Update app.py

app.py

@@ -1,51 +1,48 @@
 import streamlit as st
-from PIL import Image
-from transformers import CLIPProcessor, CLIPModel
-import os
-
-# Initialize Hugging Face Model
-processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
-model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
-
-# Streamlit app layout
-st.title("AI Multimodal File Processing App")
-st.write("This app uses Hugging Face's CLIP model to analyze and edit image and text files.")
-
-# Option to upload an image
-st.subheader("Upload an Image")
-uploaded_image = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
-
-if uploaded_image is not None:
-    image = Image.open(uploaded_image)
-    st.image(image, caption="Uploaded Image", use_column_width=True)
-
-    text = st.text_input("Enter text for image description", "A picture of a cat")  # Default text
-
-    if st.button("Analyze Image"):
-        # Process the image with CLIP
-        inputs = processor(text=text, images=image, return_tensors="pt", padding=True)
-        outputs = model(**inputs)
-        
-        # Display the similarity score between text and image
-        logits_per_image = outputs.logits_per_image  # Similarity score
-        st.write(f"Similarity Score: {logits_per_image.item()}")
-        st.write(f"Description: {text}")
-
-# Option to upload a text file
-st.subheader("Upload a Text File")
-uploaded_textfile = st.file_uploader("Choose a text file...", type=["txt"])
-
-if uploaded_textfile is not None:
-    text_data = uploaded_textfile.read().decode('utf-8')
-    st.text_area("Text File Content", text_data, height=200)
-
-    if st.button("Process Text"):
-        # Example: Modify the text (e.g., convert to uppercase)
-        processed_text = text_data.upper()
-        st.write("Processed Text:")
-        st.text_area("Processed Text Output", processed_text, height=200)
-
-# Optional: File download button
-if uploaded_image is not None or uploaded_textfile is not None:
-    st.download_button("Download Processed File", data="Some file data here", file_name="processed_file.txt")
-
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+from streamlit_webrtc import webrtc_streamer, VideoProcessorBase, WebRtcMode
+
+# Load the pretrained DialoGPT model
+tokenizer = GPT2Tokenizer.from_pretrained("microsoft/DialoGPT-medium")
+model = GPT2LMHeadModel.from_pretrained("microsoft/DialoGPT-medium")
+
+# Streamlit UI Setup
+st.title("AI Multimodal Chat & File Processing App")
+
+# Chat history session state setup
+if "history" not in st.session_state:
+    st.session_state.history = []
+
+# Function to process the chat
+def chat_with_model(user_input):
+    new_user_input_ids = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors="pt")
+    st.session_state.history.append(new_user_input_ids)
+
+    bot_input_ids = new_user_input_ids
+    for history in st.session_state.history:
+        bot_input_ids = history if len(history) < 2048 else history[-1024:]
+
+    chat_history_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
+    bot_output = tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
+    return bot_output
+
+# Chat Input Box
+user_input = st.text_input("You: ", "")
+if user_input:
+    response = chat_with_model(user_input)
+    st.session_state.history.append(tokenizer.encode(user_input + tokenizer.eos_token, return_tensors="pt"))
+    st.write(f"Bot: {response}")
+
+# Show chat history
+if st.session_state.history:
+    for i in range(len(st.session_state.history) - 1, -1, -1):
+        user_msg = tokenizer.decode(st.session_state.history[i], skip_special_tokens=True)
+        st.write(f"You: {user_msg}")
+
+# Video/Audio Stream
+st.subheader("Video/Audio Stream")
+class VideoProcessor(VideoProcessorBase):
+    def recv(self, frame):
+        return frame
+
+webrtc_streamer(key="example", mode=WebRtcMode.SENDRECV, video_processor_factory=VideoProcessor)