RAG Q&A pipeline with QLoRA fine-tuning. FastAPI + Chroma + hybrid retrieval + cross-encoder rerank. Runs free on Apple Silicon via Ollama.
-
Updated
May 8, 2026 - Python
RAG Q&A pipeline with QLoRA fine-tuning. FastAPI + Chroma + hybrid retrieval + cross-encoder rerank. Runs free on Apple Silicon via Ollama.
An agentic LLM framework combining parallel reasoning, runtime Python execution, isolated sandboxes, and consensus-based answer aggregation.
RAG Q&A + autonomous triage agent for customer feedback. Built on Gemini free tier with ChromaDB, structured JSON validation, and deterministic routing.
Add a description, image, and links to the retrieval-augmented-generation- topic page so that developers can more easily learn about it.
To associate your repository with the retrieval-augmented-generation- topic, visit your repo's landing page and select "manage topics."