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/524-594.md

@@ -0,0 +1,129 @@
+# MON 87701
+
+- EPA Reg No: **524-594**
+- Registrant: BAYER CROPSCIENCE, LLC
+- Signal word: Caution
+- Active ingredients: Bacillus thuringiensis Cry1Ac and the genetic material necessary for its production (PV-GMIR9) in soybean. (0.00091%)
+- Label accepted: 2020-01-22
+- Source PDF: https://www3.epa.gov/pesticides/chem_search/ppls/000524-00594-20200122.pdf
+
+---
+UNITED STATES ENVIRONMENTAL PROTECTION AGENCY 
+WASHINGTON, D.C. 20460 
+ 
+OFFICE OF CHEMICAL SAFETY 
+AND POLLUTION PREVENTION 
+ 
+January 22, 2020 
+ 
+David J. Chi 
+Regulatory Affairs Manager 
+Bayer U.S. – Crop Science 
+Monsanto Company 
+700 Chesterfield Parkway West 
+Chesterfield, MO 63017 
+ 
+Subject: Non-PRIA (Pesticide Registration Im provement Act) Labelling Amendment to 
+ remove the reference to a grower guide 
+Product Name: MON 88701
+ 
+EPA Registration Number: 524-594 
+Application Date: September 23, 2019 
+OPP Decision Number: 556069 
+ 
+Dear Mr. Chi: 
+ 
+The amended labeling referred to above, submitted in connection with registration under the 
+Federal Insecticide, Fungicide, and Rodenticide Act (FIFRA), as amended, is acceptable provided you 
+comply with the revised terms of registration as set forth below: 
+ 
+1) The subject registration is limited to a combined yearly total of 15,000 acres for breeding purposes, 
+agronomic testing and producing seed in the United States and the Commonwealth of Puerto Rico. 
+ 
+2) Monsanto must submit reports on IRM monitoring and remedial action plans to the U.S. 
+Environmental Protection Agency (EPA) annually by August 31st each year. 
+ 
+3) Upon the EPA’s request, Monsanto must provide a report on the acreage where MON 87701 has been 
+grown by State and territory. 
+ 
+4) Harvested seed are not allowed for sale as commercial seed in the U.S. under the conditions of this 
+registration, but any non-treated seed containing MON 87701 may be sold as grain. 
+ 
+5) MON 87701 soybean may be combined through conventional breeding with other registered plant 
+incorporated protectants that are similarly approved for use in combination, through conventional 
+breeding, with other registered plant-incorporated protectants to produce soybean varieties with 
+combined pesticidal traits. 
+ 
+Your release for shipment of this product constitutes acceptance of these terms. If these terms are not complied
+
+Page 2 of 2 
+EPA Reg. No. 524-594 
+OPP Decision No. 556069 
+ 
+ 
+ 
+with, this registration will be subject to cancellation in accordance with FIFRA section 6. 
+ 
+A stamped copy of the labeling is enclosed for your records. This labeling supersedes all previously 
+accepted labeling. 
+ 
+If you have any questions, please contact Michael Glikes of my team by phone at (703) 305-6231 or via 
+email at glikes.michael@epa.gov. 
+ 
+ 
+Sincerely, 
+ 
+ 
+ 
+Alan Reynolds, Team Leader 
+Emerging Technologies Branch 
+Biopesticides and Pollution 
+ Prevention Division (7511P) 
+Office of Pesticide Programs 
+ 
+ 
+Enclosure
+
+Plant-Incorporated Protectant Label 
+MON 87701 
+ 
+ 
+ (OECD Unique Identifier: MON-877Ø1-2) 
+ 
+Active Ingredients: 
+ 
+Bacillus thuringiensis Cry1Ac protein and the genetic material (vector PV-GMIR9) 
+necessary for its production in MON 87701 (O ECD Unique Identifier: MON-877Ø1-2) 
+soybean ............................................................................................................ ≤0.00091%* 
+* Percentage (wt/wt) on a dry weight basis. 
+ 
+Keep Out Of Reach Of Children 
+CAUTION 
+EPA Registration No. 524-594 
+EPA Establishment No. 524-MO-002 
+Monsanto Company 
+800 N. Lindbergh Blvd 
+St. Louis, MO 63167 
+ 
+NET CONTENTS______ 
+ 
+DIRECTIONS FOR USE 
+It is a violation of Federal law to use this seed in any manner inconsistent with this 
+labeling. 
+This product may be used only for breeding purposes, for example, seed manufacturing, 
+research, agronomic testing, small scale rese arch trials, and production in breeding 
+nurseries as specified in the terms and conditions of this registration and on the labeling. 
+This product may be combined through conventional breeding with other registered plant 
+incorporated protectants that are similarly approved for use in combination, through 
+conventional breeding, with other registered plant-incorporated protectants to produce 
+soybean varieties with combined pesticidal traits. 
+ 
+The insect-protected soybean may be grown on up to 1,000 acres per county and up to a 
+combined total of 15,000 acres per year in the United States (U.S.) and the territory of 
+Puerto Rico. 
+ 
+Harvested seed are not allowed for sale as commercial seed in the U.S. under the 
+conditions of this registration but any non-t reated seed containing MON 87701 may be 
+sold as grain. 
+01/22/2020
+524-594