Gemini-pro-vision

app.py

@@ -0,0 +1,62 @@
+from dotenv import load_dotenv
+load_dotenv()
+
+import streamlit as st
+import os
+from PIL import Image
+import google.generativeai as genai
+
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+
+# Load Gemini pro Vision
+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(uploaded_file):
+    if uploaded_file is not None:
+        bytes_data = uploaded_file.getvalue()
+
+        image_parts = [
+            {
+                "mime_type":uploaded_file.type,
+                "data":bytes_data
+            }
+        ]
+        return image_parts
+    else:
+        raise FileNotFoundError("No file uploaded")
+    
+
+
+# Streamlit
+st.set_page_config(page_title="Extractor",page_icon=":100:")
+st.header("Quick Info")
+st.subheader("Extract information from images")
+input = st.text_input("Input prompt :",key="input")
+uploaded_file = st.file_uploader("Choose an image ...",type=["jpg","jpeg","png"])
+image = ""
+if uploaded_file is not None:
+    image = Image.open(uploaded_file)
+    st.image(image,caption="Uploaded Image",use_column_width=True)
+
+submit = st.button("Tell me about the image")
+
+input_prompt = """
+You are an expert in understanding images. We will upload an image
+and you will have to answer any question based on the uploaded image
+"""
+
+if submit:
+    image_data = input_image(uploaded_file)
+    response = get_gemini_response(input,image_data,input_prompt)
+    st.subheader("The response :")
+    st.write(response)
+
+
+    
+
+
+

requirements.txt

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