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>

corpus/epa_ppls/241-441.md

@@ -0,0 +1,68 @@
+# BEYOND
+
+- EPA Reg No: **241-441**
+- Registrant: BASF AGRICULTURAL SOLUTIONS US LLC
+- Signal word: Caution
+- Active ingredients: Imazamox (12.1%)
+- Label accepted: 2024-04-22
+- Source PDF: https://www3.epa.gov/pesticides/chem_search/ppls/000241-00441-20240422.pdf
+
+---
+April 22, 2024
+Christa Ellers-Kirk
+Federal Registration Manager
+BASF Corporation, 26 Davis Drive
+Research Triangle Park, NC 27709-3528
+Subject: Notification per PRN 98-10 – add not for use in California on Prostrate pigweed, 
+Palmer amaranth (pigweed), Prickly sida, and Jerusalem artichoke.
+Product Name: Beyond
+ EPA Registration Number: 241-441
+ Application Date: 05/10/2023
+ Case Number: 00474577
+Dear Christa Ellers-Kirk: 
+The Agency is in receipt of your Application for Pesticide Notification under Pesticide 
+Registration Notice (PRN) 98-10 for the above referenced product. The Registration Division 
+(RD) has conducted a review of this request for its applicability under PRN 98-10 and finds that 
+the action requested falls within the scope of PRN 98-10. 
+The label submitted with the application has been stamped “NOTIFICATION” and placed in our 
+records.
+Should you wish to add/retain a reference to the company’s website on your label, then please 
+be aware that the website becomes labeling under the Federal Insecticide, Fungicide, and 
+Rodenticide Act (FIFRA) and is subject to review by the Agency. If the website is false or 
+misleading, the product would be misbranded and unlawful to sell or distribute under FIFRA 
+section 12(a)(1)(E). 40 CFR 156.10(a)(5) lists examples of statements EPA may consider false or 
+misleading. In addition, regardless of whether a website is referenced on your product’s label, 
+claims made on the website may not substantially differ from those claims approved through 
+the registration process. Therefore, should the Agency find or if it is brought to our attention 
+that a website contains false or misleading statements or claims substantially differing from the 
+EPA approved registration, the website will be referred to the EPA’s Office of Enforcement and 
+Compliance.
+
+Page 2 of 2
+EPA Reg. No. 241-441
+Case Number 00474577
+If you have any questions, please contact Francisco Llarena-Arias at 202-566-2816 or at llarena-
+arias.francisco@epa.gov.
+ 
+ 
+ 
+ 
+Sincerely, 
+ 
+ 
+ 
+ 
+ 
+Francisco Llarena-Arias 
+For Lydia Crawford, 
+Acting Product Manager 24 
+Fungicide & Herbicide Branch 
+Registration Division (7505P) 
+ 
+ 
+ 
+ 
+ 
+ 
+ 
+Enclosure