Theory as well implementation of various type of rag structures
-
Updated
Dec 21, 2025 - Jupyter Notebook
#
speculative-rag
Here are 4 public repositories matching this topic...
An implementation of Speculative RAG exploring latency-quality trade-offs in multi-draft retrieval. Features batched parallel drafting via vLLM and log-probability verifier selection for fast, high-quality QA on a single A100 GPU.
nlp benchmarking gpu latency high-performance-computing throughput quantization faiss rag vector-search hpml a100 llm vllm retrieval-augmented-generation speculative-rag
-
Updated
Apr 28, 2026 - Python
AegisLogic (PCRA): A novel, local-first retrieval architecture (PCRA) for zero-hallucination Cyber Threat Intelligence. Synthesizes Graph (KuzuDB), Vector (Qdrant), and Temporal data via a LangGraph state machine. Includes empirical research on LLM evaluation metrics.
knowledge-graph cyber-threat-intelligence knowledge-graphs applied-research qdrant kuzudb llm-evaluation langgraph ragas graphrag agentic-rag speculative-rag
-
Updated
Jul 10, 2026 - Python
A high-performance Speculative RAG pipeline designed to reduce latency by combining fast draft generation and accurate verification using Groq Llama models, local HuggingFace embeddings, ChromaDB vector search, and end-to-end observability with Langfuse.
-
Updated
Jan 1, 2026 - Python
Improve this page
Add a description, image, and links to the speculative-rag topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the speculative-rag topic, visit your repo's landing page and select "manage topics."