Blog

Table of Contents Building an Intelligent Chatbot with Qwen3 Instruct and Thinking Models Qwen3 Model Details Qwen3 Model Architecture: Dense Models, MoE Variants, and Dual-Mode Reasoning Qwen3 Training Data and Post-Training Pipeline for Reasoning and Instruction Following Qwen3 Benchmark Performance:…

Table of Contents Google DeepMind’s Gemma 4: MoE, Efficiency Tricks, and Benchmarks Gemma 4 Model Family Overview: E2B, E4B, 31B, and MoE 26B A4B Gemma 4 Capabilities: Reasoning, Multimodal AI, and Thinking Mode Gemma 4 Thinking Mode: Chain-of-Thought Reasoning Explained…

Table of Contents RAG Observability with Langfuse, vLLM, and FAISS Introduction to Production-Grade RAG and LLM Observability RAG Observability Architecture with Langfuse, vLLM, and FAISS Project Setup Building a Langfuse-Traced Retriever with FAISS Building a Traced LLM Wrapper for vLLM…

Table of Contents Run an Apache Airflow DAG with Docker Compose and PostgreSQL Project Structure PDF Parsing and Text Chunking Logic for Airflow DAG Docker Orchestration and Runtime for Airflow and FastAPI Running the Apache Airflow and FastAPI Document Ingestion…

Table of Contents Apache Airflow Document Ingestion Pipeline for RAG Systems Introduction to Production-Grade Document Ingestion Pipelines Why Airflow Instead of Cron Jobs or Celery? Apache Airflow Document Ingestion Pipeline Architecture Component 1: FastAPI Ingestion Service Component 2: Apache Airflow…

Table of Contents Manual Tracing, Scores, and Evaluation with Langfuse (Self-Hosted) Why Manual Tracing Matters for LLM Observability Decorator vs Manual Tracing: When to Use Which Manual Tracing with the Langfuse Low-Level API Why Manual Tracing Matters (Even If You…

Table of Contents LLM Observability with Self-Hosted Langfuse and vLLM Introduction to LLM Observability with Langfuse How Langfuse Fits into an LLM Observability Stack Langfuse Architecture for LLM Observability Why Understanding LLM Observability Architecture Matters Setting Up a Self-Hosted Langfuse…

Table of Contents Building and Training a Kimi-K2 Model Using DeepSeek-V3 Components Kimi-K2 vs DeepSeek-V3: Key Architecture Differences in LLM Design Mixture of Experts Scaling in Kimi-K2: Model Size, Sparsity, and Efficiency Attention Head Optimization in Kimi-K2 for Efficient Long-Context…

Table of Contents Semantic Caching for LLMs: TTLs, Confidence, and Cache Safety Why Semantic Caching for LLMs Requires Production Hardening Cache TTL in Semantic Caching: Preventing Stale LLM Responses MLOps Project Structure for Semantic Caching with FastAPI and Redis How…