Update app.py

app.py

@@ -6,15 +6,12 @@ from huggingface_hub import hf_hub_download
 from sentence_transformers import SentenceTransformer
 
 # ============================================================
-# CONFIG
+# CONFIG — ONLY CATEGORY MODELS
 # ============================================================
 
 HF_USER = "ClergeF"
 
-# Your 12 individual HF repos
-MODEL_REPOS = {
-    "value_impact": "value-impact-model",
-    "impact": "impact-model",
+CATEGORY_REPOS = {
     "family": "family-model",
     "community": "community-model",
     "education": "education-model",
@@ -27,10 +24,7 @@ MODEL_REPOS = {
     "innovation": "innovation-model",
 }
 
-# Model file names inside each repo
-MODEL_FILES = {
-    "value_impact": "value_impact.json",
-    "impact": "impact.json",
+CATEGORY_FILES = {
     "family": "family_level.json",
     "community": "community_level.json",
     "education": "education_level.json",
@@ -44,70 +38,54 @@ MODEL_FILES = {
 }
 
 # ============================================================
-# LOAD EMBEDDER
+# EMBEDDER
 # ============================================================
 
-# Keep it light + consistent for Spaces
 print("Loading embedder: all-MiniLM-L6-v2 …")
 embedder = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
 
-
 # ============================================================
-# MODEL LOADING HELPERS
+# HELPERS
 # ============================================================
 
-def load_model_from_hf(repo_name: str, filename: str):
-    """Downloads a model.json file from HuggingFace and returns Python dict."""
-    print(f"↳ Loading {filename} from {repo_name} …")
+def embed(text: str):
+    return embedder.encode([text])[0]
 
+
+def load_model(repo, filename):
+    print(f"Loading: {repo}/{filename}")
     path = hf_hub_download(
-        repo_id=f"{HF_USER}/{repo_name}",
+        repo_id=f"{HF_USER}/{repo}",
         filename=filename
     )
-
     with open(path, "r") as f:
         return json.load(f)
 
 
-def embed(text: str):
-    """Returns a 384-dim sentence embedding."""
-    return embedder.encode([text])[0]
-
-
 def linear_predict(model_json, vec):
-    """Linear model forward pass using coef + intercept."""
     coef = np.array(model_json["coef"])
     intercept = np.array(model_json["intercept"])
-
-    if coef.ndim == 2:      # Multi-output
-        return coef @ vec + intercept
-    else:
-        return float(np.dot(coef, vec) + intercept)
-
+    return float(np.dot(coef, vec) + intercept)
 
 # ============================================================
-# LOAD ALL 12 MODELS AT STARTUP
+# LOAD 10 CATEGORY MODELS
 # ============================================================
 
-print("Loading all 12 models…")
-
-loaded_models = {}
-
-for key in MODEL_REPOS:
-    repo = MODEL_REPOS[key]
-    file = MODEL_FILES[key]
+print("Loading category models…")
+models = {}
 
-    model_json = load_model_from_hf(repo, file)
-    loaded_models[key] = model_json
-
-print("✔ All models loaded successfully.")
+for key in CATEGORY_REPOS:
+    repo = CATEGORY_REPOS[key]
+    file = CATEGORY_FILES[key]
+    models[key] = load_model(repo, file)
 
+print("✔ Category models loaded!")
 
 # ============================================================
-# FASTAPI APP
+# API
 # ============================================================
 
-app = FastAPI(title="MVT Community Value API (Production)")
+app = FastAPI(title="Category Classification API")
 
 
 class InputText(BaseModel):
@@ -115,33 +93,20 @@ class InputText(BaseModel):
 
 
 @app.get("/")
-def root():
-    return {"status": "ok", "message": "MVT Category & Value API running!"}
+def home():
+    return {"status": "ok", "message": "Category API running"}
 
 
-# ============================================================
-# PREDICT ROUTE
-# ============================================================
-
 @app.post("/predict")
 def predict(payload: InputText):
     text = payload.text
     vec = embed(text)
 
     out = {}
-
-    # MULTI-OUTPUT: Value + Impact
-    value_pred, impact_pred = linear_predict(loaded_models["value_impact"], vec)
-    out["estimated_value"] = float(value_pred)
-    out["impact_level"] = float(impact_pred)
-
-    # ALL OTHER SINGLE-OUTPUT MODELS
-    for key in MODEL_REPOS:
-        if key == "value_impact":
-            continue  # skip, already handled
-        out[key] = float(linear_predict(loaded_models[key], vec))
+    for cat in CATEGORY_REPOS:
+        out[f"{cat}_score"] = linear_predict(models[cat], vec)
 
     return {
         "input": text,
-        "predictions": out
+        "categories": out
     }