File size: 2,036 Bytes
11e1c78 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
import streamlit as st
import os
import pathlib
import textwrap
from PIL import Image
import google.generativeai as genai
genai.configure(api_key='AIzaSyCeNgXfZx0kJ736XFVtxXxev_RdscB0i5s')
## Function to load OpenAI model and get respones
def get_gemini_response(input,image,prompt):
model = genai.GenerativeModel('gemini-pro-vision')
response = model.generate_content([input,image[0],prompt])
return response.text
def input_image_setup(uploaded_file):
# Check if a file has been uploaded
if uploaded_file is not None:
# Read the file into bytes
bytes_data = uploaded_file.getvalue()
image_parts = [
{
"mime_type": uploaded_file.type, # Get the mime type of the uploaded file
"data": bytes_data
}
]
return image_parts
else:
raise FileNotFoundError("No file uploaded")
##initialize our streamlit app
st.set_page_config(page_title="Gemini Image Demo")
st.header("Generative AI : Invoice Reader")
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 business cards.
You will receive input images as business card & you will have to answer questions based on the input image.
You have to extract information from business card images and give correct tag to the output text
like person name, company name, occupation, address, phone/telephone number, email, website, etc.
"""
## If ask button is clicked
if submit:
image_data = input_image_setup(uploaded_file)
response=get_gemini_response(input_prompt,image_data,input)
st.subheader("The Response is")
st.write(response) |