Upload 2 files

app.py

@@ -0,0 +1,111 @@
+import os 
+import base64
+from io import BytesIO
+from PIL import Image
+import streamlit as st
+from langchain.memory import ConversationSummaryBufferMemory
+from langchain_google_genai import ChatGoogleGenerativeAI
+from datetime import datetime
+from langchain_core.messages import HumanMessage
+
+os.environ["GOOGLE_API_KEY"] = "AIzaSyAc0VslmJlmiTFx7GB8QPYEHUZ5nZb5_Nk"
+st.title("Vision Bot")
+
+llm = ChatGoogleGenerativeAI(
+    model="gemini-1.5-flash",
+    max_tokens=4000
+)
+
+IMAGE_SAVE_FOLDER = "./uploaded_images"
+if not os.path.exists(IMAGE_SAVE_FOLDER):
+    os.makedirs(IMAGE_SAVE_FOLDER)
+
+st.markdown(
+    """
+<style>
+    .st-emotion-cache-janbn0 {
+        flex-direction: row-reverse;
+        text-align: right;
+    }
+</style>
+""",
+    unsafe_allow_html=True,
+)
+
+# Initialize session states
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+if "llm" not in st.session_state:
+    st.session_state.llm = llm
+if "rag_memory" not in st.session_state:
+    st.session_state.rag_memory = ConversationSummaryBufferMemory(llm=st.session_state.llm, max_token_limit=5000)
+if "current_image" not in st.session_state:
+    st.session_state.current_image = None
+if "last_displayed_image" not in st.session_state:
+    st.session_state.last_displayed_image = None
+
+container = st.container()
+
+# Upload image
+uploaded_image = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"], key="image_uploader")
+
+# Check if a new image is uploaded
+if uploaded_image and uploaded_image != st.session_state.current_image:
+    st.session_state.current_image = uploaded_image
+    st.image(uploaded_image, caption="Newly Uploaded Image")
+    
+    # Add a system message to mark the new image in the conversation
+    st.session_state.messages.append({
+        "role": "system", 
+        "content": f"New image uploaded: {uploaded_image.name}",
+        "image": uploaded_image
+    })
+
+# Display messages
+for message in st.session_state.messages:
+    with container.chat_message(message["role"]):
+        if message["role"] == "system" and "image" in message:
+            st.image(message["image"])
+        st.write(message["content"])
+
+# Take prompt
+if prompt := st.chat_input("Enter your query here..."):
+    with container.chat_message("user"):
+        st.write(prompt)
+
+    # Save user input in session state
+    st.session_state.messages.append({"role": "user", "content": prompt})
+
+    if st.session_state.current_image:
+        # Save uploaded image to disk
+        image = Image.open(st.session_state.current_image)
+        current_date = datetime.now().strftime("%Y%m%d")
+        image_name = f"{current_date}_{st.session_state.current_image.name}"
+        image_path = os.path.join(IMAGE_SAVE_FOLDER, image_name)
+        image.save(image_path)
+
+        # Encode image in base64
+        with open(image_path, "rb") as image_file:
+            encoded_string = base64.b64encode(image_file.read()).decode()
+
+        # Send image and text to the model
+        chat = HumanMessage(
+            content=[
+                {"type": "text", "text": prompt},
+                {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{encoded_string}"}},
+            ]
+        )
+    else:
+        # Send only text to the model if no image is uploaded
+        chat = HumanMessage(content=prompt)
+
+    # Get AI response
+    ai_msg = llm.invoke([chat]).content
+    with container.chat_message("assistant"): 
+        st.write(ai_msg)
+
+    # Save the conversation context in memory
+    st.session_state.rag_memory.save_context({'input': prompt}, {'output': ai_msg})
+    
+    # Append the assistant's message to the session state
+    st.session_state.messages.append({"role": "assistant", "content": ai_msg})

requirements.txt

@@ -0,0 +1,3 @@
+streamlit
+langchain
+langchain_google_genai