Vision-Language Fusion</title><link>https://r4stin.github.io/project/_vlm-denoising/</link><pubDate>Thu, 01 May 2025 00:00:00 +0000</pubDate><guid>https://r4stin.github.io/project/_vlm-denoising/</guid><description>&lt;p>A medical image denoising system that fuses vision and language: a UNet-based denoiser is conditioned on CLIP text embeddings derived from the VQA-RAD dataset, letting textual context guide the reconstruction of noisy scans. Compared to a vision-only baseline, the vision-language fusion improved reconstruction quality by 12.5% in PSNR and 4.6% in SSIM.&lt;/p></description></item></channel></rss>