Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/shamspias/langchain-gemini-api
An innovative AI conversation API leveraging Google's Gemini for multimodal understanding. Combines FastAPI, Langchain, and Redis for robust, scalable, and privacy-conscious text and image-based interactions
https://github.com/shamspias/langchain-gemini-api
fastapi gemini gemini-ai gemini-api gemini-pro gemini-pro-api gemini-pro-bot gemini-pro-vision google-gemini google-generative-ai langchain langchain-python large-language-models python vision-api
Last synced: 2 months ago
JSON representation
An innovative AI conversation API leveraging Google's Gemini for multimodal understanding. Combines FastAPI, Langchain, and Redis for robust, scalable, and privacy-conscious text and image-based interactions
- Host: GitHub
- URL: https://github.com/shamspias/langchain-gemini-api
- Owner: shamspias
- Created: 2023-12-19T06:40:34.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2023-12-30T12:56:52.000Z (about 1 year ago)
- Last Synced: 2023-12-30T13:37:17.860Z (about 1 year ago)
- Topics: fastapi, gemini, gemini-ai, gemini-api, gemini-pro, gemini-pro-api, gemini-pro-bot, gemini-pro-vision, google-gemini, google-generative-ai, langchain, langchain-python, large-language-models, python, vision-api
- Language: Python
- Homepage: https://t.me/rim_nova_bot
- Size: 2.84 MB
- Stars: 7
- Watchers: 2
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# langchain-gemini-api
## Overview
`langchain-gemini-api` is an AI-powered conversation API that integrates Google's Gemini API, designed to facilitate
advanced text and image-based interactions. This project combines the capabilities of modern deep learning models with
FastAPI for high performance and scalability, Langchain for sophisticated conversational workflows, and Redis for
ephemeral conversation storage.
## Key Features
- **Asynchronous API**: Utilizing FastAPI for enhanced performance and scalability.
- **Langchain Integration**: Advanced conversational workflows using multiple AI models.
- **Google Gemini API**: Incorporating Gemini, Gemini Pro, and Gemini Pro Vision for superior conversation understanding
and generation.
- **Ephemeral Conversation Storage**: Implementing Redis for data privacy and efficient memory usage.
- **User-Friendly Interface**: Simplified API endpoints for easy integration.
## Getting Started
### Prerequisites for Google Gemini API
- Get a [Google Gemini AI API key here](https://makersuite.google.com/app/apikey) and add it to Secrets in your Repl
with the key GOOGLE_API_KEY.
### Prerequisites for langchain-gemini-api
- Python 3.9 or higher
- FastAPI
- Uvicorn
- Redis
- Access to Google Gemini API
### Installation
#### Install Redis
1. Install Redis:
```bash
sudo apt update
sudo apt install redis-server
```
Windows users can download Redis from [here](https://github.com/tporadowski/redis/releases)
2. Test Redis:
```bash
redis-cli ping
```
If Redis is running, it will return `PONG`.
#### Install Python Dependencies
1. Clone the repository:
```bash
git clone https://github.com/shamspias/langchain-gemini-api.git
```
2. Create a virtual environment:
```bash
python3 -m venv venv
```
for Windows:
```bash
python -m venv venv
```
3. Activate the virtual environment:
```bash
source venv/bin/activate
```
4. Navigate to the project directory and install dependencies:
```bash
cd langchain-gemini-api
pip install -r requirements.txt
```
## Configuration
1. Create a `.env` file in the project directory and add the following:
```bash
GEMINI_API_KEY= # e.g. "1234567890"
REDIS_URL=redis://localhost:6379/0 # default Redis URL
MY_API_KEY= # e.g. "1234567890"
SYSTEM_INSTRUCTION= # e.g. "Your are Sam and an AI assistant...etc"
```
## Running the API
1. Start fastapi server:
```bash
uvicorn app.main:app --reload
```
The API will be available at http://localhost:8000.
## API Endpoints
- **/conversations/**: Endpoint for text and image based conversations.
- **/delete/**: Endpoint to delete conversation data.
## API Documentation
- **/docs**: [Swagger UI for API documentation](http://127.0.0.1:8000/docs).
- **/redoc**: [ReDoc UI for API documentation](http://127.0.0.1:8000/redoc).
## Acknowledgments
- Google Gemini API team
- [Langchain contributors](https://python.langchain.com/docs/integrations/chat/google_generative_ai)
- FastAPI community
## Demo
### Conversation
#### With telegram bot use this one: https://t.me/rim_nova_bot
#### This is the telegram bot repo: [Gemini-Telegram-Bot](https://github.com/shamspias/gemini-telegram-bot)
### Video
- Coming soon