OpenChat: Simplifying Chatbot Creation with Large Language Models
Introduction
OpenChat is an everyday user chatbot console that simplifies the utilization of large language models. As AI continues to advance, the installation and usage of these models have become overwhelming. OpenChat aims to address this challenge by providing a two-step setup process to create a comprehensive chatbot console. It serves as a central hub for managing multiple customized chatbots.
Important disclaimer: This project is not production-ready and is meant for a local environment at this early stage. We quickly built this project to validate the idea, so please excuse any shortcomings in the code. You may come across several areas that require enhancements, and we truly appreciate your support by opening issues, submitting pull requests, and providing suggestions.
Try OpenChat Now
You can try OpenChat on openchat.so. Visit the website to explore the capabilities of OpenChat and experience the power of large language models in chatbot development.
Current Features
OpenChat provides the following features to simplify chatbot creation and management:
- Create unlimited local chatbots based on GPT-3 (and GPT-4 if available).
- Customize your chatbots by providing PDF files, websites, and soon, integrations with platforms like Notion, Confluence, and Office 365.
- Each chatbot has unlimited memory capacity, enabling seamless interaction with large files such as a 400-page PDF.
- Embed chatbots as widgets on your website or internal company tools.
- Use your entire codebase as a data source for your chatbots (pair programming mode).
- And much more!
Roadmap
OpenChat is continuously evolving and improving. Here is the roadmap for upcoming features and enhancements:
- Create unlimited chatbots
- Share chatbots via URL
- Integrate chatbots on any website using JS (as a widget on the bottom right corner)
- Support GPT-3 models
- Support vector database to provide chatbots with larger memory
- Accept websites as a data source
- Accept PDF files as a data source
- Support multiple data sources per chatbot
- Support ingesting an entire codebase using GitHub API and
use it as a data source with pair programming mode
- Support pre-defined messages with a single click
- Support Slack integration (allow users to connect chatbots with their Slack workspaces)
- Support Intercom integration (enable users to sync chat conversations with Intercom)
- Support offline open-source models (e.g., Alpaca, LLM drivers)
- Support Vertex AI and Palm as LLMs
- Support Confluence, Notion, Office 365, and Google Workspace
- Refactor the codebase to be API ready
- Create a new UI designer for website-embedded chatbots
- Support custom input fields for chatbots
- Support offline usage: this is a major feature, OpenChat will operate fully offline with no internet connection at this stage (offline LLMs, offline Vector DBs)
We welcome your feedback and ideas! If you have any suggestions or cool ideas, feel free to reach out to us.
Getting Started
To get started with OpenChat, follow these steps:
Make sure you have Docker installed on your machine.
Clone the OpenChat Git repository by running the following command:
git clone git@github.com:openchatai/OpenChat.git
- Update the
common.envfile with your API keys:
OPENAI_API_KEY=# you can get it from your account in openai.com
PINECONE_API_KEY=# you can get from "API Keys" tab in pinecone
PINECONE_ENVIRONMENT=# you can get it after creating your index in pinecone
PINECONE_INDEX_NAME=# you can get it after creating your index in pinecone
Note: For Pinecone DB, make sure that the dimension is equal to 1536.
- Navigate to the repository folder and run the following command:
make install
Once the installation is complete, you can access the OpenChat console at http://localhost:8000.
Upgrade Guide
OpenChat strives to avoid introducing breaking changes. To upgrade to the latest version, follow these steps:
Run
git pullto fetch the latest changes from the repository.Run
make installto install the latest dependencies and update the project.
Acknowledgements
We would like to express our gratitude to the following contributors for their valuable contributions to the OpenChat project:
This project follows the all-contributors specification. Contributions of any kind are welcome!
License
OpenChat is licensed under the MIT License.
Conclusion
OpenChat aims to simplify the creation and management of chatbots powered by large language models. With its user-friendly interface and extensive features, OpenChat enables users to leverage the power of AI in their chatbot projects. Whether you are a developer or a non-technical user, OpenChat provides a streamlined experience for building and deploying chatbots. We are continuously working on enhancing OpenChat and incorporating new features based on user feedback and requirements. Feel free to join our Discord community and contribute to the project. Together, let's unlock the potential of large language models in chatbot development!
Top comments (1)
The competition is fierce, but the best ai chatbots and chatbots for e-commerce sales truly stand out in terms of responsiveness and user engagement – a must-have for websites