justin
a97107de46
Image rebuild (skip scrape) / build (push) Failing after 1h37m12s
Dockerfile: self-contained image with corpus + Chroma + BM25 baked in. Drawbar's compose pulls + runs without volume mounts. Built from sources.json (labels schema), PRODUCT_NAME=crop_chem by default, HYBRID_SEARCH=true (always-on for production quality). RERANK_URL + OLLAMA_URL get set at compose time. .gitea/workflows/refresh.yml: monthly cron (1st @ 06:00 UTC) does full scrape → reindex → image push. Scrapes Bayer (~30 min) + EPA PPLS row-crop filtered (~7h). Skips reindex+push if no corpus diff. Tags pushed: :latest, :<sha12>, :corpus-<YYYY.MM.DD>. .gitea/workflows/image-only.yml: on-demand or auto on code-only pushes to main (paths: docs_mcp/, rag/, scrape/, requirements.txt, Dockerfile, sources.json). Reindexes from committed corpus, builds image, pushes. ~10 min vs ~9h full refresh. .gitignore: corpus/ now COMMITTED (4,159 labels, 265 MB of .md + sidecars). Lets image-only.yml rebuild indexes without re-scraping. chroma/ + bm25/ still gitignored (regenerable binary indexes). .dockerignore: drops venv, eval results, PLAN/README/CLAUDE.md, deploy/, .git/ — keeps the image lean. corpus + chroma + bm25 explicitly NOT in dockerignore (those go INTO the image). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
70 lines
2.4 KiB
JSON
70 lines
2.4 KiB
JSON
{
|
|
"source": "bayer",
|
|
"source_key": "roundup-powermax",
|
|
"epa_reg_no": "524-549-ZA",
|
|
"product_name": "Roundup PowerMAX Herbicide",
|
|
"product_class": "herbicide",
|
|
"registrant": null,
|
|
"active_ingredients": [
|
|
{
|
|
"name": "Glyphosate, N-(phosphonomethyl)glycine,in the form of its potassium salt",
|
|
"cas": null,
|
|
"percent": null
|
|
}
|
|
],
|
|
"signal_word": null,
|
|
"label": {
|
|
"url": "https://cs-assets.bayer.com/is/content/bayer/Roundup_PowerMAX_Herbicide_Bayer_Label2pdf",
|
|
"filename": "Roundup_PowerMAX_Herbicide_Bayer_Label2pdf",
|
|
"accepted_date": null,
|
|
"last_modified": "2026-01-30T14:03:23+00:00",
|
|
"page_count": 25,
|
|
"text_layer": true
|
|
},
|
|
"supplemental_documents": [
|
|
{
|
|
"kind": "MSDS",
|
|
"title": "ROUNDUP POWERMAX HERBICIDE MSDS - Spanish",
|
|
"url": "https://cs-assets.bayer.com/is/content/bayer/Roundup_PowerMAX_Herbicide2j_MSDSpdf",
|
|
"last_modified": "2025-08-17T08:38:44+00:00"
|
|
},
|
|
{
|
|
"kind": "MSDS",
|
|
"title": "ROUNDUP POWERMAX HERBICIDE MSDS - English",
|
|
"url": "https://preview1.assetsadobe.com/is/content/bayer/Roundup_PowerMAX_Herbicide2h_MSDSpdf",
|
|
"last_modified": "2025-05-27T23:23:09+00:00"
|
|
},
|
|
{
|
|
"kind": "Supplemental",
|
|
"title": "USE WITH ENLIST E3 SOYBEAN (Expires 2026-03-31)",
|
|
"url": "https://cs-assets.bayer.com/is/content/bayer/Roundup_PowerMAX_Herbicide_Bayer_Supplemental_Label1uppdf",
|
|
"last_modified": "2026-01-27T08:55:13+00:00"
|
|
},
|
|
{
|
|
"kind": "Supplemental",
|
|
"title": "USE WITH GT27 SOYBEAN",
|
|
"url": "https://cs-assets.bayer.com/is/content/bayer/Roundup_PowerMAX_Herbicide_Bayer_Supplemental_Label1uepdf",
|
|
"last_modified": "2026-01-27T08:55:13+00:00"
|
|
},
|
|
{
|
|
"kind": "Supplemental",
|
|
"title": "USE WITH AGRISURE GT CORN",
|
|
"url": "https://cs-assets.bayer.com/is/content/bayer/Roundup_PowerMAX_Herbicide_Bayer_Supplemental_Label1eupdf",
|
|
"last_modified": "2026-01-27T08:55:14+00:00"
|
|
},
|
|
{
|
|
"kind": "Bulletin",
|
|
"title": "Roundup PowerMAX Product Bulletin",
|
|
"url": "https://cs-assets.bayer.com/is/content/bayer/Roundup-PowerMAX_2025pdf",
|
|
"last_modified": "2026-05-19T20:30:31+00:00"
|
|
}
|
|
],
|
|
"source_urls": {
|
|
"product_page": "https://www.cropscience.bayer.us/crop-protection/herbicide/roundup-powermax-herbicide",
|
|
"label_api": null,
|
|
"label_index": null
|
|
},
|
|
"fetched_at": "2026-05-24T00:57:19.681926+00:00",
|
|
"scraper_version": "0.1.0"
|
|
}
|