Home Up PDF Prof. Dr. Ingo Claßen
LLMs

paper

  • AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls
  • Automatic Chain of Thought Prompting in Large Language Models
  • Benchmarking and Improving Text-to-SQL Generation under Ambiguity
  • Bridging Language and Data - Optimizing Text-to-SQL Generation in Large Language Models
  • C3: Zero-shot Text-to-SQL with ChatGPT
  • Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Direct Preference Optimization: Your Language Model is Secretly a Reward Model
  • Enhancing Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategies
  • DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
  • DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
  • Generative Agents: Interactive Simulacra of Human Behavior
  • Judging llm-as-a-judge with mt-bench and chatbot arena
  • LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
  • LoRA: Low-Rank Adaptation of Large Language Models
  • QLoRA: Efficient Finetuning of Quantized LLMs
  • ReAct: Synergizing Reasoning and Acting in Language Models
  • ReFT: Representation Finetuning for Language Models
  • Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
  • Retrieval-Augmented Generation for Large Language Models - A Survey
  • Retrieval-augmented GPT-3.5-based Text-to-SQL Framework with Sample-aware Prompting and Dynamic Revision Chain
  • Text-to-SQL Empowered by Large Language Models - A Benchmark Evaluation
  • Towards Robustness of Text-to-SQL Models against Synonym Substitution
  • Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models
  • Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models
  • VeRA: Vector-based Random Matrix Adaptation

agents

  • Agentic 1: Model Context Protocol (link)
  • Agentic 2: Crew AI & Semantic Kernel (link)
  • Agentic 3: LangChain & LangGraph (link)
  • Agentic 4: Manus & AutoGen (link)
  • Agentic AI: Build a Tech Research Agent (link)
  • Building RAG Research Multi-Agent with LangGraph (link)
  • Creating a Research Agent with AutoGen and Panel UI (link)
  • Create AI Agent CRUD Application with PydanticAI: Step by Step (link)
  • Agentic RAG Series: Exploring LangGraph for Advanced Workflows (link)
  • Evaluation-Driven Development for agentic applications using PydanticAI (link)
  • Financial Analysis: Multi-Agent with Open Source LLMs Using CrewAI and Ollama Models (link)
  • Choosing Between LLM Agent Frameworks (link)
  • Want to Build AI Agents? Tired of LangChain, CrewAI, AutoGen & Other AI Agent Frameworks? Read this! (link)
  • Agentic AI: Comparing New Open-Source Frameworks (link)

agent frameworks

autogen

crewai

langgraph

manus

smalagents

coding

cot

  • Advanced Prompt Engineering: Chain of Thought (CoT) (link)

deepseek

  • The Chinese OBLITERATED OpenAI. A side-by-side comparison of DeepSeek R1 vs OpenAI O1 for Finance (link)
  • Fine-tuning DeepSeek R1 to respond like Humans using Python! (link)

divers

  • Awesome LLM Books (link)
  • LLM Visualization (link)
  • 50+ Open-Source Options for Running LLMs Locally (link)
  • Crawl4AI git (link)
  • AI-Powered Information Extraction and Matchmaking (link)
  • The 6 Best LLM Tools To Run Models Locally (link)
  • EvalPlus - a rigorous evaluation framework for LLM4Code (link)
  • Tiktokenizer (link)
  • Overview of Large Language Models (link)
  • Calculate : How much GPU Memory you need to serve any LLM ? (link)
  • A Tutorial on LLM (link)
  • Think Big LLM Models Can’t Fit Small GPUs? Think Again! (link)
  • unsloth (link)
  • Building an Agent for Data Visualization (Plotly) (link)
  • 6 Real-World Uses of Microsoft’s Newest Phi-3 Vision-Language Model (link)
  • What is Prompt Management for LLM Applications? (link)
  • Generative AI Agents Developer Contest by NVIDIA and LangChain (link)
  • How to fine-tune LLMs on custom datasets at Scale using Qwak and CometML (link)
  • LLM Fine Tuning Series - In Context Learning (link)
  • Large Language Model Course (link)
  • GPT-4o vs. GPT-4 vs. Gemini 1.5 ⭐ — Performance Analysis (link)
  • Tabular Data, RAG, & LLMs: Improve Results Through Data Table Prompting (link)
  • List of Different Ways to Run LLMs Locally (link)
  • Why Vector Search Didn’t Work for Your RAG Solution? (link)
  • 100x Faster — Scaling Your RAG App for Billions of Embeddings (link)
  • The 4 Advanced RAG Algorithms You Must Know to Implement (link)
  • Using DuckDB + Ibis for RAG (link)
  • DuckDB-NSQL: How to Quack in SQL (link)
  • Fine-Tuning Mistral 7B for Named Entity Recognition (NER) (link)
  • A Very Gentle Introduction to Large Language Models without the Hype (link)
  • RAG Vs VectorDB (link)
  • Advanced RAG Techniques: an Illustrated Overview (link)
  • Integrating Vector Databases with LLMs: A Hands-On Guide (link)
  • Core RAG Architecture with AlloyDB AI (link)
  • Forget RAG: Embrace agent design for a more intelligent grounded ChatGPT! (link)
  • Exploring Data Modelling with ChatGPT (link)
  • What Are ChatGPT Plugins? The Next Phase of Conversational AI Is Here (link)
  • Anomaly Detection in Time Series using ChatGPT (link)

