INTIAL

.gitignore

@@ -0,0 +1,2 @@
+.venv
+.idea

Dockerfile

@@ -0,0 +1,17 @@
+# ===== Base Image =====
+FROM python:3.10-slim
+
+# ===== Set working directory =====
+WORKDIR /app
+
+# ===== Copy project files =====
+COPY . /app
+
+# ===== Install dependencies =====
+RUN pip install --no-cache-dir -r requirements.txt
+
+# ===== Expose the port =====
+EXPOSE 7860
+
+# ===== Run FastAPI using uvicorn =====
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,32 @@
+import uvicorn
+from fastapi import FastAPI
+from pydantic import BaseModel
+from suicidality_model import predict_suicidality
+from translator import to_english
+
+app = FastAPI(title="🌾 Farmer Mental Health AI")
+
+# ✅ Define a request model
+class TextInput(BaseModel):
+    text: str
+
+@app.get("/")
+def home():
+    return {"message": "Farmer Mental Health AI is up and running 🚀"}
+
+# ✅ Accept JSON body input
+@app.post("/analyze/")
+def analyze_text(data: TextInput):
+    text = data.text
+    text_en = to_english(text)
+    result = predict_suicidality(text_en)
+    return {
+        "original_text": text,
+        "translated_to_english": text_en,
+        "label": result["label"],
+        "confidence": result["confidence"],
+        "sentiment": result["sentiment"]
+    }
+
+if __name__ == "__main__":
+    uvicorn.run("app:app", host="0.0.0.0", port=9000, reload=True)

requirements.txt

@@ -0,0 +1,6 @@
+fastapi
+uvicorn
+pydantic
+googletrans==4.0.0-rc1
+transformers
+torch

suicidality_model.py

@@ -0,0 +1,32 @@
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from textblob import TextBlob
+import torch
+
+# Load the Hugging Face model
+model_name = "sentinet/suicidality"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+labels = ["non-suicidal", "suicidal"]
+
+def sentiment_score(text):
+    """Calculate basic sentiment polarity (-1 = negative, +1 = positive)."""
+    blob = TextBlob(text)
+    return round(blob.sentiment.polarity, 3)
+
+def predict_suicidality(text: str):
+    """Predict suicidality and sentiment for the given (English) text."""
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
+    with torch.no_grad():
+        logits = model(**inputs).logits
+    probs = torch.softmax(logits, dim=1)
+    pred_class = torch.argmax(probs, dim=1).item()
+    confidence = probs[0][pred_class].item()
+
+    sentiment = sentiment_score(text)  # ✅ this is now correctly scoped
+
+    return {
+        "label": labels[pred_class],
+        "confidence": round(confidence, 3),
+        "sentiment": sentiment
+    }

translator.py

@@ -0,0 +1,11 @@
+from googletrans import Translator
+
+translator = Translator()
+
+def to_english(text):
+    result = translator.translate(text, src='auto', dest='en')
+    return result.text
+
+def to_hindi(text):
+    result = translator.translate(text, src='en', dest='hi')
+    return result.text