Create app.py

app.py

@@ -0,0 +1,56 @@
+from flask import Flask, request, jsonify
+from transformers import AutoProcessor, AutoModelForVision2Seq
+from PIL import Image
+import torch
+import io
+
+app = Flask(__name__)
+
+model_id = "microsoft/phi-3-vision-instruct"
+
+# Load processor + model
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForVision2Seq.from_pretrained(
+    model_id,
+    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+    device_map="auto"
+)
+
+@app.route("/")
+def home():
+    return jsonify({"message": "✅ Phi-3 Vision Flask Endpoint Running"})
+
+# Text-only
+@app.route("/chat", methods=["POST"])
+def chat():
+    data = request.json
+    text = data.get("text")
+
+    if not text:
+        return jsonify({"error": "No text provided"}), 400
+
+    inputs = processor(text=text, return_tensors="pt").to(model.device)
+    output = model.generate(**inputs, max_new_tokens=150)
+    response = processor.decode(output[0], skip_special_tokens=True)
+
+    return jsonify({"response": response})
+
+# Vision + Text
+@app.route("/vision", methods=["POST"])
+def vision():
+    if "image" not in request.files or "text" not in request.form:
+        return jsonify({"error": "Send `image` (file) and `text` (string)."}), 400
+
+    text = request.form["text"]
+    image_file = request.files["image"]
+
+    image = Image.open(io.BytesIO(image_file.read())).convert("RGB")
+
+    inputs = processor(text=text, images=image, return_tensors="pt").to(model.device)
+    output = model.generate(**inputs, max_new_tokens=150)
+    response = processor.decode(output[0], skip_special_tokens=True)
+
+    return jsonify({"response": response})
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=7860)