Skip to content
Skill

rag-service

by papdawin

AI Summary

A tenant-specific RAG service that enables voice assistants to search and answer questions using company-supplied knowledge (locations, hours, contact info). Useful for SaaS platforms serving multiple companies with shared LLM infrastructure.

Install

Copy this and paste it into Claude Code, Cursor, or any AI assistant:

I want to install the "rag-service" skill in my project.

Please run this command in my terminal:
# Install skill into the correct directory (11 files)
mkdir -p .claude/skills/rag && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/rag/SKILL.md "https://raw.githubusercontent.com/papdawin/customer-service-assistant/master/rag/skill.md" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/rag/Dockerfile "https://raw.githubusercontent.com/papdawin/customer-service-assistant/master/rag/Dockerfile" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/rag/app.py "https://raw.githubusercontent.com/papdawin/customer-service-assistant/master/rag/app.py" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/rag/config.py "https://raw.githubusercontent.com/papdawin/customer-service-assistant/master/rag/config.py" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/rag/embeddings.py "https://raw.githubusercontent.com/papdawin/customer-service-assistant/master/rag/embeddings.py" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/rag/index.py "https://raw.githubusercontent.com/papdawin/customer-service-assistant/master/rag/index.py" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/rag/llm.py "https://raw.githubusercontent.com/papdawin/customer-service-assistant/master/rag/llm.py" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/rag/models.py "https://raw.githubusercontent.com/papdawin/customer-service-assistant/master/rag/models.py" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/rag/requirements.txt "https://raw.githubusercontent.com/papdawin/customer-service-assistant/master/rag/requirements.txt" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/rag/retrieval.py "https://raw.githubusercontent.com/papdawin/customer-service-assistant/master/rag/retrieval.py" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/rag/token_utils.py "https://raw.githubusercontent.com/papdawin/customer-service-assistant/master/rag/token_utils.py"

Then restart Claude Code (or reload the window in Cursor) so the skill is picked up.

Description

Tenant-specific RAG service for company knowledge in the voice assistant platform.

Purpose

Enable each company to supply its own information (e.g., location, opening hours, contact and reachability details) so the voice assistant can search and answer accurately. Each tenant has its own index; the LLM is shared across tenants.

Interfaces

• HTTP GET /health for index and model status. • HTTP POST /query for question answering and timing data.

Models

• Embedding model from EMBED_MODEL. • Shared LLM client llm from llm module.

Libraries

• fastapi • stdlib: time, contextlib

Discussion

0/2000
Loading comments...

Health Signals

MaintenanceCommitted 1mo ago
Active
AdoptionUnder 100 stars
0 ★ · Niche
DocsREADME + description
Well-documented

GitHub Signals

Issues0
Updated1mo ago
View on GitHub
No License

My Fox Den

Community Rating

Sign in to rate this booster

Works With

Claude Code