python-gemini-api 1.1.1

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

Gemini API

A unofficial Python wrapper, python-gemini-api, operates through reverse-engineering, utilizing cookie values to interact with Google Gemini for users struggling with frequent authentication problems or unable to authenticate via Google Authentication.

Collaborated competently with Antonio Cheong.

What is Gemini?

| Paper | Official Website | Official API | API Documents |

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 Bard service was changed to Gemini.

• Gemini API
  • What is Gemini?
  • Installation
  • Authentication
  • Usage
    • # 01. Initialization
    • # 02. Generate Content
    • # 03. Text generation
    • # 04. Image generation
    • # 05. Retrieving Images from Gemini Responses
  • Further
    • Use rotating proxies
  • More features
  • Open-source LLM, Gemma
    • How to use Gemma

Installation

pip install python-gemini-api

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

For the updated version, use as follows:

pip install -q -U python-gemini-api

Authentication

[!NOTE] Cookies can change quickly. Don't reopen the same session or repeat prompts too often; they'll expire faster. If the cookie value doesn't export correctly, refresh the Gemini page and export again. Check this sample cookie file.

1. Visit https://gemini.google.com/

2. F12 for browser console → Session: Application → Cookies → Copy the value of some working cookie sets. If it doesn't work, go to step 3.

   Some working cookie sets

   Cookies may vary by account or region.

   First try __Secure-1PSIDCC alone. If it doesn't work, use __Secure-1PSID and __Secure-1PSIDTS. Still no success? Try these four cookies: __Secure-1PSIDCC, __Secure-1PSID, __Secure-1PSIDTS, NID. If none work, proceed to step 3 and consider sending the entire cookie file.

3. (Recommended) Export Gemini site cookies via a browser extension (e.g., Chrome extension). Use ExportThisCookies, open, and copy the txt file contents.

Further: For manual collection or Required for a few users upon error

4. For manual cookie collection, refer to this image. Press F12 → Network → Send any prompt to gemini webui → Click the post address starting with "https://gemini.google.com/_/BardChatUi/data/assistant.lamda.BardFrontendService/StreamGenerate" → Headers → Request Headers → Cookie → Copy and Reformat as JSON manually.
5. (Required for a few users upon error) If errors persist after manually collecting cookies, refresh the Gemini website and collect cookies again. If errors continue, some users may need to manually set the nonce value. To do this: Press F12 → Network → Send any prompt to gemini webui → Click the post address starting with "https://gemini.google.com/_/BardChatUi/data/assistant.lamda.BardFrontendService/StreamGenerate" → Payload → Form Data → Copy the "at" key value. See this image for reference.

Usage

# 01. Initialization

Please explicitly declare cookies in dict format. You can also enter the path to the file containing the cookie with cookie_fp.

from gemini import Gemini

cookies = {
    "__Secure-1PSIDCC" : "value",
    "__Secure-1PSID" : "value",
    "__Secure-1PSIDTS" : "value",
    "NID" : "value",
    # Cookies may vary by account or region. Consider sending the entire cookie file.
  }

GeminiClient = Gemini(cookies=cookies)
# GeminiClient = Gemini(cookie_fp="folder/cookie_file.json") # Or use cookie file path
# GeminiClient = Gemini(auto_cookies=True) # Or use auto_cookies paprameter

[!IMPORTANT] If the session connects successfully and generate_content runs well, CLOSE Gemini website. If Gemini web stays open in the browser, cookies may expire faster.

# 02. Generate Content

To check regardless of the data type of the model output, return the response_dict argument. And use it appropriately.

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

[!IMPORTANT] Once connected and generating valid content, Be sure to CLOSE the gemini website or CLOSE your browser for cookie stability.

The output of the generate_content function is GeminiModelOutput, with the following structure:

Properties of GeminiModelOutput:

• rcid: returns the response choice id of the chosen candidate.
• text: returns the text of the chosen candidate.
• web_images: returns a list of web images from the chosen candidate.
• generated_images: returns a list of generated images from the chosen candidate.
• response_dict: returns the response dictionary, if available.

[!NOTE] If the session fails to connect, works improperly, or terminates, returning an error, it is recommended to manually renew the cookies. The error is likely due to incorrect cookie values. Refresh or log out of Gemini web to renew cookies and try again.

# 03. Text generation

Returns text generated by Gemini.

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

# 04. Image generation

Returns images generated by Gemini.

