如何利用streamlit 將 gemini pro vision 進行圖片內容介紹

1.安裝pip install google-generativeai

2.至 gemini pro 取 api key

3.撰寫如下文章:(方法一)
import json
import requests
import base64
import streamlit as st

讀取圖片檔案，並轉換成 Base64 編碼的字串

with open(“ss.jpg”, “rb”) as image_file:
image_base64_string = base64.b64encode(image_file.read()).decode(‘utf-8’)
# print(image_base64_string)

url = f’https://generativelanguage.googleapis.com/v1/models/gemini-pro-vision:generateContent?key={“XXXXXSlt0IWdyIHs71gQYGmDq5keWHYpw”}’
headers = {‘Content-Type’: ‘application/json’}
data = {
“contents”: [
{
“parts”: [
{“text”: “詳細說明你在這張圖片中看到什麼？”},
{
“inline_data”: {
“mime_type”: “image/jpeg”,
“data”: image_base64_string
}
}
]
},
]
}
response = requests.post(url, headers=headers, json=data)
st.write(response.json()[“candidates”][0][“content”][“parts”][0][“text”])
st.write(response.json())

3.撰寫如下文章:(方法二)

import streamlit as st
import google.generativeai as genai
import google.ai.generativelanguage as glm
from PIL import ImageAPI_KEY = 'AIzaSyA7dRRSlt0xxxxxw'   自己改
genai.configure(api_key=API_KEY)st.set_page_config(page_title="Generate Blog", page_icon="📸",layout="centered",initial_sidebar_state='collapsed')st.header("輸入一個影像，將進行影像解說")uploaded_file = st.file_uploader("選擇影像", accept_multiple_files=False, type=['jpg', 'png'])if uploaded_file is not None:image = Image.open(uploaded_file)c1,c2=st.columns([1,1])c1.image(image, caption='Uploaded Image', use_column_width=True, width=150)bytes_data = uploaded_file.getvalue()generate = st.button("針對圖片進行說明!")if generate:model = genai.GenerativeModel('gemini-pro-vision')response = model.generate_content(glm.Content(parts = [glm.Part(text="詳細說明你在這張圖片中看到什麼？"),glm.Part(inline_data=glm.Blob(mime_type='image/jpeg',data=bytes_data)),],),stream=True)response.resolve()c2.write(response.text)

在这里插入图片描述