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/9779-66.md

@@ -0,0 +1,153 @@
+# RIVERSIDE 10% MALATHION DUST
+
+- EPA Reg No: **9779-66**
+- Registrant: WINFIELD SOLUTIONS, LLC
+- Signal word: Caution
+- Active ingredients: Malathion  (NO INERT USE) (10%)
+- Label accepted: 1974-04-25
+- Source PDF: https://www3.epa.gov/pesticides/chem_search/ppls/009779-00066-19740425.pdf
+
+---
+conOli . 
+mCIl ._-_.""" 
+FORAGE CROPS 
+AlFAlfA 
+{ 
+I 
+• 
+, 
+, 
+• 
+HO o 
+·10·20 o 
+12 ,. 
+10·12 1 
+12 1 
+12 o 
+8·10 o 
+15 o 
+10·12 . 0 
+12·15 o 
+15·18 o 
+12·15 o 
+• 
+CUCURBITS 
+,Cucumbers 
+APII!!lS 
+CIJtllttSER BE ETlE 
+I~l -
+-
+J.~PORT[O CABBAGE WORM. 
+DI~~O"mlVAE. 
+CABBAGE LOOPEk 
+ton Ciuuila"er,·coIlJrds. Brussels sproulS 
+ind broccoh only) 
+CUCUM8£~ BEETlq, 
+Do nol api runless planls are dry. 
+15 
+12 
+12 
+1 
+1 
+7 
+Burnips 
+and 
+Bro~,oli 
+10·12 7 
+12 
+12·15 
+12 
+121S 
+lHO 
+12 
+7 
+l·Broccoli 
+7 
+leill4 
+I 
+I 
+I 
+two cc/o(2..f ~ (1.1l.f.fI( (X'P:I IIcF/J'fi!i>:J) ,.4 UfAcJ( 
++lsrflE oveQ,~ ~.4 CAI.a. t)l.S't1lI'Bun~.., 
+'. 
+• • 
+-~~-~ ... ~-~-... - ... _ ............. - .............................. --_ ..• -'> .... 
+I 
+j .. ... -----:. ... . .- ,.~ ,\ " " ~ " 
+i 
+.... . J. . , .. 
+~. 
+I 
+~ 
+I , 
+•• 
+~.l ~ , .. " . ..., 
+TJ r""();' , 'j"'''' .-. ., ..... ' .• _.1 .. , " i 
+) ',- "\1 (,' t': f," • L ~ ...... .' '..1 
+tl "fl' Ii ,. .... ) C .. -""'!'," •. { J:' r' '.' f • 't I I,' I I ' , r11~~J • .'Ir.t .............. .-
+'. , 
+, 
+I 
+~ 
+~ 
+~ 
+I, 
+, 
+• 
+. ''''1' ;.I.~ 
+I 
+----~--~.------------~-----.. -.---.----------
+ruIlPIIII' 
+•• 
+SQUASH 
+OllA 
+---
+DNIONS 
+'=---;:"2 
+J'(rVl\ P£ [$ 
+.01 FUIlG£ 
+, 
+• 
+Ippltcalion within 7 day~ 01 Nr· 
+wesl II vines lie 10 be used for '"I Mal leeds 
+II vines are Rollo be led IpplJClliOQ may be 
+II' ade Illlthln 
+.. ,,.tlUFACTUAfO BY 
+20 3 
+12·15 I 
+20 I 
+• • 12 
+10·12 • 
+12·1~ o 
+12·1S 7 
+IIJ·12 3 
+RIVERSIDE CHEMICAL CO. ca,. SUBSIQIARY o~ C()()K INDUSfH,,:; INC .I.IEI.IPH:S TN 38115 
+12t:'PItDdtU A-I- 51 10 
+• • • • , , t ., • • • 
+I • I • " • . · f I • · I • I I , • • 
+t I • • • • • • ••• 
+• 
+• • • I f f I • • , ! ! I • 
+I • 
+, • I I • 
+• J • . · • . • 
+I . I 
+• I • 
+•• 
+.- .1 
+I 
+I 
+• 
+! 
+I 
+\ 
+• 
+\ 
+., 
+) 
+i 
+I 
+, 
+I • 
+I 
+1