All Documents
3,528 documents available
Enhancing Budget-Aware Gating for Retrieval Augmented Generation (RAG)
Describes a thesis that designs and validates a Budget-Aware Uncertainty Gate (BAUG) to reduce token consumption and latency in multi-round RAG systems while maintaining answer quality.
JudgeIt (From SuperKnowa)- Automatic Eval Framework for Gen AI Pipelines
Automates GenAI pipeline evaluation using an LLM-as-a-judge, replacing slow human evaluation for RAG, multi-turn query rewrite, and agentic workflows.
Support Agent Chatbot Implementation Plan
Outlines a multi-channel customer support chatbot using Cloudflare Workers, RAG, and vector search across multiple businesses and personas.
NLP - Dialogue System
Lists 12 influential papers on multi-turn dialogue systems with conference venues and one-sentence summaries of each contribution.
Warp AI Coding Preferences for Ragex
Defines coding conventions, architecture, and implementation phases for an Elixir-based MCP server that performs hybrid RAG codebase analysis.
RAG Content Chunker Skill
Splits text or Markdown into token-counted chunks with deterministic IDs for RAG pipelines, supporting three chunking strategies.
❓ Frequently Asked Questions (FAQ)
Answers common questions about the AI Engagement Accelerator Kit's contents, setup, and usage for cross-functional GenAI project teams.
SPEC: MCP Mode Skill Generation
Replaces MCP mode's raw document dump with an LLM-generated SKILL.md file containing actionable instructions and code patterns.
llm-hallucination-survey
Curates a structured bibliography of 100+ papers on LLM hallucination, organised by evaluation, source, and mitigation.
📈 AlphaInsight Pro - Final Year Project Demo
Describes a production-deployed financial RAG demo app with PDF processing, semantic search, and AI Q&A via a Bloomberg-style terminal UI.
040: Memory Retrieval Pipeline
Defines a 4-stage memory retrieval pipeline with three retrieval modes, entity synthesis, dedup, contradiction detection, supersession, and file-backed freshness scanning.
Overview
Explains how LocusZoom.js retrieves and combines data from multiple sources using adapters, namespaces, and data operations.
RALM_Survey
Catalogs over 100 papers on retrieval-augmented language models, organized by definition, retriever, LM, enhancement, data source, and application.
README
Indexes 20+ KDB.AI sample notebooks covering vector database use cases from quickstarts to multimodal RAG and time-series search.
Information Retrieval
Curates a collection of foundational and neural IR resources, including papers, courses, and tutorials, with brief annotations.
Interactive RAG with MongoDB Atlas + Function Calling API
Explains interactive RAG with MongoDB Atlas and OpenAI function calling, enabling dynamic retrieval strategy adjustments.
Notes
Collects RAG optimization techniques, a MicroSaaS business plan, and a LangChain development strategy into a single personal reference note.
FlexFlow Serve: Low-Latency, High-Performance LLM Serving
Introduces FlexFlow Serve, an open-source compiler and distributed system for low-latency, high-performance LLM serving with speculative inference.
Curso de Chatbots - Implementaciones RAG
Teaches RAG through four Python implementations that load documents, generate embeddings, and answer queries using OpenAI or local models.
Quickly build Generative AI applications with Amazon Bedrock
Provides runnable code samples for image generation, text tasks, chatbots, and RAG using Amazon Bedrock foundation models.
FlashRAG
Explains FlashRAG's SKR method, retrieval algorithms (DPR, E5, BGE, ANCE), and multi-stage pipeline (recall, coarse ranking, fine ranking, reranking) for RAG systems.
softrag
Provides a local-first RAG library using SQLite with sqlite-vec for document, embedding, and cache storage in a single.db file.
Retrieval Augmented Generation
Implements a local Retrieval-Augmented Generation system using LangChain, Ollama, and Hugging Face models to augment LLM responses with context from a vector store.
Agentic RAG In This Project
Documents the agentic RAG pipeline, covering retrieval, entity extraction, tool planning, execution, and response synthesis with trace output.