python-gemini-api 0.1.1

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

Development Status :: 3 - Alpha

Gemini API

A Python wrapper, python-gemini-api, interacts with Google Gemini via reverse engineering.

What is Gemini?

Gemini is a family of generative AI models developed by Google DeepMind that is designed for multimodal use cases. The Gemini API gives you access to the Gemini Pro and Gemini Pro Vision models. In February 2024, Google"s Gemini service was changed to Gemini.
Paper, Official Web, Open-source Gemma-7b

Installation

pip install python-gemini-api

pip install git+https://github.com/dsdanielpark/Gemini-API.git

Authentication

Warning DO NOT expose your cookies.

• Depending on the region and Google account status, multiple cookies may be required, including __Secure-1PSIDTS, __Secure-1PSIDCC, __Secure-1PSID, NID, or more.
• You must appropriately set the cookies_dict parameter to Gemini class.
• Cookie values can be changed frequently, thus it is recommended to automatically update them through the browser_cookie3 package.

Usage

After Bard's update to Gemini, multiple cookies, often updated, are needed based on region or Google account. Thus, automatic cookie renewal logic is crucial.

Innitiallization

from gemini import Gemini

cookies = {
    "__Secure-1PSID": "value",
    "__Secure-1PSIDTS": "value",
    "__Secure-1PSIDCC": "value",
    "NID": "value",
}

GeminiClient = Gemini(cookies=cookies)

Or update cookies automatically using broser_cookie3.

from gemini import Gemini

GeminiClient = Gemini(auto_cookies=True)

However, auto_cookies feature is incomplete, and you may need to periodically update cookie values in a .env file or json file. You will need to develop a logic that suits you for automatically updating cookies.

Before proceeding, ensure that the GeminiClient object is defined without any errors.

Text generation

prompt = "Hello, Gemini. What's the weather like in Seoul today?"
response = GeminiClient.generate_content(prompt)
print(response)

Image generation

prompt = "Hello, Gemini. Give me a beautiful photo of Seoul's scenery."
response = GeminiClient.generate_content(prompt)

print("\n".join(response.images)) # Print images

for i, image in enumerate(response.images): # Save images
    image.save(path="folder_path/", filename=f"seoul_{i}.png")

Generate content about image

It may not work as it is only available for certain accounts, regions, and other restrictions. As an experimental feature, it is possible to ask questions with an image. However, this functionality is only available for accounts with image upload capability in Gemini"s web UI.

prompt = "What is in the image?"
image = open("folder_path/image.jpg", "rb").read() # (jpeg, png, webp) are supported.

response = GeminiClient.generate_content(prompt, image)

Text To Speech(TTS) from Gemini

Business users and high traffic volume may be subject to account restrictions according to Google"s policies. Please use the Official Google Cloud API for any other purpose. The user is solely responsible for all code, and it is imperative to consult Google"s official services and policies. Furthermore, the code in this repository is provided under the MIT license, and it disclaims any liability, including explicit or implied legal responsibilities.

text = "Hello, I'm developer in seoul" # Gemini will speak this sentence
response = GeminiClient.generate_content(prompt, image)
audio = GeminiClient.speech(text)
with open("speech.ogg", "wb") as f:
    f.write(bytes(audio["audio"]))

Further

Behind a proxy

If you are working behind a proxy, use the following.

proxies = {
    "http": "http://proxy.example.com:8080",
    "https": "https://proxy.example.com:8080"
}

GeminiClient = Gemini(cookies=cookies, proxies=proxies, timeout=30)
GeminiClient.generate_content("Hello, Gemini. Give me a beautiful photo of Seoul"s scenery.")

Use rotating proxies

If you want to avoid blocked requests and bans, then use Smart Proxy by Crawlbase. It forwards your connection requests to a randomly rotating IP address in a pool of proxies before reaching the target website. The combination of AI and ML make it more effective to avoid CAPTCHAs and blocks.

# Get your proxy url at crawlbase https://crawlbase.com/docs/smart-proxy/get/
proxy_url = "http://xxxxx:@smartproxy.crawlbase.com:8012" 
proxies = {"http": proxy_url, "https": proxy_url}

GeminiClient = Gemini(cookies=cookies, proxies=proxies, timeout=30)
GeminiClient.generate_content("Hello, Gemini. Give me a beautiful photo of Seoul's scenery.")

Reusable session object

You can continue the conversation using a reusable session. However, this feature is limited, and it is difficult for a package-level feature to perfectly maintain conversation_id and context. You can try to maintain the consistency of conversations same way as other LLM services, such as passing some sort of summary of past conversations to the DB.

from gemini import Gemini, SESSION_HEADERS
import requests

cookies = {
    "__Secure-1PSID": "value",
    "__Secure-1PSIDTS": "value",
    "__Secure-1PSIDCC": "value",
    "NID": "value",
}

session = requests.Session()
session.headers = SESSION_HEADERS
session.cookies.update(cookies)

GeminiClient = Gemini(session=session, timeout=30)
response = GeminiClient.generate_content("Hello, Gemini. What's the weather like in Seoul today?")["content"]

# Continued conversation without set new session
response = GeminiClient.generate_content("What was my last prompt?")

More features

• Chat Gemini
• Get image links
• Multi-language Gemini
• Export Conversation
• Export Code to Repl.it
• Executing Python code received as a response from Gemini
• Max_token, Max_sentences
• Translation to another programming language

FAQ

You can find most help on the FAQ and Issue pages. Alternatively, utilize the official Gemini API at Google AI Studio.

Issues

Sincerely grateful for any reports on new features or bugs. Your valuable feedback on the code is highly appreciated. Frequent errors may occur due to changes in Google"s service API interface. Both Issue reports and Pull requests contributing to improvements are always welcome. We strive to maintain an active and courteous open community.

Contributors

We would like to express my sincere gratitude to all the contributors.

Contacts

• Core Maintainer: Minwoo(Daniel) Park, @dsdanielpark
• E-mail: [e-mail]

License

MIT license, 2024, Minwoo(Daniel) Park. We hereby strongly disclaim any explicit or implicit legal liability related to our works. Users are required to use this package responsibly and at their own risk.

References

[1] Github acheong08/Gemini
[2] Github GoogleCloudPlatform/generative-ai
[3] Github HanaokaYuzu/Gemini-API
[4] Google AI Studio