Sync

from gemini import Gemini, GeminiImage

prompt = "Create illustrations of Seoul, South Korea."
response = GeminiClient.generate_content(prompt)

generated_images = response.generated_images # Check generated images [Dict]

GeminiImage.save_sync(generated_images, save_path="cached_folder")

# You can use byte type image dict as follow:
# bytes_images_dict = GeminiImage.fetch_images_dict_sync(generated_images, cookies) # Get bytes images dict
# GeminiImage.save_images_sync(bytes_images_dict, path="cached_folder") # Save to path

Async

import asyncio
from gemini import Gemini, GeminiImage

async def fetch_and_save_images_async(prompt: str):
    response = await GeminiClient.generate_content_async(prompt)

    generated_images = response.generated_images  # Check response images [Dict]
    for image in generated_images:
        gemini_image = GeminiImage(url=image.url)
        await gemini_image.save(path="cached_folder")  # Save to path asynchronously

# Run the async function
if __name__ == "__main__":
    user_prompt = input("Enter your prompt: ")
    asyncio.run(fetch_and_save_images_async(user_prompt))

GeminiImage.save logics

import asyncio
from gemini import Gemini, GeminiImage

async def fetch_and_save_images_async(prompt: str):
    response = await GeminiClient.generate_content_async(prompt)

    generated_images = response.generated_images  # Check response images [Dict]
    bytes_images_dict = await GeminiImage.fetch_images_dict(generated_images, cookies)  # Get bytes images dict asynchronously
    await GeminiImage.save_images(bytes_images_dict, path="cached_folder")  # Save to path asynchronously

# Run the async function
if __name__ == "__main__":
    user_prompt = input("Enter your prompt: ")
    asyncio.run(fetch_and_save_images_async(user_prompt))

# 05. Retrieving Images from Gemini Responses

Returns images in response of Gemini.

Sync

from gemini import Gemini, GeminiImage

prompt = "Please recommend a travel itinerary for Seoul."
response = GeminiClient.generate_content(prompt)

response_images = response.web_images # Check response images [Dict]

GeminiImage.save_sync(response_images, save_path="cached_folder")

# You can use byte type image dict as follow:
# bytes_images_dict = GeminiImage.fetch_bytes_sync(response_images, cookies) # Get bytes images dict
# GeminiImage.save_images_sync(bytes_images_dict, path="cached_folder") # Save to path

Async

import asyncio
from gemini import Gemini, GeminiImage

async def fetch_and_save_images_async(prompt: str):
    response = await GeminiClient.generate_content_async(prompt)

    response_images = response.web_images  # Check response images [Dict]
    for image in response_images:
        gemini_image = GeminiImage(url=image.url)
        await gemini_image.save(path="cached_folder")  # Save to path asynchronously

# Run the async function
if __name__ == "__main__":
    user_prompt = input("Enter your prompt: ")
    asyncio.run(fetch_and_save_images_async(user_prompt))

GeminiImage.save logics

import asyncio
from gemini import Gemini, GeminiImage

async def fetch_and_save_images_async(prompt: str):
    response = await GeminiClient.generate_content_async(prompt)

    response_images = response.web_images  # Check response images [Dict]
    bytes_images_dict = await GeminiImage.fetch_images_dict(response_images, cookies)  # Get bytes images dict asynchronously
    await GeminiImage.save_images(bytes_images_dict, path="cached_folder")  # Save to path asynchronously

# Run the async function
if __name__ == "__main__":
    user_prompt = input("Enter your prompt: ")
    asyncio.run(fetch_and_save_images_async(user_prompt))

Further

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.")

More features

Explore additional features in this document.

Open-source LLM, Gemma

If you have sufficient GPU resources, you can download weights directly instead of using the Gemini API to generate content. Consider Gemma, an open-source model available for on-premises use.

Gemma models are Google's lightweight, advanced text-to-text, decoder-only language models, derived from Gemini research. Available in English, they offer open weights and variants, ideal for tasks like question answering and summarization. Their small size enables deployment in resource-limited settings, broadening access to cutting-edge AI. For more infomation, visit Gemma-7b model card.

How to use Gemma

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b")

input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt")

outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))

FAQ

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

Sponsor

Use Crawlbase API for efficient data scraping to train AI models, boasting a 98% success rate and 99.9% uptime. It's quick to start, GDPR/CCPA compliant, supports massive data extraction, and is trusted by 70k+ developers.

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 our sincere gratitude to all the contributors.

Contributors to the Bard API and Gemini API.

Further development potential

• refactoring
• gemini/core: httpx.session
  • messages
    • content
      • text
        • parsing
      • image
        • parsing
    • response format structure class
    • tool_calls
  • third party
    • replit
    • google tools
• gemini/client: httpx.AsyncClient
  • messages
    • content
      • text
        • parsing
      • image
        • parsing
    • response format structure class
    • tool_calls
  • third party
    • replit
    • google tools

Contacts

Core maintainers:

• Antonio Cheong / [e-mail]
  
• Daniel Park / [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. This project is a personal initiative and is not affiliated with or endorsed by Google. It is recommended to use Google's official API.

References

[1] Github: acheong08/Bard
[2] Github: dsdanielpark/Bard-API
[3] GitHub: HanaokaYuzu/Gemini-API
[4] Github: GoogleCloudPlatform/generative-ai
[5] WebSite: Google AI Studio

Warning Users bear all legal responsibilities when using the GeminiAPI package, which offers easy access to Google Gemini for developers. This unofficial Python package isn't affiliated with Google and may lead to Google account restrictions if used excessively or commercially due to its reliance on Google account cookies. Frequent changes in Google's interface, Google's API policies, and your country/region, as well as the status of your Google account, may affect functionality. Utilize the issue page and discussion page.

Copyright (c) 2024 Minwoo(Daniel) Park, South Korea