Files
crop-chem-docs/corpus/bayer/corvus.json
T
justin a97107de46
Image rebuild (skip scrape) / build (push) Failing after 1h37m12s
docker: production image + Gitea Actions for monthly refresh
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>
2026-05-24 12:32:41 -04:00

129 lines
5.2 KiB
JSON

{
"source": "bayer",
"source_key": "corvus",
"epa_reg_no": "264-1066",
"product_name": "Corvus Herbicide",
"product_class": "herbicide",
"registrant": null,
"active_ingredients": [
{
"name": "Thiencarbazone-methyl",
"cas": null,
"percent": null
},
{
"name": "Isoxaflutole",
"cas": null,
"percent": null
}
],
"signal_word": null,
"label": {
"url": "https://cs-assets.bayer.com/is/content/bayer/Corvus_Herbicide_Label1mnpdf",
"filename": "Corvus_Herbicide_Label1mnpdf",
"accepted_date": null,
"last_modified": "2026-01-30T14:28:30+00:00",
"page_count": 17,
"text_layer": true
},
"supplemental_documents": [
{
"kind": "MSDS",
"title": "CORVUS HERBICIDE MSDS - English",
"url": "https://cs-assets.bayer.com/is/content/bayer/Corvus_Herbicide_MSDS1rtpdf",
"last_modified": "2026-01-30T14:31:12+00:00"
},
{
"kind": "MSDS",
"title": "CORVUS HERBICIDE MSDS - Spanish",
"url": "https://cs-assets.bayer.com/is/content/bayer/Corvus_Herbicide_MSDS1trpdf",
"last_modified": "2026-01-30T13:57:55+00:00"
},
{
"kind": "Supplemental",
"title": "For Weed Control in Field Corn, Seed Corn, & Corn Silage",
"url": "https://cs-assets.bayer.com/is/content/bayer/Corvus_Herbicide_Supplemental1nm_Labelpdf",
"last_modified": "2026-01-30T14:08:52+00:00"
},
{
"kind": "Supplemental",
"title": "For Weed Control in Field Corn, Seed Corn, & Corn Silage",
"url": "https://cs-assets.bayer.com/is/content/bayer/Corvus_Herbicide_Supplemental1mn_Labelpdf",
"last_modified": "2026-01-30T13:58:22+00:00"
},
{
"kind": "24C",
"title": "For Fall or Spring Applications to Control Kochia, Puncturevine, & Russian Thistle in Fallow or Eco-Fallow Fields In UNION, QUAY, CURRY, ROSSEVELT, & LEA Counties Only",
"url": "https://cs-assets.bayer.com/is/content/bayer/Corvus_Herbicide_Section_24c1yipdf",
"last_modified": "2026-01-30T13:55:21+00:00"
},
{
"kind": "2EE",
"title": "Corvus + Atrazine + Dicamba Tank Mixture for Early Postemergent Use in Corn to Control of Broadleaf & Glyphosate-Resistant Weeds",
"url": "https://cs-assets.bayer.com/is/content/bayer/Corvus1g_Herbicide_2EEpdf",
"last_modified": "2026-01-30T14:25:57+00:00"
},
{
"kind": "2EE",
"title": "CORVUS Herbicide + Atrazine + Dicamba Tank Mixture for Early Postemergent Use in Corn to Control of Broadleaf & Glyphosate-Resistant Weeds",
"url": "https://cs-assets.bayer.com/is/content/bayer/Corvus_Herbicide1n_2EEpdf",
"last_modified": "2026-01-30T14:07:19+00:00"
},
{
"kind": "24C",
"title": "For Fall or Spring Applications to Control Kochia, Puncturevine, & Russian Thistle in Fallow or Eco-Fallow Fields",
"url": "https://cs-assets.bayer.com/is/content/bayer/Corvus_Herbicide_Section_24c1impdf",
"last_modified": "2026-01-30T14:01:45+00:00"
},
{
"kind": "2EE",
"title": "Corvus + Atrazine + Dicamba Tank Mixture for Early Postemergent Use in Corn to Control of Broadleaf & Glyphosate-Resistant Weeds",
"url": "https://cs-assets.bayer.com/is/content/bayer/Corvus_Herbicide_2EE1mpdf",
"last_modified": "2026-01-30T14:18:22+00:00"
},
{
"kind": "24C",
"title": "For Fall or Spring Applications to Control Kochia, Puncturevine, & Russian Thistle in Fallow or Eco-Fallow Fields",
"url": "https://cs-assets.bayer.com/is/content/bayer/Corvus_Herbicide_Section_24c1lipdf",
"last_modified": "2026-01-30T14:18:25+00:00"
},
{
"kind": "2EE",
"title": "Corvus + Atrazine + Glyphosate Tank Mixture for Early Postemergent Use in Corn to Control of Broadleaf & Glyphosate-Resistant Weeds",
"url": "https://cs-assets.bayer.com/is/content/bayer/Corvus1f_Herbicide_2EEpdf",
"last_modified": "2026-01-30T14:23:36+00:00"
},
{
"kind": "2EE",
"title": "Instructions for Impregnation & Application on Dry Fertilizer",
"url": "https://cs-assets.bayer.com/is/content/bayer/Corvus_Herbicide_2EE1epdf",
"last_modified": "2026-01-30T14:28:54+00:00"
},
{
"kind": "2EE",
"title": "CORVUS Herbicide + Atrazine + Glyphosate Tank for Early Postemergent Use in Corn to Control of Broadleaf & Glyphosate-Resistant Weeds",
"url": "https://cs-assets.bayer.com/is/content/bayer/Corvus_Herbicide1m_2EEpdf",
"last_modified": "2026-01-30T14:18:25+00:00"
},
{
"kind": "2EE",
"title": "Corvus + Atrazine + Glyphosate Tank Mixture for Early Postemergent Use in Corn to Control of Broadleaf & Glyphosate-Resistant Weeds",
"url": "https://cs-assets.bayer.com/is/content/bayer/Corvus_Herbicide_2EE1npdf",
"last_modified": "2026-01-30T14:18:25+00:00"
},
{
"kind": "Bulletin",
"title": "Corvus Product Bulletin",
"url": "https://cs-assets.bayer.com/is/content/bayer/Corvus_2025pdf",
"last_modified": "2026-05-15T20:15:31+00:00"
}
],
"source_urls": {
"product_page": "https://www.cropscience.bayer.us/crop-protection/herbicide/corvus-herbicide",
"label_api": null,
"label_index": null
},
"fetched_at": "2026-05-24T00:57:06.689897+00:00",
"scraper_version": "0.1.0"
}