ufukhurriyet's starred repositories
rag_with_kg
RAG with knowledge graphs implemented from scratch
hands-on-introduction-data-engineering-4395021
This repo is for the Linkedin Learning course: Hands-On Introduction: Data Engineering
awesome-data-engineering
A curated list of data engineering tools for software developers
ml-engineering
Machine Learning Engineering Open Book
data-engineering-zoomcamp
Free Data Engineering course!
language-models
pre-trained Language Models
communication-services-AI-customer-service-sample
A sample app for the customer support center running in Azure, using Azure Communication Services and Azure OpenAI for text and voice bots.
medical_kb_chatbot
medical_kb_chatbot
android-medical-assistant
An android chatbot that analyzes your medical symptoms
NLP-chatbot
A medical chatbot that asks patients about their health and books a doctor's appointment on demand.
Doctor-Friende
Rasa-Doctor-Friende.A chinese medical chatbot based on Neo4j knowledge graph and Rasa.
Health-Care-Chatbot
It is a medical chatbot that will provide quick answers to FAQs by setting up rule-based keyword chatbots.
MedicalChatbot
Medical-domain Dialogue System for Diseases Identification
Llama2-Medical-Chatbot
This is a medical bot built using Llama2 and Sentence Transformers. The bot is powered by Langchain and Chainlit. The bot runs on a decent CPU machine with a minimum of 16GB of RAM.
langchain-experiments
Building Apps with LLMs
haystack
:mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
combining-linking-techniques
Combining Linking Techniques (CLiT) is an entity linking combination and execution framework, allowing for the seamless integration of EL systems and result exploitation for the sake of system reusability, result reproducibility, analysis and continuous improvement. (We hate waste. Especially wasting time. So let's reuse instead!)
AGDISTIS_DEMO
A demo of the MAG - a Multilingual, Knowledge-base Agonistic and Deterministic Entity Linking approach in 40 languages implemented within AGDISTIS Framework. We provide MAG in 9 different languages, English, German, Italian, French, Spaninsh, Portuguese, Japanese, Dutch and Chinese. Additionally, we provide MAG on English Wikidata as a proof of its knowledge-base agnosticism.
MELBench
Multimodal entity linking (MEL) aims to utilize multimodal information to map mentions to corresponding entities defined in knowledge bases. We release three MEL datasets: Weibo-MEL, Wikidata-MEL and Richpedia-MEL, containing 25,602, 18,880 and 17,806 samples from social media, encyclopedia and multimodal knowledge graphs respectively. A MEL dataset construction approach is proposed, including five stages: multimodal information extraction, mention extraction, entity extraction, triple construction and dataset construction. Experiment results demonstrate the usability of the datasets and the distinguishability between baseline models.
google-research
Google Research
Grokking-Deep-Learning
this repository accompanies the book "Grokking Deep Learning"