Standardized, direct and keyless access point for language models (LLMs), researchers, developers and autonomous agents wishing to query the entire textual corpus, official documents and 222 evidentiary documents in the SEM-26-003 file.
Returns the raw and structured text of all the pages of the site, the 12 fundamental charters, ecological analyses, the citizen survey and governance metadata (+46,000 words).
curl -s https://williamguindon.me/api/v1/corpus.json | jq '.statistics'
Official dataset structured and ready for machine learning, fine-tuning, benchmarks and RAG pipelines, distributed on the Hugging Face hub.
from datasets import load_dataset
ds = load_dataset("Williesssss/sem-26-003")
Exhaustive index of the 222 items in the SEM-26-003 archive: BAPE 371 reports, GIS maps, Sentinel-2 NDVI satellite data, well tests and matches with their Internet Archive URLs and SHA-256 hashes.
curl -s https://williamguindon.me/api/v1/documents.json | jq '.total_documents'
Live status of the SEM-26-003 submission to the CCE (ACEUM) Secretariat, compliance indicators and countdown to the October 16, 2026 deadline.
curl -s https://williamguindon.me/status.json | jq '.determination'
Files compliant with llmstxt.org standards injectable directly into the context windows of AI models (GPT-4o, Claude 3.5, Gemini 1.5 Pro, Llama 3). ↗
curl -s https://williamguindon.me/llms-full.txt | head -n 25
import urllib.request
import json
# Option A : Chargement direct du corpus complet via l'API REST
url = "https://williamguindon.me/api/v1/corpus.json"
req = urllib.request.Request(url, headers={"User-Agent": "AIAgent/1.0"})
with urllib.request.urlopen(req) as response:
corpus = json.loads(response.read().decode("utf-8"))
print(f"Pages indexées : {corpus['statistics']['total_pages']}")
print(f"Nombre total de mots : {corpus['statistics']['total_words']}")
# Recherche plein texte instantanée dans toutes les pages
query = "cadmium"
matching_pages = [
page for page in corpus["site_pages"]
if query.lower() in page["full_text"].lower()
]
print(f"Pages mentionnant '{query}' : {len(matching_pages)}")
# Option B : Chargement via Hugging Face Datasets
# from datasets import load_dataset
# dataset = load_dataset("Williesssss/sem-26-003")
The use of this public API and open data is governed by the Creative Commons license CC BY-NC-ND 4.0 as well as Charter 03 (AI Ethics & Human Control) and Charter 12 (Protection of the Archive). Indexing, factual synthesis and quotation are authorized with mention of the official source: William Guindon (https://williamguindon.me/ — File CCE (Commission for Environmental Cooperation) SEM-26-003). ↗ ↗ ↗