Chnaged requirement text

app/routes.py

@@ -65,42 +65,74 @@ def transcribe():
         return error_response(str(e), 500)
 
 
+# @bp.route('/analyze_image', methods=['POST'])
+# def analyze_image():
+#     if 'file' not in request.files:
+#         return error_response("No image file provided", 400)
+#
+#     file = request.files['file']
+#     image_bytes = file.read()
+#
+#     try:
+#         # send raw bytes to HF inference
+#         result = ocr_api(image_bytes)
+#         # TroCR returns a single string of text
+#         extracted = ""
+#         if isinstance(result, str):
+#             extracted = result
+#         elif isinstance(result, dict) and "generated_text" in result:
+#             extracted = result["generated_text"]
+#         else:
+#             # fallback to printing whatever we got
+#             extracted = str(result)
+#
+#         extracted = extracted.strip()
+#         if not extracted:
+#             return error_response("No text extracted from image", 400)
 @bp.route('/analyze_image', methods=['POST'])
 def analyze_image():
-    if 'file' not in request.files:
-        return error_response("No image file provided", 400)
+            if 'file' not in request.files:
+                return error_response("No image file provided", 400)
+
+            f = request.files['file']
+            path = os.path.join("/tmp", secure_filename(f.filename))
+            f.save(path)
+
+            # read raw bytes
+            with open(path, "rb") as img_f:
+                img_bytes = img_f.read()
+
+            try:
+                # 1) Ask the vision-LLM to describe / extract text
+                completion = hf.chat.completions.create(
+                    model="google/gemma-3-27b-it",
+                    messages=[{
+                        "role": "user",
+                        "content": [
+                            {"type": "text", "text": "Extract any text you see in this image."},
+                            {"type": "image_bytes", "image_bytes": {"data": img_bytes}}
+                        ]
+                    }],
+                    max_tokens=512,
+                )
+
+                extracted = completion.choices[0].message.content.strip();
+
+                analysis = analyze_text_internal(extracted)
+                tags     = generate_tags(extracted)
+                return jsonify({
+                    "extracted_text": extracted,
+                    "sentiment":     analysis["sentiment"],
+                    "emotion":       analysis["emotion"],
+                    "confidence":    analysis["confidence"],
+                    "tags":          tags
+                })
+            except Exception as e:
+                return error_response(str(e), 500)
+
+
 
-    file = request.files['file']
-    image_bytes = file.read()
 
-    try:
-        # send raw bytes to HF inference
-        result = ocr_api(image_bytes)
-        # TroCR returns a single string of text
-        extracted = ""
-        if isinstance(result, str):
-            extracted = result
-        elif isinstance(result, dict) and "generated_text" in result:
-            extracted = result["generated_text"]
-        else:
-            # fallback to printing whatever we got
-            extracted = str(result)
-
-        extracted = extracted.strip()
-        if not extracted:
-            return error_response("No text extracted from image", 400)
-
-        analysis = analyze_text_internal(extracted)
-        tags     = generate_tags(extracted)
-        return jsonify({
-            "extracted_text": extracted,
-            "sentiment":     analysis["sentiment"],
-            "emotion":       analysis["emotion"],
-            "confidence":    analysis["confidence"],
-            "tags":          tags
-        })
-    except Exception as e:
-        return error_response(str(e), 500)
 
 
 # Internal function to call analyze_text directly