Add simple prompt

app.py

@@ -115,7 +115,14 @@ with gr.Blocks(css=css) as demo:
                 This involves identifying both the initial stages of root intrusion and the more advanced stages where roots have significantly obstructed the pipe.
                 5) Additional considerations while analyzing the images: do not consider blurred text or user-defined circled areas in the images.
                 6) You will always try to describe the image that you see.
-                You must provide your output in JSON format with DESCRIPTION: <your description of the image>, PREDICTION: <your prediction, either DEFECTIVE or NON DEFECTIVE
+                You must provide your output in JSON format with DESCRIPTION: <your description of the image>, PREDICTION: <your prediction, either DEFECTIVE or NON DEFECTIVE>
+
+                #### Basic prompt used for GPT4-V
+                You are a virtual sewer technician with the capability to analyze images from CCTV cameras taken inside sewer pipes.
+                Your task is to examine each image and provide a concise, yet accurate, summary for retrieval.
+                After summarizing, you must classify the image as DEFECTIVE or NON DEFECTIVE.
+                You will always try to describe the image that you see.
+                You must provide your output in JSON format with DESCRIPTION: <your description of the image>, PREDICTION: <your prediction, either DEFECTIVE or NON DEFECTIVE>
                 """)