Skip to main content

haiku.rag-slim

The core of haiku.rag, agentic RAG on LanceDB, Pydantic AI and Docling, with every heavy dependency an optional extra.

Most users want haiku.rag, which is this package with Docling, the VoyageAI and Cohere embedders, every reranker and the terminal UI.

Installation

Python 3.12 or newer.

uv pip install haiku.rag-slim
uv pip install 'haiku.rag-slim[docling]'          # PDF, DOCX, PPTX, XLSX, HTML, EPUB, LaTeX, email and image conversion
uv pip install 'haiku.rag-slim[docling,anthropic,cross-encoder]'

The core includes OpenAI and Ollama support, the MCP server and Logfire. Without docling, documents can be converted through docling-serve.

Extras: docling, tui, voyageai, cohere, zeroentropy, cross-encoder, jina, s3, ingester, and one per model provider: anthropic, google, groq, mistral, bedrock, vertexai. Ollama and any OpenAI-compatible endpoint need none. Installation lists what each provides.

Documentation

Quick start, CLI, Python API and MCP setup: ggozad.github.io/haiku.rag.

Metadata

Release files for haiku.rag-slim 0.105.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for haiku.rag-slim 0.105.0
File Size Uploaded Provenance Actions
haiku_rag_slim-0.105.0.tar.gz 340.5 kB Without provenance Details for haiku_rag_slim-0.105.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for haiku.rag-slim 0.105.0
File Interpreter ABI Platform Actions
haiku_rag_slim-0.105.0-py3-none-any.whl Python 3 none any Details for haiku_rag_slim-0.105.0-py3-none-any.whl

Total release size: 771.1 kB

Release files / haiku_rag_slim-0.105.0.tar.gz

Download URL haiku_rag_slim-0.105.0.tar.gz
Size 340.5 kB
Tags Source
SHA-256 checksum
How to use checksums
df036866d26670e28b830d1d9162ab3d1f05319f863b9280020bacce267ce4f1
BLAKE2b-256 checksum
How to use checksums
7499aae13463cabd6774bccdd83af7d5fcb9e6125ac414b76cedd47cae8ba2b3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.18

Release files / haiku_rag_slim-0.105.0-py3-none-any.whl

Download URL haiku_rag_slim-0.105.0-py3-none-any.whl
Size 430.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
f10c2258b329814b59364b98a53e025540caa5853d5dc9e3f7510377d173614e
BLAKE2b-256 checksum
How to use checksums
2c439f8051a3ad15d077ef70edf812b9f1bb28ee63d3d6a417067539e827592d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.18

Security for haiku.rag-slim 0.105.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.105.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page