mirror of
https://github.com/hanzoai/cdn.git
synced 2026-10-30 15:06:53 +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
3.0 KiB
JSON
48 lines
3.0 KiB
JSON
{
|
|
"author": "hanzo.ai",
|
|
"category": {
|
|
"description": "",
|
|
"examples": "",
|
|
"id": "utilities",
|
|
"name": "Utilities"
|
|
},
|
|
"changelog": "",
|
|
"created_at": "2025-04-30T15:50:54.259Z",
|
|
"description": "This tool reads an input CSV file, processes specified columns and combine them according to a user-defined prompt using an LLM, and adds the results to a new column in the output CSV. It supports error handling, retries, skips rows with empty cells, and provides detailed processing statistics. The output can either override the input file, or be saved to a new CSV file with a timestamp (e.g., \"input_processed_20250421_143022.csv\") and placed in the same folder as the input CSV.\n\nHow to Use :\n\n1. Configure Defaults : Set default CSV parameters : delimiter (e.g., ';'), encoding (e.g., 'utf-8'), quotechar (e.g., '\"'), max LLM retries (e.g., 2), and default output behavior ('new_file' or 'override').\n\n2. Prepare Input CSV file : Use an existing CSV file with the data to process.\n\n3. Provide a prompt with {} placeholders matching CSV column names (e.g., \"Summarize this product description in one sentence : {Description}.\", \"Population of {City} in {Date}, just write the number\").\n\n4. Specify New Column Name : Set the name for the new column to store LLM results (e.g., \"Summary\", \"Population_Size\").\n\n5. Provide Optional Data Description : Include a brief context about the data to guide the LLM (e.g., \"Product descriptions from a retail dataset.\").\n\n6. Set Custom CSV Parameters (Optional) : Customize delimiter, encoding, or quotechar to match the input CSV ; defaults from configuration apply if not specified.\n\n7. Choose Output Behavior (Optional) : Select 'new_file' for a new output file or 'override' to replace the input file; defaults to configuration if not set.\n\n8. Run the Tool : Execute with the provided inputs.\n\n9. Review Summary : Check the output message for stats (e.g., total rows, processed rows, empty cell errors, LLM errors) and the output CSV path.\n\n10. Verify Output CSV file : Inspect the resulting CSV with the new column containing LLM-processed data.\n\nHigh LLM Usage Warning : This tool makes an LLM call for each processed row, which may result in significant usage.",
|
|
"downloads": 6,
|
|
"icon_url": "",
|
|
"id": "csv-column-ai-combinator",
|
|
"install_command": "",
|
|
"license": "MIT",
|
|
"mcp_config": {
|
|
"args": [
|
|
"local:::__gilles_test2_sep_shinkai:::csv_column_ai_combinator"
|
|
],
|
|
"command": "any",
|
|
"env": {}
|
|
},
|
|
"name": "CSV column AI combinator",
|
|
"operating_system": [
|
|
"linux",
|
|
"macos",
|
|
"windows"
|
|
],
|
|
"path": "/tools/csv-column-ai-combinator",
|
|
"price": 0,
|
|
"readme": "",
|
|
"repository": "github.com/hanzoai/tools",
|
|
"router_key": "@hanzo/csv-column-ai-combinator",
|
|
"runner": "any",
|
|
"screenshots": [],
|
|
"tags": [
|
|
"CSV",
|
|
"processing",
|
|
"data",
|
|
"column",
|
|
"combine"
|
|
],
|
|
"type": "Tool",
|
|
"updated_at": "2025-04-30T15:50:54.259Z",
|
|
"version": "1.0.0"
|
|
}
|