mirror of
https://github.com/hanzoai/cdn.git
synced 2026-11-02 21:02:16 +00:00
zeekayandHanzo Dev
edabf3842c
The Market read plane is files and nothing else. This makes that actually true
and actually deployable.
Catalog: was 10 mock "zoo-eco-agent" placeholders + 5 mock tools, which every
app would have shown to every user. Now generated from the curated flatfile
catalog (hanzoai/store data/{agents,tools}) -> 23 agents + 179 tools, each with
its own detail document. Drops purchases.json: per-user state has no business
on a public CDN. Strips upstream icon URLs, which are expired presigned R2 links
that carry an AWS credential + signature in the query string.
Versioning: index.json gains `schema` (breaking-shape gate, so a client that
does not recognise it keeps its bundle) and a `version` that is a content digest
over every served document. It changes iff what we serve changes, which is what
makes a deploy checkable rather than hopeful.
One writer: gen-market.py -> market.py with `gen` and `check`. It emits the CDN
documents AND each app's offline bundle, so the two cannot disagree about the
schema; `check` re-derives the digest and validates counts, ids, dangling
featured references and per-tool details, with no network and no other checkout.
Deploy: upload, then purge the Cloudflare edge for exactly the URLs written,
then verify the live manifest matches the repo and fail if it does not. Also
resolves wrangler once instead of re-resolving it per object.
CI: hanzo.yml + a 7-line cicd.yml importing hanzoai/ci. Static assets, so no
images:/deploy: — test: is the gate.
Co-authored-by: Hanzo Dev <[email protected]>
48 lines
1.9 KiB
JSON
48 lines
1.9 KiB
JSON
{
|
|
"author": "hanzo.ai",
|
|
"category": {
|
|
"description": "",
|
|
"examples": "",
|
|
"id": "education",
|
|
"name": "Education"
|
|
},
|
|
"changelog": "",
|
|
"created_at": "2025-03-17T13:20:51.486Z",
|
|
"description": "This tool extracts text from a PowerPoint presentation, creates a lesson text about it, and generates an audio file of the lesson. It extracts content slide by slide and shape by shape. It uses OCR to extract text from image shapes (using Tesseract). It generates a detailed lesson text about the PPTX using a LLM and optional additional instructions. Optionally, it generates a mp3 audio file of the lesson using ElevenLabs text-to-speech. This tool requires Tesseract to be installed for OCR. It also requires the tool \u201cElevenLabs Text to Speech\u201d from the Hanzo AI Store, and an API key for ElevenLabs text-to-speech if choosing to generate audio files. You can download Tesseract from here : https://github.com/UB-Mannheim/tesseract/wiki. You can get an ElevenLabs API key here : https://elevenlabs.io/developers.",
|
|
"downloads": 29,
|
|
"icon_url": "",
|
|
"id": "pptx-content-extractor-with-ocr-and-audio-lesson-generator",
|
|
"install_command": "",
|
|
"license": "MIT",
|
|
"mcp_config": {
|
|
"args": [
|
|
"local:::__gilles_test2_sep_shinkai:::pptx_content_extractor_with_ocr_and_audio_lesson_generator"
|
|
],
|
|
"command": "any",
|
|
"env": {}
|
|
},
|
|
"name": "PPTX content extractor with OCR and audio lesson generator",
|
|
"operating_system": [
|
|
"linux",
|
|
"macos",
|
|
"windows"
|
|
],
|
|
"path": "/tools/pptx-content-extractor-with-ocr-and-audio-lesson-generator",
|
|
"price": 0,
|
|
"readme": "",
|
|
"repository": "github.com/hanzoai/tools",
|
|
"router_key": "@hanzo/pptx-content-extractor-with-ocr-and-audio-lesson-generator",
|
|
"runner": "any",
|
|
"screenshots": [],
|
|
"tags": [
|
|
"pptx",
|
|
"powerpoint",
|
|
"lesson",
|
|
"presentation",
|
|
"audio"
|
|
],
|
|
"type": "Tool",
|
|
"updated_at": "2025-03-17T13:20:51.486Z",
|
|
"version": "1.0.0"
|
|
}
|