geminikit 1.1.3

The python package that returns Response of Google Gemini through Cookies.

GeminiKit

An unofficial Python wrapper, geminikit, has been developed through reverse-engineering. This tool utilizes cookie values to interact with Google Gemini for testing purposes.

Installation

pip install -U geminikit

or

pip install git+https://github.com/rekcah-pavi/geminikit

---

Log Cookies

video guide

1. Close All Tabs

Ensure all tabs are closed in Google Chrome.

2. Access Network Export

• Open a new tab and navigate to chrome://net-export/.

3. Configure Logging Settings

• Check the box labeled Include cookies and credentials.
• Set the Maximum log size to 1 MB.
• Click the Start logging button.

4. Perform Actions

• Open a new tab and go to gemini.google.com.
• Log in to your Gemini account.
• Send a sample message and wait for Gemini's response.

5. Stop Logging

• Return to the logging tab and click the Stop logging button.

6. Retrieve Cookies

• The cookies will be saved in a JSON file.

7. Get cookies from your saved file

from geminikit import get_cookies_from_file

with open("chrome-net-export-log.json",'r') as f:
	cookies = get_cookies_from_file(f.read())

print(cookies)

---

Usage

Setup gemini

from geminikit import Gemini
gemini = Gemini(cookies)

Ask a message

res = gemini.ask("hello")
print(res['text'])

Text to Voice

res = gemini.speech("hello")
with open("a.wav","wb") as f:
	f.write(res)

Ask with photo

with open("cat.jpg","rb") as f:
	img_link = gemini.upload_image(f.read())

photo = ['cat.jpg', img_link] # photo name (if not available, use 'none.jpg'), link

res = gemini.ask("What is in this photo?",photo=photo)
print(print(res['text'])

Save responce images

res = gemini.ask("send me some wallpapers")

print(res['text'])

#Also, you can access URLs directly.
for url in res['image_urls']:
	img_name  = url.split("/")[-1]
	img_bytes = gemini.get_img_bytes(url)
	with open(img_name,'wb') as f:
		f.write(img_bytes)

Save generated images

res = gemini.ask("Generate an image of a cat holding a rose.")

print(res['text'])

#You can't access URLs directly.
for url in res['generated_image_urls']:
	img_name  = url.split("/")[-1][:10]+".png"
	img_bytes = gemini.get_img_bytes(url)
	with open(img_name,'wb') as f:
		f.write(img_bytes)