gemini-webapi 0.1.0

A reverse-engineered async wrapper for Google Gemini web client

Gemini-API

A reverse-engineered asynchronous python wrapper for Google Gemini (formerly Bard).

Features

• ImageFx Support - Supports retrieving images generated by ImageFx, Google's latest AI image generator.
• Classified Outputs - Automatically categorizes texts, web images and AI generated images from the response.
• Official Flavor - Provides a simple and elegant interface inspired by Google Generative AI's official API.
• Asynchronous - Utilizes asyncio to run generating tasks and return outputs efficiently.

Installation

pip install gemini-webapi

Authentication

• Go to https://gemini.google.com and login with your Google account
• Press F12 for web inspector, go to Network tab and refresh the page
• Click any request and copy cookie values of __Secure-1PSID and __Secure-1PSIDTS

Note: __Secure-1PSIDTS could get expired frequently if the Google account is actively used elsewhere, especially when visiting https://gemini.google.com directly. It's recommended to use a separate Google account if you are builing a keep-alive service with this package.

Usage

Initialization

Import required packages and initialize a client with your cookies obtained from the previous step.

import asyncio
from gemini import GeminiClient

# Replace "COOKIE VALUE HERE" with your actual cookie values
Secure_1PSID = "COOKIE VALUE HERE"
Secure_1PSIDTS = "COOKIE VALUE HERE"

async def main():
    client = GeminiClient(Secure_1PSID, Secure_1PSIDTS, proxy=None)
    await client.init(timeout=30)

asyncio.run(main())

Generate contents from text inputs

Ask a one-turn quick question by calling GeminiClient.generate_content.

async def main():
    response = await client.generate_content("Hello World!")
    print(response.text)

asyncio.run(main())

Note: simply use print(response) to get the same output if you just want to see the response text

Conversations across multiple turns

If you want to keep conversation continuous, please use GeminiClient.start_chat to create a ChatSession object and send messages through it. The conversation history will be automatically handled and get updated after each turn.

async def main():
    chat = client.start_chat()
    response1 = await chat.send_message("Briefly introduce Europe")
    response2 = await chat.send_message("What's the population there?")
    print(response1.text, response2.text, sep="\n\n----------------------------------\n\n")

asyncio.run(main())

Retrieve images in response

Images in the API's output are stored as a list of Image objects. You can access the image title, URL, and description by calling image.title, image.url and image.alt respectively.

async def main():
    response = await client.generate_content("Send me some pictures of cats")
    images = response.images
    for image in images:
        print(image, "\n\n----------------------------------\n")

asyncio.run(main())

Generate image with ImageFx

In February 2022, Google introduced a new AI image generator called ImageFx and integrated it into Gemini. You can ask Gemini to generate images with ImageFx simply by natural language.

async def main():
    response = await client.generate_content("Generate some pictures of cats")
    images = response.images
    for image in images:
        print(image, "\n\n----------------------------------\n")

asyncio.run(main())

Note: by default, when asked to send images (like the previous example), Gemini will send images fetched from web instead of generating images with AI model, unless you specifically require to "generate" images in your prompt. In this package, web images and generated images are treated differently as WebImage and GeneratedImage, and will be automatically categorized in the output.

Check and switch to other answer candidates

A response from Gemini usually contains multiple reply candidates with different generated contents. You can check all candidates and choose one to continue the conversation. By default, the first candidate will be chosen automatically.

async def main():
    # Start a conversation and list all reply candidates
    chat = client.start_chat()
    response = await chat.send_message("What's the best Japanese dish? Recommend one only.")
    for candidate in response.candidates:
        print(candidate, "\n\n----------------------------------\n")

    # Control the ongoing conversation flow by choosing candidate manually
    new_candidate = chat.choose_candidate(index=1)  # Choose the second candidate here
    followup_response = await chat.send_message("Tell me more about it.")  # Will generate contents based on the chosen candidate
    print(new_candidate, followup_response, sep="\n\n----------------------------------\n\n")

asyncio.run(main())

References

Google AI Studio

acheong08/Bard