Hopsworks reposted this
This is a visual blueprint to create an LLM, End-to-End System using the FTI Framework, based on one of the many content and talks by Jim Dowling during this year. And this might be a bit daunting, so, what is in the diagram here? 1️⃣ Data Collection: Gathering Raw Data From Different Sources 📂 /Data Sources │ ├──── PDFs 📄 │ │ └──── External storage (e.g., S3, Drive) │ ├──── ClickLog 🖱️ │ │ ├──── Last Clicks │ │ └──── Chat History │ └──── Orders 🛒 │ ├──── Name │ └──── Last Buy ────── 2️⃣ Data Transformation: Turning Data into Intelligence 🔧 /ML Pipelines │ ├──── Feature Pipeline 🛠️ │ │ ├──── Extract Text │ │ ├──── Feature Engineering │ │ └──── Compute Embeddings │ └──── Training Pipeline 🧠 │ ├──── Instruction Dataset │ └──── Fine-Tuned Model ────── 3️⃣ Infrastructure: Supporting the System 🏗️ /Data Infrastructure (Hopsworks) │ ├──── Feature Store 📊 │ ├──── Model Registry 🗂️ │ └──── ANN Index 🔍 ────── 4️⃣ User Interaction: Delivering 👥 /Users & Application │ ├──── Inference Pipeline 💡 │ │ ├──────────── RAG (Retrieval-Augmented Generation) │ │ ├──────────── Enriched Prompt │ │ └──────────── Fine-Tuned Model │ └──── Response Logging 📈 ────── If you are curious on how to build such systems; feel free to go the github repo and build it yourself ; https://lnkd.in/gHvAUtwU
Which tool was used to make the diagram?
Thank you for sharing this visual blueprint for creating an LLM, End-to-End System using the FTI Framework. It looks like a complex process, but your diagram breaks it down into manageable steps. I appreciate the effort you put into creating this and making it available on Github for others to learn from. It's inspiring to see people like you sharing their knowledge and expertise with the community. Keep up the great work!
It's a great example! There's a lot of tools out there that provide this type of functionality in the public cloud... but with Hopsworks you never have to leave your own data environment - so you can use it on truly private / sensitive data...
Senior ML/AI Engineer • MLOps • Founder @ Decoding ML ~ Posts and articles about building production-grade ML/AI systems.
2moLove the diagram 🔥