“RAG”

Build a RAG (Retrieval-Augmented Generation) pipeline — chunk data, embed, store in vector DB, query at inference, inject into system prompt.

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

Consulta el corpus histórico de Producto de Olé (brain + intakes + PRDs + decision-logs + findings) indexado en Bedrock Knowledge Bases y devuelve respuestas…

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

Answer questions from indexed document evidence.

Semantic search over locally indexed documents, notes, images, and videos

Responde preguntas sobre documentación técnica, CVEs, políticas y contenido indexado en ChromaDB.

从知识库检索扫地机器人专业资料。当用户询问产品功能、故障排除、使用技巧、保养维护、选购建议等专业问题时使用。

Build retrieval-augmented workflows with clear ingestion, retrieval, and answer boundaries.

Local knowledge retrieval and indexing skill.

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…

Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup

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.

Design RAG pipelines: chunking, retrieval evaluation, and architecture.