attune-rag 0.1.6

Lightweight, LLM-agnostic RAG pipeline with pluggable corpora. Works with Claude, OpenAI, Gemini, or any LLM.

attune-rag

Lightweight, LLM-agnostic RAG pipeline with pluggable corpora. Works with Claude, OpenAI, Gemini, or any LLM.

• No LLM SDK at install time. All provider deps are optional extras.
• Pluggable corpus. Use attune-help (the default), any markdown directory, or your own CorpusProtocol.
• Returns a prompt string by default — send it to whatever LLM you like. Optional provider adapters ship convenience wrappers.
• Optional hybrid retrieval. QueryExpander and LLMReranker layer Claude Haiku on top of keyword retrieval to improve recall and precision — both opt-in, both fail-safe.

Install

pip install attune-rag                     # core only
pip install 'attune-rag[attune-help]'      # + bundled help corpus
pip install 'attune-rag[claude]'           # + Claude adapter
pip install 'attune-rag[openai]'           # + OpenAI adapter
pip install 'attune-rag[gemini]'           # + Gemini adapter
pip install 'attune-rag[all]'              # everything

Quick start — Claude

pip install 'attune-rag[attune-help,claude]'

import asyncio
from attune_rag import RagPipeline

async def main():
    pipeline = RagPipeline()  # defaults to AttuneHelpCorpus
    response, result = await pipeline.run_and_generate(
        "How do I run a security audit with attune?",
        provider="claude",
    )
    print(response)
    print("\nSources:", [h.entry.path for h in result.citation.hits])

asyncio.run(main())

Quick start — OpenAI

pip install 'attune-rag[attune-help,openai]'

response, result = await pipeline.run_and_generate(
    "...", provider="openai", model="gpt-4o",
)

Quick start — Gemini

pip install 'attune-rag[attune-help,gemini]'

response, result = await pipeline.run_and_generate(
    "...", provider="gemini", model="gemini-1.5-pro",
)

Quick start — custom corpus, any LLM

from pathlib import Path
from attune_rag import RagPipeline, DirectoryCorpus

pipeline = RagPipeline(corpus=DirectoryCorpus(Path("./my-docs")))
result = pipeline.run("How do I...?")

# Send result.augmented_prompt to whatever LLM you use.
# The pipeline itself does NOT call an LLM unless you use
# run_and_generate or call a provider adapter yourself.

Hybrid retrieval (optional)

QueryExpander and LLMReranker require the [claude] extra and an ANTHROPIC_API_KEY. Both are opt-in and fail-safe — any API error falls back to keyword-only order automatically.

from attune_rag import RagPipeline, LLMReranker, QueryExpander

# Reranker only (recommended for precision):
pipeline = RagPipeline(reranker=LLMReranker())

# Expander + reranker (max coverage):
pipeline = RagPipeline(
    expander=QueryExpander(),
    reranker=LLMReranker(),
)

Dashboard

attune-rag dashboard show    # live terminal dashboard
attune-rag dashboard render --out report.html  # HTML snapshot

Status

v0.1.6. Part of the attune ecosystem (attune-ai, attune-help, attune-author).

License

Apache 2.0. See LICENSE.