Upload 2 files

app.py

@@ -0,0 +1,46 @@
+from dotenv import load_dotenv
+load_dotenv()
+import streamlit as st
+import os
+import google.generativeai as genai
+from PIL import Image
+
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+# load gemini model
+model=genai.GenerativeModel("gemini-pro-vision")
+def get_gemini_response(input,image,prompt):
+    response=model.generate_content([input,image[0],prompt])
+    return response.text
+def input_image_setup(uploaded_img):
+    if uploaded_img is not None:
+        bytes_data = uploaded_img.getvalue()
+        image_parts=[
+            {
+                "mime_type": uploaded_img.type,
+                "data": bytes_data
+            }
+        ]
+        return image_parts
+    else:
+        raise FileNotFoundError("Image not found")
+
+
+st.set_page_config(page_title="Invoice extractor", page_icon="🔮")
+st.title("Gemini llm application")
+input = st.text_input("Ask a question", key="input")
+uploaded_img = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
+image=""
+if uploaded_img is not None:
+    image = Image.open(uploaded_img)
+    st.image(image, caption="Uploaded Image.", use_column_width=True)
+submit=st.button("Submit")
+
+input_prompt="""
+You are expert in understanding invoices. We will show you an invoice and you have to answer the following questions based on the invoice:
+
+"""
+if submit:
+    image_data=input_image_setup(uploaded_img)
+    response=get_gemini_response(input_prompt,image_data,input)
+    st.subheader("Response:")
+    st.write(response) 

requirements.txt

@@ -0,0 +1,6 @@
+streamlit
+google-generativeai
+python-dotenv
+langchain
+PyPDF2
+chromadb