GenAI Projects
A collection of generative AI resources and project notes on schema mapping, feature engineering, PDF extraction, and agent frameworks.
Categories
Tags
On this page 7 sections
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.
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.
RAG: PDF Converting (Completed)
LLM can be used to convert PDFs into structured data. This is useful for extracting information from unstructured documents.