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/352-500.md

@@ -0,0 +1,75 @@
+# DUPONT EXTRAZINE II 4L HERBICIDE
+
+- EPA Reg No: **352-500**
+- Registrant: CORTEVA AGRISCIENCE, LLC
+- Signal word: Warning
+- Active ingredients: Atrazine (10.4%); Cyanazine (32%)
+- Label accepted: 1999-01-15
+- Source PDF: https://www3.epa.gov/pesticides/chem_search/ppls/000352-00500-19990115.pdf
+
+---
+( 
+DuPont Agricultural 
+Products 
+" ...... A Growing Partnership With Nature" 
+/-15"- 91· I c9r)-/ ST(" 'LEMENTAL LABELING 
+EXTRAZINE"' II 4L HERBICIDE 
+MAXIMUM USE RATES 
+FOR 1999 - 2002 
+A EPTED 
+JAHU. EPA REG. NO. 352-500 
+AXIMUM USE RATES FOR 1999 - 2002 
+SE 
+! is a violation of Federal law to use this product in a manner 
+mconsistent with its labeling. 
+DuPont EXTRAZINE II 4L Herbicide is a liquid formulation 
+that can be applied alone or in combination with other herbicides 
+to control a wide variety of weeds in field corn, sweet corn, 
+popcorn, field corn grown for seed. The use rates specified in 
+this supplemental label supercede all specimen and packaging 
+labels for the year 1999. 
+CYANAZINE RATE LIMITS 
+One pound of EXTRAZINE II 4L contains 0.75 Ib cyanazine . . active ingredient (a.i.). Rate limits for 1999 - 2002 descnbed 
+• This product may not be sold or distributed after September 30, 
+2002. 
+• This product may not be used after December 31, 2002. 
+When statellocal requirements regarding the use of cyanazine 
+(including lower maximum use rates andlor higher set-backs) 
+differ from the label, the more restrictive/protective require· 
+ments apply. 
+IMPORTANT PRECAUTIONS 
+( 
+below apply to cyanazine from all sources. Adhere to the rate 
+recommendations in this label and observe the rate limits and 
+other restrictions for the time period indicated. 
+Refer to the EXTRAZINE II 4 L label for weed control, use rate, 
+mixing and other use instructions. Use rates vary according to 
+application type, ,timing and soil type. Read and follow all use 
+directions and precautions but do not exceed the maximum rates 
+listed above. 
+1999: 
+• Do not apply more than 4.0 quarts of EXTRAZINE II 4L per 
+acre per year. 
+• An enclosed cab is required when applying EXTRAZINE II 
+4L. An enclosed cab must have a nonporous barrier that totally 
+surrounds the occupants and prevents contact with pesticides 
+outside of the cab. 
+2000-2002 
+• Do not apply more than 1.3 quarts of EXTRAZINE II 4L per 
+acre per year to any crop land. 
+IMPORTANT 
+BEFORE USING "EXTRAZINE II 4L" READ 
+AND FOLLOW ALL APPLICABLE DIREC­
+TIONS, RESTRICTIONS AND PRECAUTIONS 
+ON THE EPA-REGISTERED LABEL. 
+This bulletin contains new or supplemental instructions for use 
+of this product which does not appear on the EPA-registered 
+package labels. Follow these instructions carefully. 
+This label must be in the possession of the user at the time of 
+application. 
+EXTRAZINE II 4L is a Restricted Use Pesticide 
+An enclosed cab is required when applying D·1l1198 
+EXTRAZINE II 4L. 
+For product information call 1-888-6-DUPONT 
+© 1998 E. I. du Pont de Nemours and Company, Agricultural Products, Wilmington, Delaware 19898 
+H - Page I of I