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/524-619.md

@@ -0,0 +1,139 @@
+# MON 87751
+
+- EPA Reg No: **524-619**
+- Registrant: BAYER CROPSCIENCE, LLC
+- Signal word: Caution
+- Active ingredients: Bacillus thuringiensis Cry1A.105 protein and the genetic material  (Vector PV-GMIR1316) necessary for production in Mon 87751 soybean (0.00032%); Bacillus thuringiensis Cry2Ab2 protein and the genetic material  (Vector PV-GMIR1316) necessary for production in Mon 87751 soybean (0.00051%)
+- Label accepted: 2015-05-13
+- Source PDF: https://www3.epa.gov/pesticides/chem_search/ppls/000524-00619-20150513.pdf
+
+---
+UNITED STATES ENVIRONMENTAL PROTECTION AGENCY 
+WASHINGTON, D.C. 20460 
+OFFICE OF CHEMICAL SAFETY 
+AND POLLUTION PREVENTION 
+May 13, 2015 
+Debbie Mahadeo 
+Regulatory Affairs Manager 
+Monsanto Company 
+800 N. Lindbergh Blvd. 
+St. Louis, MO 63167 
+Subject: 
+Non-PRIA (Pesticide Registration Improvement Act) Labeling Amendment – Add a 
+statement to allow non-treated seed containing MON 87751 to be sold as grain and edit 
+page numbers and edit 524-XXX to 524-619 
+Product Name: MON 87751 
+EPA Registration Number: 524-619 
+Application Date: May 12, 2015 
+OPP Decision Number: 504928 
+Dear Ms. Mahadeo: 
+The amended labeling referred to above, submitted in connection with registration under the Federal 
+Insecticide, Fungicide, and Rodenticide Act (FIFRA), as amended, is acceptable. 
+This approval does not affect any terms or conditions that were previously imposed on this registration. 
+You continue to be subject to existing terms or conditions on your registration and any deadlines 
+connected with them. 
+A stamped copy of your labeling is enclosed for your records. This labeling supersedes all previously 
+accepted labeling. You must submit one (1) copy of the final printed labeling before you release this 
+product for shipment with the new labeling. In accordance with 40 CFR § 152.130(c), you may 
+distribute or sell this product under the previously approved labeling for 18 months from the date of this 
+letter. After 18 months, you may only distribute or sell this product if it bears this new revised labeling 
+or subsequently approved labeling. “To distribute or sell” is defined under FIFRA section 2(gg) and its 
+implementing regulation at 40 CFR § 152.3. 
+Should you wish to add/retain a reference to your company’s website on your label, then please be 
+aware that the website becomes labeling under FIFRA and is subject to review by the U.S. 
+Environmental Protection Agency (EPA). If the website is false or misleading, the product will be 
+considered to be misbranded and sale or distribution of the product is unlawful under FIFRA section 
+12(a)(1)(E). 40 CFR § 156.10(a)(5) lists examples of statements the EPA may consider false or
+
+Page 2 of 2 
+EPA Reg. No. 524-619 
+OPP Decision No. 504928 
+misleading. In addition, regardless of whether a website is referenced on your product’s label, claims 
+made on the website may not substantially differ from those claims approved through the registration 
+process. Therefore, should the EPA find or if it is brought to our attention that a website contains false 
+or misleading statements or claims substantially differing from the EPA-approved registration, the 
+website will be referred to the EPA’s Office of Enforcement and Compliance Assurance. 
+Your release for shipment of this product constitutes acceptance of these terms. If these terms are not 
+complied with, this registration will be subject to cancellation in accordance with FIFRA section 6. 
+If you have any questions, please contact Kenneth Haymes, Ph.D. of my team by phone at (703) 347-
+0398 or via email at haymes.kenneth@epa.gov. 
+Sincerely,
+Alan Reynolds, Team Leader 
+Microbial Pesticides Branch 
+Biopesticides and Pollution Prevention Division (7511P) 
+Office of Pesticide Programs 
+Enclosure: stamped label
+
+Monsanto Company SY258-14E1 524-619
+ Page 1 of 2 
+ 
+Plant-Incorporated Protectant Label 
+ 
+MON 87751 
+Lepidopteran-Protected Soybean 
+ (OECD Unique Identifier MON-87751-7) 
+ 
+ 
+Active Ingredients: 
+Bacillus thuringiensis Cry1A.105 protein and the genetic material necessary for its production 
+(vector PV-GMIR13196) in MON 87751 soybean (OECD Unique Identifier MON-87751-7)
+........................................................................................................................... ≤0.00032%* 
+ 
+Bacillus thuringiensis Cry2Ab2 protein and the genetic mate rial necessary for its production 
+(vector PV-GMIR13196) in MON 87751 soybean (OECD Unique Identifier MON-87751-7)
+........................................................................................................................... ≤0.00051%* 
+ 
+ 
+* Maximum percent (wt/wt) of dry grain. 
+ 
+ 
+ 
+KEEP OUT OF REACH OF CHILDREN 
+ 
+CAUTION 
+ 
+ 
+Net Contents __________ 
+ 
+ 
+EPA Registration Number 524-619 
+EPA Establishment Number 524-MO-002 
+ 
+Monsanto Company 
+800 North Lindbergh Blvd. 
+St. Louis, Missouri 63167 
+ 
+ 
+05/13/2015
+524-619
+
+Monsanto Company SY258-14E1 524-619
+ Page 2 of 2 
+ 
+DIRECTIONS FOR USE 
+ 
+It is a violation of federal law to use this product in a manner inconsistent with its labeling. 
+Seed containing this pesticide product may onl y be planted for the purposes of agronomic 
+evaluation, seed increase and production in breeding nurseries as specified in the terms and 
+conditions of this registration and on the labelin g. Commercial plantings of this product for the 
+purposes of grain production and controlling insect pests are prohibited. 
+MON 87751 soybean may be combined through conve ntional breeding with other registered 
+plant incorporated protectants that are similarly approved for use in combination, through 
+conventional breeding, with other registered pl ant-incorporated protectants to produce soybean 
+varieties with combined pesticidal traits. 
+ 
+Soybean has been transformed to express Bacillus thuringiensis Cry1A.105 and Cry2Ab2 
+proteins for the control of the following lepidopteran soybean pests: 
+Soybean velvetbean caterpillar Anticarsia gemmatalis 
+Soybean looper Chrysodeixis includens 
+Soybean axil borer Crocidosema aporema 
+Sunflower looper Rachiplusia nu 
+Corn earworm Helicoverpa zea 
+Fall armyworm Spodoptera frugiperda 
+ 
+Plants that contain the pesticide product may be grown on 15,000 acres or less in total per year in 
+the U.S. with no more than 1,000 acres per county per year (per municipio in Puerto Rico). 
+Harvested seed should not be allowed for sale as commercial seed in the U.S. under the current 
+conditions of this registration, but any non-tre ated seed containing MON 87751 may be sold as 
+grain. 
+There are no refuge requirements for planting MON 87751 Soybean.