About YatseaLi

YatseaLi

In my previous blog post, we have discussed the business values, overview and technical details about end-to-end Low-Code Machine Learning with Ludwig and SAP AI Core. In this blog post, I'll continue sharing my experience of replicating another two ...

YatseaLi

Ludwig is a popular open-source low-code framework for building custom AI models like LLMs and other deep neural networks. It simplifies the machine learning process with a low-code approach, enabling non-ML roles(application developers, business use...

YatseaLi

In the blog post about Function Calling LLMs for SAP: Structured Outputs and API calling by @MarioDeFelipe, Mario has done a great job in explaining the why and how of LLM's structured output with Function Calling for SAP API integration.On 6 Aug 202...

YatseaLi

Following the blog post Product Updates for SAP Build Code – July 2024 Edition by @BirgitS. Use Joule to enhance your already existing data models and services is now supported in SAP Build Code, which enables the developers to enhance a specific dat...

YatseaLi

Authors: @YatseaLi, @cesarecalabria, @amagnani, @jacobahtan In my previous blog post about Bring Open-Source or or Open-Weight LLMs into SAP AI Core, we have gone through an overview introduction of deploying and running open-source LLMs in SAP AI Co...

YatseaLi

Hi @Srina, Thanks for your feedback.Here you have my answer to your inquiry about BYOM self-hosted LLM from private data center into SAP AI Core, such as a private LLM or fine-tuning models.In this case, llama.cpp and vLLM are recommended to serve t...

YatseaLi

Very interesting. With the hana tool, I guess it can already accomplish the paper about Semantic Operators: A Declarative Model for Rich, AI-based Analytics Over Text Data and some similar experimental feature in google big query like this.Looking fo...

YatseaLi

Great article. In addition, I would like to bet on:1. Small Language Model(SLM): Small and specialized LMs will take the spaces of vertical industries, and the long tails etc., while the LLM remains dominant for general-purpose. And these SLMs should...

YatseaLi

@jagdish_chandrasekaran,For sentence-transformer, as mentioned in Why Infinity section in its official github repo Deploy any model from HuggingFace: deploy any embedding, reranking, clip and sentence-transformer model from HuggingFaceFor imgbedding...

YatseaLi

@Akaay,llama 3.1 models family is for text generation, not for text embedding purpose. Here list some text embedding available in ollama.nomic-embed-text hellord/mxbai-embed-large-v1Once the embedding model pulled in ollama in SAP AI Core, then you c...

User Statistics

User Activity

Low-Code Machine Learning with Ludwig and SAP AI Core #2-Defect Detection & Sound Anomaly Detection

Low-Code Machine Learning with Ludwig and SAP AI Core

From Unstructured Input to Structured Output: LLM meets SAP

Enhance your existing CAP projects with Joule in SAP Build Code

Bring Open-Source LLMs into SAP AI Core with Custom Transformer Server

Re: Bring Open-Source LLMs into SAP AI Core

Re: Stop Guessing! Use Case with Conversational AI Agents in SAP Analytics Cloud

Re: AI in 2025 - predictions or guessing game

Re: Bring Open-Source Text Embedding Models into SAP AI Core with Infinity

Re: Bring Open-Source Text Embedding Models into SAP AI Core with Infinity