danvics/haiku.rag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
haiku.rag/haiku_rag_slim
History
Yiorgis Gozadinos 6f976ef2a9
Share the LanceDB session across connections 
Every `Store` built its own connection with its own caches and discarded them on
close, so the index a vector query loads was refetched by the next connection.
On object storage that first fetch dominates: measured on a ~500k-chunk 2560-dim
corpus over a ~200ms link, the first query cost ~41s and the second ~3s, and a
new connection reusing the session cost ~7s instead of ~47s.

`connect_lancedb` now passes a process-wide session, keyed on the configured
cache sizes so a caller asking for different sizes gets its own.

Also sets `read_consistency_interval`, defaulting to 30s. It was None, meaning a
connection never re-checked for other processes' writes. Per-call connections hid
that; a shared session makes connections long-lived enough for a reader to go
stale against the ingester.

All three settings reject negatives at the config boundary. A negative cache size
raises OverflowError and a negative interval panics inside Lance, so neither is
catchable further in. Zero stays valid for both: no cache, and check on every
read.

The routing tests now assert the kwargs they care about rather than the full call
signature, since every connection carries the two new kwargs.
2026-08-18 14:58:17 +03:00
..
haiku/rag Share the LanceDB session across connections 2026-08-18 14:58:17 +03:00
LICENSE Restructure into uv workspace to support minimal and full installations 2025-11-04 17:59:12 +02:00
pyproject.toml Fix the MCP registry entry and fill in package and docs metadata 2026-08-18 14:37:05 +03:00
README.md Remove the mxbai reranking provider 2026-07-14 11:09:55 +03:00

README.md

haiku.rag-slim

Opinionated agentic RAG powered by LanceDB, Pydantic AI, and Docling - Core package with minimal dependencies.

haiku.rag-slim is the core package for users who want to install only the dependencies they need. Document processing (docling), and reranker support are all optional extras.

For most users, we recommend installing haiku.rag instead, which includes all features out of the box.

Installation

Python 3.12 or newer required

Minimal Installation

uv pip install haiku.rag-slim

Core functionality with OpenAI/Ollama support, MCP server, and Logfire observability. Document processing (docling) is optional.

With Document Processing

uv pip install haiku.rag-slim[docling]

Adds support for 40+ file formats including PDF, DOCX, HTML, and more.

Available Extras

Document Processing:

  • docling - PDF, DOCX, HTML, and 40+ file formats

Embedding Providers:

  • voyageai - VoyageAI embeddings

Rerankers:

  • cross-encoder - Local reranking via sentence-transformers
  • cohere - Cohere
  • zeroentropy - Zero Entropy

Model Providers:

  • OpenAI/Ollama - included in core (OpenAI-compatible APIs)
  • anthropic - Anthropic Claude
  • groq - Groq
  • google - Google Gemini
  • mistral - Mistral AI
  • bedrock - AWS Bedrock
  • vertexai - Google Vertex AI
# Common combinations
uv pip install haiku.rag-slim[docling,anthropic,cross-encoder]
uv pip install haiku.rag-slim[docling,groq]

Usage

See the main haiku.rag repository for:

  • Quick start guide
  • CLI examples
  • Python API usage
  • MCP server setup

Documentation

Full documentation: https://ggozad.github.io/haiku.rag/