Self-Reflective RAG Archives

Fixing Ollama Connection Refused (HTTP 11434) in Python and Docker

When calling a local Ollama instance from Python scripts, AI agents, or Docker containers, you may encounter:…

Fixing CUDA Out of Memory (OOM) When Serving DeepSeek-R1 with vLLM

When deploying DeepSeek-R1 (such as DeepSeek-R1-Distill-Qwen-14B or 32B) using vLLM, encountering a sudden torch.cuda.OutOfMemoryError: CUDA out of memory during startup or high concurrency is one of the most common issues developers face.…

Fixing Common LangChain Memory Deprecation and Migration to LangGraph – Short note

When building modern Python applications and AI pipelines, engineers frequently need a fast, reliable solution for langchain conversationbuffermemory deprecated. Instead of sifting through massive frameworks, here is the direct, copy-paste implementation with error handling.…

Corrective RAG (CRAG) in Python with LangGraph: Building Self-Reflective Retrieval Pipelines with Document Grading, Fallback Web Search, and Hallucination Gates

TechJunkGigs

Engineering Tools

Core Topics