rabilrbl / gemini-pro-bot Goto Github PK

A Python Telegram bot powered by Google's gemini-pro LLM API

License: GNU General Public License v3.0

Dockerfile 2.53% Python 97.47%

bard chatbot gemini gemini-pro google-bard google-gemini gpt llm multimodal telegram-bot llm-bot multimodal-bot gemini-pro-bot gemini-pro-vision

gemini-pro-bot's Introduction

GEMINI-PRO-BOT

A Python Telegram bot powered by Google's gemini-pro LLM API

This is a Python Telegram bot that uses Google's gemini-pro LLM API to generate creative text formats based on user input. It is designed to be a fun and interactive way to explore the possibilities of large language models.

Screencast.from.20-12-23.01.07.12.PM.+0530.webm

Features

Generate creative text formats like poems, code, scripts, musical pieces, etc.
Stream the generation process, so you can see the text unfold in real-time.
Reply to your messages with Bard's creative output.
Easy to use with simple commands:
- /start: Greet the bot and get started.
- /help: Get information about the bot's capabilities.
Send any text message to trigger the generation process.
Send any image with captions to generate responses based on the image. (Multi-modal support)
User authentication to prevent unauthorized access by setting AUTHORIZED_USERS in the .env file (optional).

Requirements

Python 3.10+
Telegram Bot API token
Google gemini-pro API key
dotenv (for environment variables)

Docker

GitHub Container Registry

Simply run the following command to run the pre-built image from GitHub Container Registry:

docker run --env-file .env ghcr.io/rabilrbl/gemini-pro-bot:latest

Update the image with:

docker pull ghcr.io/rabilrbl/gemini-pro-bot:latest

Build

Build the image with:

docker build -t gemini-pro-bot .

Once the image is built, you can run it with:

docker run --env-file .env gemini-pro-bot

Installation

Clone this repository.
Install the required dependencies:
- pipenv install (if using pipenv)
- pip install -r requirements.txt (if not using pipenv)
Create a .env file and add the following environment variables:
- BOT_TOKEN: Your Telegram Bot API token. You can get one by talking to @BotFather.
- GOOGLE_API_KEY: Your Google Bard API key. You can get one from Google AI Studio.
- AUTHORIZED_USERS: A comma-separated list of Telegram usernames or user IDs that are authorized to access the bot. (optional) Example value: shonan23,1234567890
Run the bot:
- python main.py (if not using pipenv)
- pipenv run python main.py (if using pipenv)

Usage

Start the bot by running the script.
```
python main.py
```
Open the bot in your Telegram chat.
Send any text message to the bot.
The bot will generate creative text formats based on your input and stream the results back to you.
If you want to restrict public access to the bot, you can set AUTHORIZED_USERS in the .env file to a comma-separated list of Telegram user IDs. Only these users will be able to access the bot. Example:
```
AUTHORIZED_USERS=shonan23,1234567890
```

Bot Commands

Command	Description
`/start`	Greet the bot and get started.
`/help`	Get information about the bot's capabilities.
`/new`	Start a new chat session.

Star History

Contributing

We welcome contributions to this project. Please feel free to fork the repository and submit pull requests.

Disclaimer

This bot is still under development and may sometimes provide nonsensical or inappropriate responses. Use it responsibly and have fun!

License

This is a free and open-source project released under the GNU Affero General Public License v3.0 license. See the LICENSE file for details.

gemini-pro-bot's People

Contributors

Stargazers

Watchers

gemini-pro-bot's Issues

Adding the possibility to have people reply in groups only when the bot is mentioned

Bug: Await expression

in send_message_async
    response = await self.model.generate_content(
TypeError: object GenerateContentResponse can't be used in 'await' expression

Voice message options

Can you please add the following feature to the bot: the ability to receive and send voice messages? "google cli" 😃

Gemini Telegram Bot API Access Issue - Location Restriction Error

Hello Dear,

I am writing to report an issue with accessing the Google AI API from my server located in Frankfurt, Germany. My Telegram bot, which utilizes the API for research and study purposes, has suddenly stopped functioning since April 29, 2024. Upon investigation, I encountered the following error message: "400 User location is not supported for the API use."

