|
|
--- |
|
|
title: ChatXBT |
|
|
emoji: 💬 |
|
|
colorFrom: purple |
|
|
colorTo: pink |
|
|
sdk: docker |
|
|
sdk_version: "latest" |
|
|
app_file: chatxbt-assistant.py |
|
|
pinned: false |
|
|
--- |
|
|
|
|
|
# ChatXBT Web3 AI Assistant Service |
|
|
|
|
|
AI-powered unification and execution protocol for web3 applications |
|
|
|
|
|
## Requirements |
|
|
|
|
|
The list below contains all the requirements needed to have a complete developer environment to start working on this project. |
|
|
Follow the links to install or update these tools on your machine. |
|
|
|
|
|
1. [Python 3.12+](https://www.python.org/downloads/release/python-3120/) |
|
|
2. [Pyenv](https://github.com/pyenv/pyenv) |
|
|
3. [Pip Installer](https://pip.pypa.io/en/stable/installation/) |
|
|
4. [Python Venv](https://docs.python.org/3/library/venv.html) |
|
|
|
|
|
## Installation |
|
|
|
|
|
1. Clone the repository: `git clone https://github.com/ChatXBT/chatxbt-web3-ai-assistant.git` |
|
|
2. Get a copy of the `.env` file from the project manager |
|
|
3. Create a virtual environment: `python -m venv env` |
|
|
4. Activate the virtual environment: `source env/bin/activate` |
|
|
5. Install the dependencies: `pip install -r requirements.txt` |
|
|
6. Run the application: `chainlit run chatxbt-assistant.py -w` |
|
|
7. Open the application in your browser: `http://localhost:8000` |
|
|
|
|
|
## Project Overview |
|
|
|
|
|
The project is structured as follows: |
|
|
|
|
|
1. src/data_sources: `a list of data sources that can be used to retrieve data for the AI assistant.` |
|
|
2. src/databases: `a list of databases that can be used to store data for the AI assistant.` |
|
|
3. src/libs: `a list of libraries that can be used to extend the classes and functions servicing the AI assistant.` |
|
|
4. src/llms: `a list of language models powered libs that can be used to power the AI assistant.` |
|
|
5. src/search_services: `a list of search services that can be used to retrieve data for the AI assistant.` |
|
|
6. src/tools: `a list of tools that can be used to extend the functionality of the AI assistant.` |
|
|
|
|
|
## Guides |
|
|
|
|
|
1. Follow the development, structure and documentation patterns of the `src/tools/coin_data_toolkit.py` to build custom toolkits |
|
|
2. Follow the development, structure and documentation patterns of the `src/tools/coin_data_toolkit.py` to build classes |
|
|
3. Pay attention to the `constants` variables and `caching` decorators to optimize performance of class functions/methods across the project |
|
|
4. Create new classes in the appropriate folders to maintain an organized codebase and project |
|
|
5. After installing any new package run `` to update the dependency requirements list |
|
|
6. Expose RPC functions for SDKs that do not support python runtime. use [DeepKit](https://deepkit.io/documentation/rpc) and [BunJS](https://bun.sh/) if possible. |
|
|
|
|
|
## Git Workflow |
|
|
|
|
|
For this project, we will be using a very simple version of the Gitflow workflow. This workflow is designed to manage the development, release, and maintenance of software projects. It provides a clear and structured approach to managing branches, releases, and feature development. |
|
|
|
|
|
### Feature |
|
|
|
|
|
1. Create a branch off of main branch: `git checkout -b feature/my-feature` |
|
|
2. Make your changes and commit them: `git commit -m "Add my feature"` |
|
|
3. Push your changes to the remote repository: `git push origin feature/my-feature` |
|
|
4. Open a pull request on GitHub and request a review from a team member. |
|
|
5. Once the pull request is approved, merge it into the main branch. |
|
|
6. Delete the feature branch: `git branch -d feature/my-feature` |
|
|
7. Update your local main branch: `git checkout main && git pull origin main` |
|
|
|
|
|
### Bugfix |
|
|
|
|
|
1. For bug fixes, create a branch off of main branch: `git checkout -b bugfix/my-bugfix` |
|
|
2. Make your changes and commit them: `git commit -m "Fix my bug"` |
|
|
3. Push your changes to the remote repository: `git push origin bugfix/my-bugfix` |
|
|
4. Open a pull request on GitHub and request a review from a team member. |
|
|
5. Deploy the bugfix branch to a staging environment for testing. |
|
|
6. Once testing is finished, merge the pull request into the main branch. |
|
|
7. Once the pull request is approved, merge it into the main branch. |
|
|
8. Delete the bugfix branch: `git branch -d bugfix/my-bugfix` |
|
|
9. Update your local main branch: `git checkout main && git pull origin main` |
|
|
|
|
|
## Deployment to production |
|
|
|
|
|
To be finalised and added |
|
|
|
|
|
## TODO |
|
|
|
|
|
1. Add deployment instructions |
|
|
2. Setup CI/CD pipelines for automatic deployment |
|
|
3. Setup and integrate `LiteLLM` instance for LLM service high availability |
|
|
4. Add RPC class for remote method calls to other ChatXBT services written in other languages such as `JS`, `TS` & `GO` |
|
|
5. Write enough unit tests to ensure class and function input and output correctness |
|
|
|
