Update app.py

app.py

@@ -1,3 +1,4 @@
+import streamlit as st
 from bertopic import BERTopic
 from PIL import Image
 from transformers import (
@@ -6,129 +7,58 @@ from transformers import (
     BlenderbotForConditionalGeneration,
 )
 
-image_path = ""
-current_image_path = ""
-question = ""
-first_turn = True
+def main():
+    st.title("Image Upload App")
+    st.write("Drag and drop an image file here.")
 
-try:
-    while image_path != str(1) and question != str(1):
-        ###############################################################################
+    # Allow the user to upload an image file
+    uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
 
-        if first_turn:
-            image_path = input("Please enter the image path (type 1 to EXIT)\n")
-        else:
-            image_path = input(
-                "Please enter the image path (type 1 to EXIT) (type 2 to reuse image)\n"
-            )
+    if uploaded_file is not None:
+        # Display the uploaded image
+        image = Image.open(uploaded_file)
+        st.image(image, caption="Uploaded Image", use_column_width=True)
 
-        ###############################################################################
+# Model 1.
+# Model 1 gets input from the user.
+# User -> Model 1
 
-        if image_path == str(1):
-            break
-        elif image_path == str(2) and first_turn == False:
-            pass
-        else:
-            image = Image.open(str(image_path))
-
-        question = input("Please enter your question (type 1 to EXIT)\n")
-
-        ###############################################################################
-
-        # 5 MODEL INFERENCES.
-        # User Input = Image + Question About The Image.
-        # User -> Model 1 -> Model 2 -> Model 3 -> Model 4 -> Model 5
-
-        # Model 1.
-
-        vqa_pipeline_output = vqa_pipeline(image, question, top_k=5)[0]
-
-        # Model 2.
-
-        text = (
-            "I love "
-            + str(vqa_pipeline_output["answer"])
-            + " and I would like to know how to [MASK]."
-        )
-        bbu_pipeline_output = bbu_pipeline(text)
-
-        # Model 3.
-
-        utterance = bbu_pipeline_output[0]["sequence"]
-        inputs = tokenizer(utterance, return_tensors="pt")
-        result = facebook_model.generate(**inputs)
-        facebook_model_output = tokenizer.decode(result[0])
-
-        # Model 4.
+vqa_pipeline = pipeline(
+    task="visual-question-answering", model="dandelin/vilt-b32-finetuned-vqa"
+)
+#########################################################################
 
-        facebook_model_output = facebook_model_output.replace("<s> ", "")
-        facebook_model_output = facebook_model_output.replace("<s>", "")
-        facebook_model_output = facebook_model_output.replace("</s>", "")
-        gpt2_pipeline_output = gpt2_pipeline(facebook_model_output)[0]["generated_text"]
+# Model 2.
+# Model 2 gets input from Model 1.
+# User -> Model 1 -> Model 2
 
-        # Model 5.
+bbu_pipeline = pipeline(task="fill-mask", model="bert-base-uncased")
+#########################################################################
 
-        topic, prob = topic_model_1.transform(gpt2_pipeline_output)
-        topic_model_1_output = topic_model_1.get_topic_info(topic[0])["Representation"][
-            0
-        ]
+# Model 3.
+# Model 3 gets input from Model 2.
+# User -> Model 1 -> Model 2 -> Model 3
 
-        topic, prob = topic_model_2.transform(gpt2_pipeline_output)
-        topic_model_2_output = topic_model_2.get_topic_info(topic[0])["Representation"][
-            0
-        ]
-        ###############################################################################
+model_name = "facebook/blenderbot-400M-distill"
+tokenizer = BlenderbotTokenizer.from_pretrained(
+    pretrained_model_name_or_path=model_name
+)
+facebook_model = BlenderbotForConditionalGeneration.from_pretrained(
+    pretrained_model_name_or_path=model_name
+)
+#########################################################################
 
-        print()
+# Model 4.
+# Model 4 gets input from Model 3.
+# User -> Model 1 -> Model 2 -> Model 3 -> Model 4
 
-        print("-" * 150)
-        print("vqa_pipeline_output = ", vqa_pipeline_output)
-        print("bbu_pipeline_output =", bbu_pipeline_output)
-        print("facebook_model_output =", facebook_model_output)
-        print("gpt2_pipeline_output =", gpt2_pipeline_output)
-        print("topic_model_1_output =", topic_model_1_output)
-        print("topic_model_2_output =", topic_model_2_output)
+gpt2_pipeline = pipeline(task="text-generation", model="gpt2")
+#########################################################################
 
-        print()
+# Model 5.
+# Model 5 gets input from Model 4.
+# User -> Model 1 -> Model 2 -> Model 3 -> Model 4 -> Model 5
 
-        print("-" * 150)
-        print("SUMMARY")
-        print("-" * 7)
-        print("Your Image:", image)
-        print("Your Question:", question)
-        print("-" * 100)
-        print(
-            "1. Highest Predicted Answer For Your Question:",
-            vqa_pipeline_output["answer"],
-            "\n",
-        )
-        print(text)
-        print(
-            "2. Highest Predicted Sequence On [MASK] Based on 1.:",
-            bbu_pipeline_output[0]["sequence"],
-            "\n",
-        )
-        print(
-            "3. Conversation Based On Previous Answer Based on 2.:",
-            facebook_model_output,
-            "\n",
-        )
-        print(
-            "4. Text Generated Based On Previous Answer Based on 3.:",
-            gpt2_pipeline_output,
-            "\n",
-        )
-        print(
-            "5. Highest Predicted Topic Model_1 For Previous The Answer Based on 4.:",
-            topic_model_1_output,
-            "\n",
-        )
-        print(
-            "6. Highest Predicted Topic Model_2 For Previous The Answer Based on 4.:",
-            topic_model_2_output,
-        )
-        print("-" * 150)
+topic_model_1 = BERTopic.load(path="davanstrien/chat_topics")
+topic_model_2 = BERTopic.load(path="MaartenGr/BERTopic_ArXiv")
 
-        first_turn = False
-except Exception as e:
-    print("Error:", e)