Thierry Moreau
Professor Of Biochemistry at University of TOURS
Tours, Centre-Val de Loire, France
Summary
🤩
RockstarThierry Moreau is a Professor of Biochemistry based in Tours with 12 years of software engineering experience bridging academic research and practical engineering. He contributes to prominent open-source AI projects, adding generative AI integrations to Weaviate’s vector database and building Llama 2 cloud demos that showcase RAG and LangChain workflows. Comfortable across back-end and full-stack roles, he writes client libraries, test suites, and demo applications that make advanced models usable in cloud environments. His dual perspective as a life scientist and developer helps translate complex biological and computational problems into reproducible, production-ready solutions. Notably, his work enabled text-generation capabilities inside a scalable cloud-native vector database, demonstrating an uncommon combination of domain knowledge and production AI engineering.
12 years of coding experience
Github Skills (20)
apim10
python10
langchain10
llama10
vector-database10
ag10
go10
api10
generative-ai10
jupyter-notebook10
api-design9
restful-api9
package-development9
api-rest9
plugin-development9
Programming languages (11)
Github contributions (5)
meta-llama/llama-cookbook
Feb 2024 - Sep 2024
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:6 PRs, 15 comments in 6 months
Contributions summary:Thierry added a demo application that showcases how to run Llama 2 in the cloud hosted on OctoAI. The application uses LangChain to ask Llama general questions and follow up questions. The user also implemented a demo for answering questions about the Llama 2 paper using Retrieval Augmented Generation (RAG) method. This demonstrates the user's ability to work with cloud environments, LLMs, and RAG techniques.
aifinetuninglangchainllamallama2
weaviate/weaviate
Apr 2024 - May 2024
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
Role in this project:Back-end Developer
Back-end DeveloperContributions:10 reviews, 1 PR, 13 comments in 6 days
Contributions summary:Thierry's initial commits focused on setting up and implementing generative AI capabilities, specifically integrating with the OctoAI platform. The code changes involve creating client libraries for interacting with the OctoAI API, including request formatting, authentication, and error handling. This work appears to enable the use of generative models within the Weaviate ecosystem, providing text generation features. Later commits expanded and refined the functionality of the text2vec-octoai module, including test and acceptance tests.
approximate-nearest-neighbor-searchsemantic-search-enginehnswfaultsimilarity-search
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.