Update app.py

app.py

@@ -1,15 +1,85 @@
-import gradio as gr
+import logging
+from fastapi import FastAPI
+from pydantic import BaseModel
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 
+# ------------------------------
+# Logging setup
+# ------------------------------
+logging.basicConfig(level=logging.INFO, format="%(asctime)s [%(levelname)s] %(message)s")
+logger = logging.getLogger(__name__)
+logger.info("🚀 Starting Privacy Audit AI Backend...")
+
+# ------------------------------
+# Load model and tokenizer
+# ------------------------------
 tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-small")
 model = AutoModelForSeq2SeqLM.from_pretrained("google/flan-t5-small")
 
-def explain_risks(text):
-    inputs = tokenizer(f"Explain privacy risks in plain language:\n{text}", return_tensors="pt")
+# ------------------------------
+# FastAPI app
+# ------------------------------
+app = FastAPI(title="Privacy Audit AI", version="1.0.0")
+
+# ------------------------------
+# Request model
+# ------------------------------
+class AnalyzeInput(BaseModel):
+    os_apps: list[str] = []
+    browser_extensions: list[str] = []
+    account_apps: list[str] = []
+
+# ------------------------------
+# Utility functions
+# ------------------------------
+def generate_plain_text(input_text: str):
+    """Generate plain-language explanation using the model."""
+    logger.info(f"Generating explanation for input: {input_text[:60]}...")
+    inputs = tokenizer(f"Explain privacy risks in plain language:\n{input_text}", return_tensors="pt")
     outputs = model.generate(**inputs, max_new_tokens=150)
-    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+    explanation = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return explanation
+
+def explain_risks(os_apps, browser_exts, account_apps):
+    summary_text = (
+        f"OS Apps: {', '.join(os_apps[:10])}, "
+        f"Browser Extensions: {', '.join(browser_exts[:5])}, "
+        f"Connected Apps: {', '.join(account_apps)}"
+    )
+    return generate_plain_text(summary_text)
 
+# ------------------------------
+# Endpoints
+# ------------------------------
+@app.get("/ping")
+def ping():
+    return {"status": "ok", "message": "Backend is alive!"}
 
+@app.post("/analyze")
+def analyze(data: AnalyzeInput):
+    explanation = explain_risks(data.os_apps, data.browser_extensions, data.account_apps)
+    return {"plain_language": explanation}
 
-iface.launch(server_name="0.0.0.0", share=True, server_port=7860)
+@app.get("/audit")
+def audit_mvp():
+    findings = "App X has camera access, App Y has location access, Chrome has 5 extensions"
+    explanation = generate_plain_text(findings)
+    return {
+        "findings": findings,
+        "plain_language": explanation,
+        "risk_level": "Medium"
+    }
 
+@app.post("/audit")
+def audit_mvp_post(data: AnalyzeInput):
+    findings_text = (
+        f"Detected {len(data.os_apps)} installed apps, "
+        f"{len(data.browser_extensions)} browser extensions, and "
+        f"{len(data.account_apps)} connected account apps."
+    )
+    explanation = generate_plain_text(findings_text)
+    return {
+        "findings": findings_text,
+        "plain_language": explanation,
+        "risk_level": "Medium"
+    }