“RAG”

MCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.

Retrieve relevant excerpts from a project's text files without loading entire files into context.

Apple developer docs and WWDC transcripts with RAG retrieval and Jev relevance ranking.

Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks.

Set up RAG / semantic search with laravel/ai — a vector column + embeddings ingestion + similarity search (and optional reranking).

Repository intelligence, code graph, history, papertrail, and cross-agent memory for coding agents.

Build retrieval and RAG with Anvia — chunking, embeddings, vector stores, knowledge graphs, filters, and search tools.

Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search pipelines…

Use for RAG pipelines, retrieval augmented generation, ColBERTv2, context retrieval, multi-hop RAG, and grounded DSPy answers.

Build a local RAG index by splitting a document and embedding its chunks using the on-device engine (private/offline).

Use when building self-correcting retrieval systems for AI agents.

Easy-to-setup local RAG server with minimal configuration

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK.

Query historical test runs, failures, and API specs from the SQLite RAG index via MCP.

Local-first RAG engine with MCP server for AI agent integration.

Use when needing global or relational understanding of codebases or knowledge corpora.

Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval

RAG 模式 —— 检索增强生成架构设计、分块策略、向量检索优化与评估方法

Use quando precisar buscar contexto vetorial, gerar embeddings, ou consultar o RAG.

RAG pipeline design — chunking, embeddings, retrieval strategies, evaluation, and demo patterns.

Discovers requirements, and generates architectural, design, and deployment guidance for a retrieval-augmented generation (RAG)-capable enterprise search…

RAG (Retrieval-Augmented Generation) system for affidavit workflows.

Detect persistent-memory poisoning and RAG/knowledge-base contamination via dialogue testing.

Use for RAG, vector search, semantic search, embeddings, knowledge bases, long-term agent memory, and grounding answers in the project's own documentation.