The following key steps need to be followed to deploy Eigent locally:
- environmental preparation: Install Node.js (≥v16) and npm, 16GB or more of RAM is recommended, and use NVIDIA GPUs that can accelerate model inference (e.g. RTX 3060).
- Get Code: Cloning repositories via Git:
git clone https://github.com/eigent-ai/eigent.git, enter the project catalog. - Dependent Installation: Implementation
npm installInstall front-end and back-end dependencies, including the React front-end framework and FastAPI back-end services. - launch an application: Run
npm run devAfter that, the browser accesses thehttp://localhost:5173You can access the interface. - Model Configuration: in
config.yamlSpecify the local model path (e.g.model_path: "/path/to/local/model") or set the cloud API key.
After the deployment is complete, theeigent run --localcommands ensure that all data processing is done locally. This model is particularly suitable for scenarios that require strict data compliance, such as healthcare and finance, and supports completely offline operation.
This answer comes from the articleEigent: an open source desktop application for automated multi-intelligence collaborationThe
May not be reproduced without permission:AI productivity tools " How to achieve local private deployment with Eigent? What are the exact steps?
