GenAI Projects
Learning never exhausts the mind
― Leonardo da Vinci
Collections#
Blogs#
| Name | URL |
|---|---|
| LLM terminology | Link |
| A Critical Look at MCP | Link |
| Ilya Rice: How I Won the Enterprise RAG Challenge | Link |
Papers#
| Paper | Link | Preview |
|---|---|---|
| A Comprehensive Overview of Large Language Models | Click | ref |
| KBLaM: Knowledge Base augmented Language Model | Click | |
| Retrieval-Augmented Generation for Large Language Models: A Survey | Click | ref |
| Revolutionizing Retrieval-Augmented Generation with Enhanced PDF Structure Recognition | Click | |
| Optimizing RAG Techniques for Automotive Industry PDF Chatbots: A Case Study with Locally Deployed Ollama Models | Click | |
| Google Prompt Engineering whitepaper | ref | |
| Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time | Click | |
| LLM Post-Training: A Deep Dive into Reasoning Large Language Models | ref | |
| Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder | Click | |
| What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization? | Click |
Model/Repository#
| Model/Repository | Link |
|---|---|
| ds4sd/SmolDocling-256M-preview | Hugging Face |
| qlib | GitHub |
| ByteDance/Dolphin | Hugging Face |
Agent Frameworks#
| Agentic Framework Name | Github Link |
|---|---|
| LangChain | GitHub |
| llama_index | GitHub |
| Autogen | GitHub |
| Haystack | GitHub |
| CrewAI (flow) | GitHub |
| langflow | GitHub |
| smolagents | GitHub |
| Pydantic AI | GitHub |
| pyspur | GitHub |
| agno (phiData) | Github |
| instructor | Github |
| DSpy | Github |
| JS Only | --- |
| n8n | GitHub |
My LLM Working Projects#
Schema Mapping (Completed)#
LLM can be used to map schema from one format to another. This is useful for data migration and integration.
| Resources | Link |
|---|---|
| blog (inspired by this blog) | Blog |
| paper (research paper on schema mapping) | ref |
Feature Engineering (Ongoing)#
LLM can be used to generate features for machine learning models. This can save time and effort in the feature engineering process.
| Resources | Link |
|---|---|
| paper (research paper on schema mapping) | ref |
| paper (research paper on schema mapping) | ref |
RAG: PDF Converting (Completed)#
LLM can be used to convert PDFs into structured data. This is useful for extracting information from unstructured documents.