Update app.py

app.py

@@ -1,48 +1,75 @@
+import requests
 from transformers import BlipForQuestionAnswering, AutoProcessor
 from PIL import Image
 import gradio as gr
-import openai
 
 # Load the BLIP model and processor
 model = BlipForQuestionAnswering.from_pretrained("Salesforce/blip-vqa-base")
 processor = AutoProcessor.from_pretrained("Salesforce/blip-vqa-base")
 
-# Set your OpenAI API key
-openai.api_key = "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"  # Replace with your OpenAI API key
+# Define your Groq API key and endpoint
+groq_api_key = "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"  # Replace with your Groq API key
+groq_api_url = "https://api.groq.com/openai/v1/chat/completions"  # Replace with the appropriate Groq endpoint
 
-# Function to generate the initial answer with BLIP and expand it with OpenAI API
-def qna(image, question):
+def qna(image, question, context):
     try:
         # Step 1: Get initial short answer from BLIP
         inputs = processor(image, question, return_tensors="pt")
         out = model.generate(**inputs)
         short_answer = processor.decode(out[0], skip_special_tokens=True)
 
-        # Step 2: Construct prompt for OpenAI API
-        prompt = f"Question: {question}\nShort Answer: {short_answer}\nProvide a detailed explanation based on this answer"
+        # Step 2: Construct prompt for Groq API
+        full_prompt = f"{context}\nUser: {question}\nBLIP: {short_answer}\nAssistant:"
+        
+        # Step 3: Send prompt to Groq API for a detailed answer
+        headers = {
+            "Authorization": f"Bearer {groq_api_key}",
+            "Content-Type": "application/json"
+        }
+        
+        data = {
+            "model": "llama3-8b-8192",  # Specify the model to use
+            "messages": [{"role": "user", "content": full_prompt}]
+        }
+        
+        response = requests.post(groq_api_url, headers=headers, json=data)
 
-        # Step 3: Send prompt to OpenAI API for a paragraph-length answer
-        response = openai.Completion.create(
-            engine="text-davinci-003",  # Specify model
-            prompt=prompt,
-            max_tokens=200  # Adjust max_tokens as needed for response length
-        )
-        detailed_answer = response.choices[0].text.strip()
+        # Check if the response is successful
+        if response.status_code == 200:
+            detailed_answer = response.json().get('choices', [])[0].get('message', {}).get('content', '').strip()
+            # Update the context with the latest question and answer
+            updated_context = f"{context}\nUser: {question}\nAssistant: {detailed_answer}"
+            return updated_context, updated_context  # Return updated context for display
+        else:
+            return f"Error {response.status_code}: {response.text}", context
 
-        return detailed_answer
+    except Exception as e:
+        return f"An error occurred: {str(e)}", context
 
-    except openai.error.OpenAIError as e:
-        # Log full error details in the backend
-        print(f"OpenAI API error: {e}")
-        # Return a user-friendly error message to the Gradio interface
-        return "An error occurred while generating the response. Please try again later."
+# Create Gradio interface with context management
+def chatbot_interface(image, question, context=""):
+    # Initialize context if image is uploaded
+    if context == "" and image is not None:
+        context = ""  # Reset context when the image is first uploaded
 
-    except Exception as e:
-        # Log any other exceptions in the backend
-        print(f"General exception: {e}")
-        # Return a general error message to the Gradio interface
-        return "A technical issue occurred. Please try again later."
-
-# Create Gradio interface
-interf = gr.Interface(fn=qna, inputs=["image", "text"], outputs="text")
-interf.launch()
+    # Get the answer from the model
+    answer, updated_context = qna(image, question, context)
+
+    # Return the updated context for display
+    return updated_context
+
+# Define the Gradio interface
+interf = gr.Interface(
+    fn=chatbot_interface,
+    inputs=[
+        gr.Image(type="pil", label="Upload Image"), 
+        gr.Textbox(label="Ask a question")
+    ],
+    outputs="text",  # Output the full conversation context
+    title="Interactive Image Chatbot",
+    description="Upload an image and have a conversation about it. Ask multiple questions about the image."
+)
+
+# Launch the interface
+if __name__ == "__main__":
+    interf.launch()