embeddings

  • Text Embeddings: Comprehensive Guide (link)

dspy

  • DSPy (link)
  • DSPy - git (link)
  • Prompt Like a Pro Using DSPy: A guide to build a better local RAG model using DSPy, Qdrant and Ollama (link)

finetuning

  • LoRA: Low-Rank Adaptation of Large Language Models (link)
  • State-of-the-art Parameter-Efficient Fine-Tuning (PEFT) methods (link)

haystack

llama

  • Building LLaMA 3 From Scratch with Python (link)
  • Crazy Challenge: Run Llama 405B on a 8GB VRAM GPU (link)
  • How to Run Llama 3.1 405B on Home Devices? Build AI Cluster! (link)
  • Fine-Tuning CodeLlama for Advanced Text-to-SQL Queries with PEFT and Accelerate (link)
  • The Llama 3 Herd of Models (link)

llamaindex

langchain / langgraph

  • home (link)
  • doc (link)
  • What Is LangChain? (link)
  • LangGraph Studio: Visualizing and Testing AI Agents with LangChain (link)
  • From Basics to Advanced: Exploring LangGraph (link)
  • How to Build AI Agents with LangGraph: A Step-by-Step Guide (link)

mcp

  • MCP-Home: Model Context Protocol (MCP) (link)
  • The guide to MCP I never had (link)
  • What is the Model Context Protocol (MCP)? (link)
  • The complete guide to building MCP Agents (link)
  • What is MCP? A Comprehensive Guide to Building Advanced AI Agents Beyond Traditional APIs. (link)
  • Bright Data MCP (link)
  • MindsDB (link)
  • 5 Best MCP Servers for Effortless Vibe Coding in 2025 (link)
  • MCP is on Fire! 10 + Insane Use Cases That Prove It’s the Future of AI Integration (link)
  • Building a Multi-Agent System with Multiple MCP Servers using Smolagents (link)
  • Comparing Model Context Protocol (MCP) Server Frameworks (link)
  • How to Setup and Use PostgreSQL MCP Server (link)
  • A Postgres MCP server (link)
  • Model Context Protocol (MCP): The AI Integration Breakthrough You Need to Know (link)
  • Model Context Protocol(MCP) with Google Gemini 2.5 Pro — A Deep Dive (Full Code) (link)
  • Claude with MCPs Replaced Cursor & Windsurf — How Did That Happen? (link)
  • Getting Started: Model Context Protocol (link)
  • How to make your clients more context-aware with OpenMemory MCP (link)

nvidia

  • Nemotron-4 15B: NVIDIA’s Powerful New Language Model (link)

ollama

  • git (link)
  • API (link)
  • docker (link)
  • Self Hosting LLMs using Ollama (link)
  • Ollama: The Ultimate Tool for Running Language Models Locally (link)
  • Unlock Any Open-Source LLM with Ollama (link)
  • Unlocking the Power of Structured Outputs with Ollama (link)
  • Your Machine, Your AI — The Ultimate Local Productivity Stack with Ollama (link)
  • Building an Advanced RAG Pipeline Using Docling, Groq, Ollama with GLIDER Evaluation (link)
  • Ollama’s New Vision Model Support: A Comprehensive Guide (link)
  • ChatOllama (link)

prompt eng

  • Testing 17 Prompt Engineering Techniques on 1B Parameter LLM (link)

phi

  • Bridging the Gap: Fine-Tuning Phi-3 for SQL Query Generation with Natural Language Queries (link)
  • Exploring the Microsoft Phi3 Vision Language model as OCR for document data extraction (link) loring the Microsoft Phi3 Vision Language model as OCR for document data extraction-part 2 (link)
  • Exploring the Microsoft Phi3 Vision Language model as OCR for document data extraction (link)

qwen

  • Qwen3 from Alibaba : How to deploy this very communist but smart model 100% Locally? (link)
  • Qwen-3 Fine Tuning Made Easy: Create Custom AI Models with Python and Unsloth (link)

rag

  • Finding the Best Open-Source Embedding Model for RAG (link)
  • Developing RAG Systems with DeepSeek R1 & Ollama (Complete Code Included) (link)
  • Full-stack RAG: FastAPI Backend (Part 1) (link)
  • Build an LLM RAG Chatbot With LangChain (link)
  • Microsoft GraphRAG and Ollama: Code Your Way to Smarter Question Answering (link)
  • Best practices for LLM optimization for call and message compliance: prompt engineering, RAG, and fine-tuning (link)
  • Graph RAG — A Conceptual Introduction (link)
  • High-Precision RAG for Table Heavy Documents (link)
  • Why Your RAG Doesn’t Work (link)

