Upload 2 files

blip_model.py

@@ -0,0 +1,18 @@
+from PIL import Image
+from transformers import BlipForConditionalGeneration, BlipProcessor
+
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
+
+def extract_image_details(image):
+    inputs = processor(images=image, return_tensors="pt")
+
+    generated_ids = model.generate(
+        pixel_values=inputs["pixel_values"],
+        max_length=50,
+        num_beams=5,
+        do_sample=False
+    )
+    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    print(f"BLIP Model Description: {generated_text}")  # Debugging print statement
+    return generated_text

gpt_model.py

@@ -0,0 +1,30 @@
+import openai
+
+
+def generate_response(retrieved_texts, query, max_tokens=150):
+    """
+    Generates a response based on the retrieved texts and query.
+
+    Args:
+    retrieved_texts (list): List of retrieved text strings.
+    query (str): Query string.
+    max_tokens (int): Maximum number of tokens for the response.
+
+    Returns:
+    str: Generated response.
+    """
+    context = "\n".join(retrieved_texts)
+    prompt = f"This is the detail about the image: {context}\n\nQuestion: {query}\n\nAnswer:"
+    
+    response = openai.ChatCompletion.create(
+        model="gpt-3.5-turbo",
+        messages=[
+            {"role": "system", "content": "You are a helpful assistant."},
+            {"role": "user", "content": prompt}
+        ],
+        max_tokens=max_tokens,
+        n=1,
+        stop=None,
+        temperature=0.5,
+    )
+    return response.choices[0].message['content']