skills.rest
KirillTrubitsyn
KirillTrubitsynCOMMUNITY
Explore all skills by this author →
GitHub

rag-kit

Enable retrieval-augmented chat with document context and web results.

3|Updated Jan 4, 2026
Search Tags:#grok#gemini#web-search#knowledge-base#ai-chat#rag-kit
One-click install
npx skills add https://github.com/KirillTrubitsyn/kirilltrubitsyn-claude-skills --skill rag-kit
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-kit
Source: https://github.com/KirillTrubitsyn/kirilltrubitsyn-claude-skills/tree/main/.claude/skills/rag-kit
Command: npx skills add https://github.com/KirillTrubitsyn/kirilltrubitsyn-claude-skills --skill rag-kit

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @google/generative-ai, and includes scripts (resource) components.

What problem does it solve?

This skill provides a ready-to-use framework to build AI chat interfaces that reason over a knowledge base of documents, enabling context-aware responses without leaking sensitive data.

Core Features & Use Cases

  • RAG-backed chat service that retrieves information from Grok Collections and optional web results.
  • Easy integration with Gemini models and a modular pipeline (grok client, chat service, document upload).
  • Use cases include law firms, internal knowledge bases, and enterprise support chatbots requiring contextual accuracy.

Quick Start

Copy the rag-kit files into your project and wire up the API endpoint to start a context-aware chat experience.

Frequently Asked Questions about rag-kit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build an AI chat with document context from my enterprise knowledge base?▼

A retrieval-augmented chat service processes your uploaded documents through a modular pipeline, combining Grok Collections and optional web search results to provide context-aware answers for enterprise knowledge bases and legal archives.

Can I use Gemini models for retrieval-augmented chat with internal documents?▼

Yes, the framework provides configuration options to integrate Gemini models for retrieval-augmented chat. It processes internal documents through a modular pipeline to generate context-aware responses while preventing sensitive data leakage.

Does the RAG pipeline support combining live web search results with stored enterprise documents?▼

Yes, the RAG pipeline supports combining live web search results with stored enterprise documents. It features configurable web search options and domain prioritization to augment your knowledge base with real-time external data.

What is the best way to set up a context-aware chatbot for legal archives?▼

The best way to set up a context-aware chatbot for legal archives is implementing a modular pipeline with a document upload service and retrieval client. This enables accurate question answering using stored legal content directly.

Do I need the Google generative AI dependency to run rag-kit?▼

Yes, you need the Google generative AI dependency to run this framework. It is required to enable the Gemini model configurations and power the chat service within the retrieval-augmented pipeline.

Related Skills

Explore More Software Engineering Skills→
PaldomPaldom
1

unstructured-pdf-generation

Generate synthetic PDF documents with JSON evaluation files for RAG systems.

Community
Intermediate
giosuetedeschi-specgiosuetedeschi-spec

prompt-caching

Implement multi-level caching strategies for LLM interactions.

Community
Advanced
OpenLAIROpenLAIR
1.0k

chroma

Store and search embeddings with a four-function API for a local vector database.

Official
Intermediate
jd-opensourcejd-opensource
299

pentest-ai-llm-security

Identifies and exploits AI/LLM security vulnerabilities in enterprise deployments using Garak and Burp Suite workflows.

Official
Advanced