  • Mastering RAG Chunking Techniques for Enhanced Document Processing (link)

  • Let’s Build a RAG Agent Using Phi-Data in Just 20 Lines of Code — Open Source & Local! (link)
  • Gen AI Merchant Matching — using Opensource LLMs, Elastic search and FIASS (link)
  • RAG LLM Best Practices (link)
  • Top 10 RAG Frameworks Github Repos 2024 (link)
  • Build an LLM RAG Chatbot With LangChain (link)
  • A Deep Dive into Retrieval-Augmented Generation (RAG) with HyDE (link)
  • Build an Agentic RAG using HuggingFace Transformers Agent (link)
  • Using RAG Architecture to query databases, export to Google Sheets, and visualize in Looker Studio. (link)
  • How to Build a Generative Search Engine for Your Local Files Using Llama 3 (link)
  • Building Vector Databases with FastAPI and ChromaDB (link)
  • Adding Context to Retrieval-Augmented Generation with Gemini Function Calling and MongoDB Atlas (link)
  • A Complete Guide to RAG and LlamaIndex (link)
  • Build RAG Application Using a LLM Running on Local Computer with Ollama and Langchain (link)
  • Advance RAG- Improve RAG performance (link)
  • RAG Detective: Retrieval Augmented Generation with website data (link)
  • Implementing Agentic RAG using Langchain (link)
  • RAG on Complex PDF using LlamaParse, Langchain and Groq (link)
  • Building an Observable arXiv RAG Chatbot with LangChain, Chainlit, and Literal AI (link)
  • Local RAG From Scratch (link)
  • LangChain SQL Agent for Massive Documents Interaction (link)
  • Implementing RAG architecture using Llama 2, Vector Store and LangChain (link)
  • How to Chat With Your Data Using OpenAI, Pinecone, Airbyte and Langchain: A Guide (link)
  • Neo4j x LangChain: Deep dive into the new Vector index implementation (link)
  • Explore OpenAI vector embedding with Neo4j, LangChain, and Wikipedia (link)
  • Build your own RAG with Mistral-7B and LangChain (link)
  • PG Phriday: Papa’s Got a Brand New RAG (link)
  • Build an Advanced Reranking-RAG System Using Llama-Index, Llama 3 and Qdrant (link)
  • Improved RAG with Llama3 and Ollama (link)
  • Build End-to-End RAG Pipeline with Monitoring and Evaluation using Langchain, Azure AI Search, OpenAI, Langfuse, Nemo-gaurdrails, ragas (link)
  • Detecting fraud in real time using Redpanda and Pinecone (link)
  • Analyze Structured Data (extracted from Unstructured Text) using LLM Agents (link)
  • Transforming Text Classification with Semantic Search Techniques — Faiss (link)
  • Extract Structured Data from Unstructured Text using LLMs (link)
  • Code Generation using Retrieval Augmented Generation + LangChain (link)
  • Open-DocLLM (link)
  • Geospatial Vector Search: Building an AI-Powered Geo-Aware News Search (link)
  • AI-Enabled Search Engine using LLM Embeddings, Django, and pgvector (link)
  • Multimodal RAG pipeline with LlamaIndex and Neo4j (link)
  • Building a Multi-Modal Retrieval-Augmented Generation (RAG) System: A Comprehensive Guide (link)

rag pgvector

  • How To Improve Your LLM Accuracy and Performance With PGVector and PostgreSQL: Introduction to Embeddings and the Role of PGVector (link)
  • SQL queries + pgvector: Retrieval Augmented Generation in PostgreSQL (link)
  • PostgreSQL as Vector database: Create LLM Apps with pgvector (link)
  • Simplifying RAG with PostgreSQL and PGVector (link)
  • Build a question-answer bot natively using Postgres extensions (link)
  • Use pgvector and Hugging Face to Build an Optimized FAQ Search with Sentence Similarity (link)

RLHF

  • Reinforcement Learning from Human Feedback - Book (link)

tiktokenizer

vLLM