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/1812-366.md

@@ -0,0 +1,68 @@
+# CYNEX 4L
+
+- EPA Reg No: **1812-366**
+- Registrant: GRIFFIN L.L.C.
+- Signal word: Warning
+- Active ingredients: Cyanazine (43%)
+- Label accepted: 1999-02-04
+- Source PDF: https://www3.epa.gov/pesticides/chem_search/ppls/001812-00366-19990204.pdf
+
+---
+FQb-04-99 OB:50A VQrn white ... I 
+501 922-6724 P.03 
+VfYi:35 I~ /.) - 3{.{' 0'-1/ cI1 f{~1 C I. f, '2 
+I 
+SUPPLIMENTAL LABELING 
+CY ·PRO® 4L HERBICIDE 
+EPARq. No.ISI2-J66 
+MAXIMUM USE RATES FOR 1999-2002 
+DIRECTIONS FOR USE 
+ACCEPTED 
+FEB 4 /%9 
+It is • violation of Federal law to use this product in a manner inconsistent with its 
+labeling. 
+Griffin CY -PRO 4L Herbicide is a liquid formulation that can be applied alone or 
+in combination with other herbicides to comrol a wide variety of weeds in field 
+corn, sweet corn, popcorn, field com grown for seed, and cotton. The use rates 
+specified in this IlUpplementallabei supercede all specimen and packaging labels fur 
+the year 1999. 
+CV ANAZINE RATE LIMITS 
+One quart ofCY-PRO 4L contains lIb. cyanazine activeinsrcdient (a.i.) Rate 
+limit. for ] 999·2002 detcribed below apply to cyanazine from all sources. Adhere 
+to the rate recommendations in this label and observe the rate limits and other 
+restlictions for the time period indicated. 
+1999: 
+• Do not apply more than J quarts ofCY·PRO 4L per acre per year. 
+• An eooIosed cab is required when applying CY -PRO 4L. An enclosed cab must 
+have a nonporous barrier that totally IUITOIII1da the occupantS and prevents 
+coutact with pesticides outSide of the cab. 
+201)0..2001 
+• Do not apply more than I quart ofCY -FRO 4L per acre per year to any crop 
+land. 
+• An enclosed cab ia required when applyiDg CY -PRO 4L. 
+• This product may not be sold or diltributed after September 30, 2002. 
+• This product may not be used der December J I, 2002. 
+, I I
+
+FQb~~4-99 08:50A VQrn white 501 922-6724 
+When statell<K:al requirements regarding the use of cyanazine (including lower 
+maximum use rates and/or higher aet-blcb) dift'er from the label, the more 
+restrWtivclprotective requirements apply. 
+IMPORTANT PRECAUTIONS 
+Refer to the CY-PRO 4L label for weed control, use rate. mixing and other use 
+instructions. Use rates vII)' according to the application type, timing and soil type. 
+Read and follow aU use directions and precautions but do not exceed the maximum 
+rates listed above. 
+IMPORTANT 
+BEFORE USING "O'-PRO 4L" READ AND FOLLOW ALL 
+APPUCABLE DIRECTIONS, RESTRICTIONS AND PRECAUTIONS ON 
+THE EPA-REGISTERED LABEL 
+Thi, buI1etin contains new or supplemental instructions for use ofthia product, 
+which does not appear on the EPA-registered package labels. FoUow these 
+instNctions carefully. 
+This label must be in the possession of the user at the time of application. 
+CY -PRO 4L is a Restricted Use Pesticide 
+For prodact iafOl'llUltioa cd 1-800-%37-1854 
+. I 
+P.04 
+o 'l ).-.