web3-copilot

Web3Copilot is an artificial intelligence tool developed using Council by ChainML to assist Web3 users navigate the ecosystem.

Requirements

• Python >=3.9
• pip >=23.1

Setup

• Create a new file called .env
  • Copy the contents of .env.example into your new .env file
  • API keys for third party tools are not provided.
    • OPENAI_API_KEY from OpenAI
    • OPENAI_LLM_MODEL from OpenAI Models
    • ETHERSCAN_API_KEY from Etherscan APIs
    • ETH_MAINNET_URL from Tenderly Dashboard > Web3 Gateway > Access Key
    • TENDERLY_API_KEY from Tenderly Dashboard > Account Settings > Authorization
• Create a virtual Python environment
  • python -m venv ./venv
• Activate the Python virtual env
  • Windows:
    • In cmd.exe: venv\Scripts\activate.bat
    • In PowerShell: venv\Scripts\Activate.ps1
  • Linux/MacOS: source venv/bin/activate
• Install the project dependencies:
  • pip install -r requirements.txt
• Generate PDF files:
  • python web3_copilot/doc_retrieval/generate.py

Usage

Run Agent Demo

• python demo.py

Run Flask App

• python app.py

NOTE: this will run on port - http://127.0.0.1:8000

Cleanup

• Delete database
  • rm -rf web3_copilot/doc_retrieval/data/database/chromadb
• Deactivate virtual env
  • deactivate
• (optional) Delete virtual env
  • rm -rf ./venv

Adding more docs from other web3 projects

NOTE: For the purpose of this tutorial, the script generates PDFs for projects that use Markdown files (.md) which are stored in the docs/ folder in their documentation repository.

Requirements

• Node >=12.22
• npm >= 6.14
• Git >=1.7

Steps

• Update the PROJECT_REPOS dictionary in web3_copilot/common/constants.py as desired.
• Install md-to-pdf
  • npm i -g md-to-pdf
• Run python web3_copilot/doc_retrieval/generate.py

Tutorial Jupyter Notebook

First Example

Go to the following Google Colab link.

• If you would like to edit the notebook, you must first make a copy: Press File -> Save a Copy in Drive.

ETHToronto Presentation

Building AI Agents with ‘Council’.