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/279-2828.md

@@ -0,0 +1,110 @@
+# GARDONA 5 DUST
+
+- EPA Reg No: **279-2828**
+- Registrant: FMC CORPORATION 
+- Signal word: Caution
+- Active ingredients: Tetrachlorvinphos (5%)
+- Label accepted: 1973-10-24
+- Source PDF: https://www3.epa.gov/pesticides/chem_search/ppls/000279-02828-19731024.pdf
+
+---
+~----------------------------------------------~.---->~----------------------------------------------.................... --...................................... .. 
+Code: 31284 
+DIRECTIONS FOR USf 
+, ", ... Q ~_' r .... :. l,' 
+" , , ~. ,-' . v' .!,l'·~· " ,', 
+, " '. "'" s ~ ,'. 
+,>, , '0' 
+" . ,_.: u ~." '. " , , l' 1'. vf" 
+, ( -.C· ,)' I ' t ,-!' .". \:' . , '_' 0"' f ( , 
+'1' , I'" 
+" ;' 0' , . ' " .' ; -, ,~, .. • .... 
+, ' ~'. ' l . ~ . , , "S S ~_ ' . 
+: '!' •.• " ~ •• ' , •. i .'. r" L, l.,'" , c' 
+. ~) : 'i.). ,-' f ',' ~ • 
+. ~-'" i, 
+'" 
+" 
+" 
+.q p ,_ ,t ••• ' ),1, 
+," " ;.' 
+, ' " ! i, ., ~ •. , , c •. I 
+t. ~ I • I r~' 
+" 's C I 'C\ '2 ',1.1-1', :1". ,",- " 
+.·.··r ... ~ .n ; , ~ 
+" 
+'c " ~ I • .., 
+.'e" 
+t; of , , • ·r< I' ' ,,' ~ .., ·t ' • " 
+• .• .! !, ',~ , .. ,~I ' .. ,r' •. 
+,', ' '--.: r 'r' I)' 1., ,' ... 
+" ' . , " : .. \ t <. • , 1 ••• " ," 
+t" ,"" r . + '. 
+GARDONA I( 5 DUST 
+INSECTICIDE 
+f r /\ REGISTRAT:orJ r., 
+: '; t ' ' .,; ~ £[ I! u, r 
+, , 
+j'''·t·f~·.: ~;f'c<,pl :':t 
+_f:~; 1· .. (~Rf[) f~~l~ 
+• " , f .' ~ : 10 I ,I 
+CAUTION 
+.~' w\ T 
+j I ... ;'C; 
+..,',00 
+KEEP OUT OF REACH OF CHILDREN 
+.>"'.',;0' ~(";I··l.! .-.lh .... ;.. 'vV d" tl • t , , , t • 
+." 
+~--l 1'" 
+,,'. <,\1 0 .... ,j 
+.' " c R 
+'.t,,' .. , 
+T • 
+,_,' r: 
+, , 
+. ". 
+•• i" 
+" . 
+'., ' .. 
+I ~, . I . _ 
+! 1,-
+)f .' 
+," ' 
+, , 
+. " 
+. " ~, 
+, , 
+Net Weight 
+50 Pounds 
+USAGE CAUTIONS 
+.• , I', ! r,: : t ~ ,. ( .", I,. "'., 
+,'r," :'1 '1'<1 ,,', .'. " 
+," .. ,,' ·\1 
+'.' ,I' ~ .. " ", .. 
+" , . 1" 
+.' ,.., ··"·r tlC,()', 
+[m __ ·'gpncy A1\isttlncE" 
+716-735·3765 
+'. , ~ I'" ,'. 
+, ..
+
+. __________________________________________ ~s-------------------------------------------------------------------------------------------------------------
+A.DDlnONAL INFORMATiON AfPEARING ON BAGS TO WHICH THIS LABEL WILL BE AnACHED 
+. A'--"-. bl, 
+, ) • , W. ,: ,i !' a: k ~ i (: S ";:1 . 
+'. .... ", i ) '\ ,.' I •. 
+}...' : ... , , f. I ~ , ','. _ /"< I ~ r ~ A '" 't< J ,~F • ~ ,\ ~:\"'._ 
+'. f- j.: ~'~! '\ : 1 \4 l : ; ~ I." r-' r H ft."" : ~ ;!. '. . ( ",'1 ,-\:--,. f. 
+~:"~. :.A.n~ 0..:1 ~,! "I- I< ...... f~.hl_ t' i-... ~·1 
+J..: ..... ( ; f' ! ,. L.., ,'" ~-!'-.' ·r .... 'f )·}1fh'· .... 
+: I • \ 
+, \'. 
+. :..~ , ' 
+,.\. -, ' .... h.: !:- .. -
+, '. 
+;. ,." 
+. ' ' 
+-FMC 
+, 
+: 
+• . "