I have confirmed that my API key is valid and functioning correctly, as demonstrated by a successful connection test using a provided script. Therefore, I suspect the issue is related to a location restriction on the Google AI API.

The Telegram bot is crucial for my ongoing research and work activities. Its unavailability is causing significant disruption and hindering my progress.

I kindly request your assistance in resolving this issue as soon as possible. Please advise if there are any restrictions on accessing the API from Frankfurt or if alternative solutions are available. I would greatly appreciate any guidance on how to restore functionality to my Telegram bot.

Thank you for your time and attention to this matter.

Sincerely,
Robert

feat: Add option to check tokens

Just like the title said, and also check tokens if prompt is long and add option to check used tokens.
Thanks.

Google Speech Synthesis

To investigate the Python code of the source code of the GitHub repository "https://github.com/rabilrbl/gemini-pro-bot" and integrate Google Cli Speech Synthesis, so that this bot turns on and off the output of the text via voice message when interacting with the command "/voice on" or "/voice off", you can follow these steps:

Clone the GitHub repository:

git clone https://github.com/rabilrbl/gemini-pro-bot

Install the required Python modules:

pip install -r requirements.txt

Create a Google Cloud Platform (GCP) project and enable the Text-to-Speech API:

Go to the GCP Console and create a new project, if you don't have one already.
Navigate to the Text-to-Speech API page and click "Enable API".

Create a service account key:

Go to the Service Accounts page and click "Create Service Account".
Enter a name for the service account and select the role "Text-to-Speech API User".
Click "Create Key" and select "JSON" as the key type.
Save the downloaded JSON key in a safe place.

Add the Google Cloud Platform credentials to the Python code:

Create a new file named credentials.json in the source code directory.
Copy the contents of the JSON key that you downloaded earlier into this file.

Import the required Python modules:

Add the following lines at the beginning of the gemini_pro_bot.py file:

import google.cloud.texttospeech as tts

Load the Google Cloud Platform credentials

with open('credentials.json', 'r') as f:
credentials = google.auth.load_credentials_from_file(f)

Instantiate the Text-to-Speech client:

Add the following line at the end of the gemini_pro_bot.py file:

client = tts.TextToSpeechClient(credentials=credentials)

Add the "/voice on" and "/voice off" commands:

Add the following lines to the handle_message() function in the gemini_pro_bot.py file:

if message.text == '/voice on':
global voice_on
voice_on = True
bot.send_message(message.chat.id, 'Voice output turned on.')
elif message.text == '/voice off':
global voice_on
voice_on = False
bot.send_message(message.chat.id, 'Voice output turned off.')

Add the function to generate speech messages:

Add the following function to the gemini_pro_bot.py file:

def generate_speech(text):
synthesis_input = tts.SynthesisInput(text=text)
voice = tts.VoiceSelectionParams(
language_code='en-US',
ssml_gender=tts.SsmlVoiceGender.NEUTRAL
)
audio_config = tts.AudioConfig(
audio_encoding=tts.AudioEncoding.MP3
)
response = client.synthesize_speech(
input=synthesis_input,
voice=voice,
audio_config=audio_config
)
return response.audio_content

Send speech messages when the "voice output" option is enabled:

Add the following line to the handle_message() function in the gemini_pro_bot.py file:

if voice_on and message.text != '/voice on' and message.text != '/voice off':
audio_content = generate_speech(message.text)
bot.send_audio(message.chat.id, audio_content)

Start the bot:

Run the following command to start the bot:

python gemini_pro_bot.py

After following these steps, the bot should turn on and off the output of the text via voice message when interacting with the "/voice on" or "/voice off" command.

Bug: Error response on non-English languages

When I request that Gemini bot compose in languages such as Arabic, it crashes.
Error: Some index error occurred. This response is not supported.