re #4 cleaning up the old ipbes and convei code and data

Author: richpsharp

.gitignore

@@ -0,0 +1,2 @@
+.env
+__pycache__/

app_esa2025/main.py

@@ -44,7 +44,9 @@
 BASE_DIR = Path(__file__).resolve().parent
 
 app = FastAPI()
-app.mount("/static", StaticFiles(directory=str(BASE_DIR / "static")), name="static")
+app.mount(
+    "/static", StaticFiles(directory=str(BASE_DIR / "static")), name="static"
+)
 templates = Jinja2Templates(directory=str(BASE_DIR / "templates"))
 templates.env.auto_reload = True
 
@@ -98,7 +100,11 @@ async def read_root(request: Request):
 
 @app.get("/get_info/")
 def get_info(db: Session = Depends(get_db)):
-    pf = db.query(ProcessedFile).order_by(ProcessedFile.processed_at.desc()).first()
+    pf = (
+        db.query(ProcessedFile)
+        .order_by(ProcessedFile.processed_at.desc())
+        .first()
+    )
     if not pf:
         return {"dbInfo": "Database not initialized yet."}
 
@@ -107,7 +113,9 @@ def get_info(db: Session = Depends(get_db)):
     if ts.tzinfo is None:
         ts = ts.replace(tzinfo=timezone.utc)
 
-    return {"dbInfo": f"Database created from {pf.filename} at {ts.isoformat()}"}
+    return {
+        "dbInfo": f"Database created from {pf.filename} at {ts.isoformat()}"
+    }
 
 
 @app.get("/entities/")
@@ -118,7 +126,9 @@ async def list_entities():
         names = [p.name for p in entities if p.name]
 
         # sort by last name (case-insensitive)
-        sorted_names = sorted(set(names), key=lambda n: n.strip().split()[-1].lower())
+        sorted_names = sorted(
+            set(names), key=lambda n: n.strip().split()[-1].lower()
+        )
 
         return {"entities": sorted_names}
     finally:
@@ -169,9 +179,9 @@ async def people_search(req: SearchRequest, db: Session = Depends(get_db)):
         raise HTTPException(status_code=400, detail="Empty query")
 
     rows: List[Entity] = db.query(Entity).all()
-    # TODO: limit 10 for debugging
-    # rows: List[Entity] = db.query(Entity).limit(10).all()
-    candidates: List[Tuple[str, str]] = [(r.name, r.bio or "") for r in rows if r.name]
+    candidates: List[Tuple[str, str]] = [
+        (r.name, r.bio or "") for r in rows if r.name
+    ]
 
     current_tokens = 0
     current_chunk = []

app_ipbes_selection/local/.gitignore

@@ -0,0 +1,3 @@
+*
+!.gitignore
+!README.md

app_ipbes_selection/local/README.md

@@ -0,0 +1,13 @@
+# Local Data Holding Space
+
+This directory is reserved for **local-only data** used during analysis.  
+Store any material here that must **not** be committed or deployed, including:
+
+- Raw CVs
+- Nominations
+- Intermediate outputs from LLMs
+- Temporary or intermediate analysis files
+- Any other private, sensitive, or non-deployable artifacts
+
+Contents of this directory are intentionally excluded from version control.  
+Use it as a workspace for local analysis inputs and outputs that should remain private.

docker-compose.yml

@@ -1,4 +1,30 @@
 services:
+
+  agu2025:
+    hostname: agu2025
+    build: ./app_agu2025
+    volumes:
+      - ./app_agu2025/data:/app/data
+      - ./app_agu2025:/app
+    environment:
+      PYTHONUNBUFFERED: '1'
+    labels:
+      - 'traefik.enable=true'
+      - 'traefik.http.routers.agu2025.rule=Host(`agu2025.craa.ecoshard.org`)'
+      - 'traefik.http.routers.agu2025.entrypoints=websecure'
+      - 'traefik.http.routers.agu2025.tls=true'
+      - 'traefik.http.routers.agu2025.tls.certresolver=letsencrypt'
+      - 'traefik.http.services.agu2025.loadbalancer.server.port=8000'
+    depends_on:
+      - reverse-proxy
+    networks:
+      - web
+    tty: true
+    stdin_open: true
+    ports:
+      - '127.0.0.1:8001:8000'
+
+
   esa2025:
     hostname: esa2025
     build: ./app_esa2025

local/.gitignore

@@ -0,0 +1,3 @@
+*
+!.gitignore
+!README.md

local/README.md

@@ -0,0 +1,13 @@
+# Local Data (Top-Level)
+
+This directory is for **local-only, legacy, or general-purpose data** that is not tied to any specific sub-application.
+Use it to store material that must **not** be committed or deployed, including:
+
+- Raw CVs or nominations
+- Old or archived input data
+- Intermediate outputs from LLMs
+- Temporary or intermediate analysis files
+- Any other private, sensitive, or non-deployable artifacts
+
+Everything placed here is intentionally excluded from version control.
+Use this space for local data that should remain private and separate from the sub-app–specific workflows.