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>
2026-05-24 12:32:41 -04:00
parent 1a45280e45
commit a97107de46
8323 changed files with 5273594 additions and 133 deletions
@@ -0,0 +1,92 @@
+# GENATE PLUS 6.7 EC
+
+- EPA Reg No: **10182-288**
+- Registrant: SYNGENTA CROP PROTECTION
+- Signal word: Caution
+- Active ingredients: Butylate (85.1%)
+- Label accepted: 1983-02-14
+- Source PDF: https://www3.epa.gov/pesticides/chem_search/ppls/000748-00236-19830214.pdf
+
+---
+- .. 
+• 
+• 
+, 
+6.'lEe 
+EMULSIFIABLE CONCENTRATE 
+HERBICIDE GRADE 
+ACTIVE INGREDIENT: 
+S·Ethyl Diisobutylthiocarbamate. . . . . . . . .. 85.1 DID 
+INERT INGREDIENTS. . . . . . . . . . . . . . . . . . . .. 14.9% 
+100.00/0 
+THIS PRODUCT CONTAINS 6.7 LBS. ACTIVE 
+INGREDIENT PER GALLON . 
+CAUTION 
+KEEP OUT OF REACH OF CHILDREN 
+NET CONTENTS 55 GALLONS 
+Manufactured By: 
+PPG Industries, Inc. 
+One Gateway Center 
+Pi:t!.bllr'lh, PA 15~72 
+H ~ Reg. No. 748·236 
+EPA Est. No. 32761 MO·3 
+r-- -
+I 
+L 
+HAZARD TO HUMANS AND DOMESTIC ANIMALS 
+Harmful if swallowed. Avoid contact with skin. eyes, Or 
+clothing. Avoid breathing spray mist. Wear rubber gloves and 
+fresh clothing. Wash thoroughly with soap and water imme· 
+diately after contact or use. 
+PRACTICAL TREATMENT 
+If in eyes or on skin, flush with plenty of water. If swallowed, 
+call a physiCian or Poison Control Center. Drink 1 or 2 glasses 
+of water and do not induce vomiting. 00 not induce vomiting 
+or give anything by mouth to an unconscious person. 
+ENVIRONMENTAL H~:!I\RDS 
+Do not apply directly to water. Do not apply where runoff is 
+likely to oCCur. Do not apply when weather conditions favor 
+drift from treatment area. Do not contaminate water by clean· 
+ing of equipment or disposal of wastes. 
+DIRECTIONS FOR USE 
+GENATE PLUS IS a selective herbicide for control of annual 
+gra~ses In field, sweet. and silage corn. See the Directions 
+For Use pamphlet attached to this container for general use 
+precaulions. specific crops, and dosage rates . 
+L82·1 B·1182A 
+INDUSTRIES
+
+r 
+f-, 
+~ 
+I 
+I 
+r 
+I 
+-~ , 
+,'~ 
+, ' 
+-" -.t. .. 
+"-~ . 
+~(l. 
+-.;: 
+.~\.,., 
+"':1 
+.-' 
+:.~ 
+ti7 .. , 
+" 
+'., 
+L 
+, • . 
+\" .... -
+Manul .. ctured By· 
+PPG Industlles. Inc. 
+OOl' G<lteway Center 
+Pittsburgh. PA lS272 
+..., . I _ .~ 
+, 
+~I"'" Biochemicals W 
+LPB2A-1A-1182A INDUSTRIES 
+., 
+.I