Files
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

76 lines
2.5 KiB
JSON

{
"source": "bayer",
"source_key": "velum-prime",
"epa_reg_no": "264-1078",
"product_name": "Velum Prime Fungicide",
"product_class": "fungicide",
"registrant": null,
"active_ingredients": [
{
"name": "Fluopyram",
"cas": null,
"percent": null
}
],
"signal_word": null,
"label": {
"url": "https://cs-assets.bayer.com/is/content/bayer/Velum_Prime_Label1epdf",
"filename": "Velum_Prime_Label1epdf",
"accepted_date": null,
"last_modified": "2025-08-17T08:38:45+00:00",
"page_count": 37,
"text_layer": true
},
"supplemental_documents": [
{
"kind": "MSDS",
"title": "VELUM PRIME MSDS - Spanish",
"url": "https://cs-assets.bayer.com/is/content/bayer/Velum_Prime_MSDS1ejpdf",
"last_modified": "2026-01-30T14:14:35+00:00"
},
{
"kind": "MSDS",
"title": "VELUM PRIME MSDS - English",
"url": "https://cs-assets.bayer.com/is/content/bayer/Velum_Prime_MSDS1jepdf",
"last_modified": "2026-01-30T14:28:49+00:00"
},
{
"kind": "2EE",
"title": "Additional Soil Application Methods for VELUM PRIME for Nematode Suppression",
"url": "https://cs-assets.bayer.com/is/content/bayer/Velum_Prime2m_2EEpdf",
"last_modified": "2026-01-30T14:24:14+00:00"
},
{
"kind": "2EE",
"title": "For Application at a Reduced Rate in Stone Fruit",
"url": "https://cs-assets.bayer.com/is/content/bayer/Velum_Prime_2EE1vpdf",
"last_modified": "2026-01-30T14:21:49+00:00"
},
{
"kind": "2EE",
"title": "Management of Potato Early Dying & Verticillium Wilt with Programs of Emesto Silver, Velum Prime, & Luna Tranquility",
"url": "https://cs-assets.bayer.com/is/content/bayer/Velum_Prime_2EE2tpdf",
"last_modified": "2026-01-30T14:26:40+00:00"
},
{
"kind": "Bulletin",
"title": "Velum Prime California Product Bulletin",
"url": "https://cs-assets.bayer.com/is/content/bayer/Velum-Prime_California_2025pdf",
"last_modified": "2026-05-14T19:44:26+00:00"
},
{
"kind": "Bulletin",
"title": "Velum Prime Product Bulletin",
"url": "https://cs-assets.bayer.com/is/content/bayer/Velum-Prime_2025pdf",
"last_modified": "2026-05-14T19:38:37+00:00"
}
],
"source_urls": {
"product_page": "https://www.cropscience.bayer.us/crop-protection/fungicide/velum-prime-fungicide",
"label_api": null,
"label_index": null
},
"fetched_at": "2026-05-24T01:02:55.081944+00:00",
"scraper_version": "0.1.0"
}