Leonie MonigattiinTowards Data ScienceAdvanced Retrieval-Augmented Generation: From Theory to LlamaIndex ImplementationHow to address limitations of naive RAG pipelines by implementing targeted advanced RAG techniques in PythonFeb 1910Feb 1910
Kristian CabadingGetting a FREE domain for your EC2 InstanceI’ve been studying AWS recently and was looking for an easier way or rather using a domain name instead of a random IP address to access my…Dec 29, 20178Dec 29, 20178
Hanane DupouyDiscover DocLLM: The New LLM From JPMorgan For Working with Complex DocumentsJPMorgan has launched a new language model called DocLLM, specifically designed for working with documents that have complex layouts. This…Jan 510Jan 510
Ahmed BesbesinTowards Data ScienceHow to Deploy a Machine Learning Model with FastAPI, Docker and Github ActionsAn end-to-end pipeline with a CI/CDJul 11, 202111Jul 11, 202111
Jonathan SerranoDeploy a FastAPI app to production using Docker and AWS ECRThere is this new word lurking around recently: MLOps. I bet you have heard of it. It is not a narrow term since its scope includes the…Apr 14, 20221Apr 14, 20221
Wenqi GlantzinTowards Data ScienceDeploying LLM Apps to AWS, the Open-Source Self-Service WayA step-by-step guide on deploying LlamaIndex RAGs to AWS ECS fargateJan 83Jan 83
James NguyeninData Science at MicrosoftForget RAG: Embrace agent design for a more intelligent grounded ChatGPT!The Retrieval Augmented Generation (RAG) design pattern has been commonly used to develop a grounded ChatGPT in a specific data domain…Nov 18, 202321Nov 18, 202321
Christopher KarginTowards Data ScienceHow to efficiently fine-tune your own open-source LLM using novel techniques — code providedIn this article I tune a base LLama2 LLM to output SQL code. I use Parameter Efficient Fine-Tuning Techniques to optimise the process.Dec 15, 20232Dec 15, 20232