Skip to content
InfratoApp
Layers / Data / RAG / Retrieval and search / haiku.rag
H

haiku.rag

UNCLAIMED

RETRIEVAL AND SEARCHDOCUMENT PARSING

haiku.rag — Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server. Listed under Retrieval and search in the Data / RAG layer. 3 of 10 comparison attributes are recorded, each with the page it was read from.

Local-first agentic RAG. Index PDFs, web pages, and whole directories, then ask questions and get answers cited to page numbers and section headings. Hybrid search, reranking, and multimodal retrieval on embedded LanceDB.

3 OF 4 SIGNALS HELD · MISSING LOGO

Websiteggozad/haiku.rag

What it runs on, and what runs on it

3 cited edges
The differentiator

Computed from the stack graph, both directions. Every cited edge links the page it was read from; a vendor-added one links the vendor’s own source — this is the reason to be here rather than on the vendor’s own site.

RUNS ON / INTEGRATES WITH

USED BY

  • nothing recorded

Open-source signals

DOWNLOADS 30D
not measured
LAST COMMIT
2026-09-11
2026-09-12JSON

A HOLLOW RING IS UNMEASURED, NOT ZERO · WE DO NOT SUBSTITUTE A PARENT COMPANY’S REPOSITORY FOR A PRODUCT THAT HAS NONE

Price

We hold no price for this product.

This is open-source software: you can run it yourself and the licence costs nothing. If the project also sells a hosted service, we do not yet hold the page it prices it on. If that changes — or if you publish /.well-known/pricing.json — it appears here with a capture date.

How we read prices →

What its categories ask

3 answered · 7 unanswered

10 questions declared by Retrieval and search and Document parsing. Most rows across the directory read like these.

ATTRIBUTEANSWEREVIDENCE · SOURCE
Hybrid searchYes
“Hybrid vector and full-text search, optional reranking , section-aware context expansion, and image search with a multimodal embedder.”
2026-10-06
LicenceMIT
“MIT licensed.”
2026-10-06
RerankingYes
“Hybrid vector and full-text search, optional reranking , section-aware context expansion, and image search with a multimodal embedder.”
2026-10-06
Connectorsno answer on record
Deploymentno answer on record
OCRno answer on record
Open sourceno answer on record
Output formatsno answer on record
Public APIno answer on record
Table extractionno answer on record

A ROW WITH NO ANSWER IS NOT A ROW WITH A “NO” · A VENDOR MAY ANSWER A BLANK ONE, MARKED VENDOR CLAIMED WITH ITS SOURCE · A DOCUMENTED VALUE IS DISPUTED, NOT OVERWRITTEN, AND STAYS VISIBLE WHILE WE RE-READ THE SOURCE

Practitioner reviews

Nobody has written one yet.

A review here is structured, not a star: hardware, scale band, what broke in production, and whether you would choose it again.

NO PERCENTAGE IS SHOWN UNDER FIVE REVIEWS · NO STAR RATINGS, EVER

Also in this category

67 products in Retrieval and search. Comparison defaults to within the category — pairing this with a GPU cloud would produce a page that means nothing.

QdrantUSED BY 22COMPARE →
ChromaUSED BY 17COMPARE →
doclingUSED BY 15COMPARE →
LanceDBUSED BY 14COMPARE →
LlamaIndexUSED BY 14COMPARE →
OpenSearchUSED BY 12COMPARE →
Unstructured.ioUSED BY 12COMPARE →
ElasticsearchUSED BY 11COMPARE →

USED BY = LISTED PRODUCTS DEPENDING ON IT, IN THIS DIRECTORY

Frequently asked

Is haiku.rag open source?
Yes — it is listed as open source, and its repository is the source for the activity figures on this page rather than anything the project says about itself.
What does haiku.rag run on?
docling, LanceDB, Pydantic AI. Every one of those is an edge we recorded from documentation that states it, not an inference from what the two products have in common.
Does haiku.rag offer hybrid search?
Yes. Read from their own page: “Hybrid vector and full-text search, optional reranking , section-aware context expansion, and image search with a multimodal embedder.”.
Does haiku.rag offer reranking?
Yes. Read from their own page: “Hybrid vector and full-text search, optional reranking , section-aware context expansion, and image search with a multimodal embedder.”.
What does a blank mean on the haiku.rag page?
That nobody has told us, not that the answer is no. A hollow ring is "no answer on record", which is a different state from a recorded no — and the two look different on purpose. A blank is an absence of evidence, and this page shows how many of its questions are in that state rather than quietly leaving them out.
Where do the haiku.rag figures come from?
Each one is read from a public page — usually the vendor's own documentation or pricing page — and carries a link to it with the date it was read. Nothing here is estimated, averaged across sources, or inferred from a similar product. If a figure cannot be traced to a page, it is not published.
Can haiku.rag change what this page says?
They can claim the listing and supply or correct values, which are then labelled as theirs. They cannot remove the page, hide a comparison they are losing, or change a figure somebody else recorded with a source. Nothing on the page is for sale. How the site is paid for is set out under money and independence at /our-data#sec5.
Something here is wrong — how do I fix it?
Dispute the value. Every figure links to the page it was read from, so a dispute names the value and gives a source that contradicts it. That is the only lever anyone has over this page, and it is the same lever for the vendor, a competitor and a reader.

Cite this page

A model that quotes us should quote us correctly. The reading and its date sit inside the citation rather than beside it, because a quotation carrying only a URL goes wrong the week the URL changes.

infratoapp, “haiku.rag — Retrieval and search”, read 6 October 2026. Hybrid search: Yes as published at ggozad.github.io. https://www.infratoapp.com/products/haiku-rag

What haiku.rag can and cannot change here

Claiming the organisation lets its admins and editors change the tagline, description, logo, docs link and deployment model of every product that org owns — live, labelled as theirs, and logged. Answers to blank questions and dependencies go live too, marked as the owner’s and sourced; a documented answer cannot be overwritten. Everything else on this page is a stated fact with a dispute route: price, licence and OSS figures. Those columns are ungranted at the database level, so they are not a feature we withheld — they are a write that cannot happen. Name, category, website, pricing page and package names can be changed by the owner only through our review. A dispute never deletes a value; it marks it and publishes the correction.