GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing github.com — Build software better, together
#
llmengineeringHere are 6 public repositories matching this topic...Language: All
Filter by language
PromptFlow is a curated, open-source hub of production-ready prompts designed specifically for modern AI developer tools like Cursor, V0.dev, Windsurf, and Lovable. It's the ultimate toolkit for developers, teams, and organizations looking to harness the full power of AI-assisted development.
learning and always developing
This repository is a practical overview of inference engineering for Large Language Model deployment, with vLLM as the serving engine. It is meant to help you understand not only how to start a model server, but also how to reason about throughput, latency, batching, quantization, KV cache memory, and GPU VRAM requirements before deploying a model.
Hands-on implementation of structured tool use, explicit agent loops, persistent state, REST APIs, and human-in-the-loop execution controls.
python sqlalchemy rest-api openai pydantic fastapi aiengineering agenticai llmengineering humanintheloop structuredoutputs
A RAG system that replaces standard BM25/FAISS retrieval with a fully learned neural retrieval stack - including a fine-tuned bi-encoder, a cross-encoder reranker, ColBERT-style late interaction scoring, and a locally hosted LLM generator. Built entirely with free and open-source tools.
nlp tensorflow pytorch machinelearning informationretrieval faiss semanticsearch rag mlops mlflow fastapi colbert crossencoder beir llm ollama llmengineering neuralretrieval
Local-first AI legal research system for UK contract law with IRAC-enforced reasoning, hybrid RAG with reranking, and on-device LLM inference. Designed to deliver grounded, citation-backed legal analysis via text and voice, no external APIs
Add this topic to your repoTo associate your repository with the llmengineering topic, visit your repo's landing page and select "manage topics." |
| You are visitor 01402520 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |