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/5905-91.md

@@ -0,0 +1,41 @@
+# HELENA BRAND 2,4-D BUTYL ESTER 6 OSO
+
+- EPA Reg No: **5905-91**
+- Registrant: HELENA AGRI-ENTERPRISES, LLC, D/B/A HELENA CHEMICAL COMP
+- Signal word: Caution
+- Active ingredients: 2,4-dichlorophenoxyacetic acid, butyl ester (80%)
+- Label accepted: 1972-04-21
+- Source PDF: https://www3.epa.gov/pesticides/chem_search/ppls/005905-00091-19720421.pdf
+
+---
+o B S I· R V I· Till S I· P R I:C AUT I 0 :-,; S 
+. ~ ~ I .,. '. I' • ~: ~!\ .. , I,. I I., I "\,!.. II'" ',. ... i ; .. !",' . \ 
+.. ~ .' ,\ ~ . .:.: ",j. ~ .. ,: .• I'P·I,I .: .. ~! II·' ..... r .. ft.· , ... 
+. : . .I • , 'J ' • " ", !", .\ •• r; • .: \ ;\ i' ",I' ,:. 
+I ~. .~.~ ....... ~: :/1 I ~t".: . . Jr·l! \11 '"I .. 11 ~ ,f. 
+,r 1'·1 'I., ... rU\ :h. ,.:,. ,'·-r '., •.. k. I: 
+.. ' . :': ~ I:· I, ~ - l-.: ! r:" 
+PO 'II I 0\ ".)tUO"'} 
+1 (11 I nw [)IRIC TIO\:\ CARIFl: I Y 
+\' .. " 
+" 
+" t I I I I I{' ,I {I I 
+, 
+BRAND 
+2,4-0 BUTYL 
+ESTER 6 OSO 
+CAl'T!():\: K':l'[' UL: r OF RF.\Ul Uf: ellil DR/·\: 
+<"I·E '>!Dl' r)t\~-;I'I 1'llR ,\[)D1TIO\:AL CAUTIO~~ 
+\ 
+I ' 
+\ .\ \ () l ! \: I \ n I· S P IL\ Y ,\ II X T U R L r () .. \ P PlY 
+III I".IHII' \\111'"'' 1.1-1'1\'1 '''1",-
+0\1- 1:\1:11\ ,,,<11:\1 
+'. , 
+'I I . I •. ,,: ... , I· 
+• 1 
+\-·j'I.\--·I-
+. , ',' \. 
+. , , : I I ' 
+.. ,' 
+\ ,. : • . I ! ~ 'I