A command-line tool to manage, deploy, and launch PathoLens with Google Colab or local backends.
Project description
๐ฌ PathoLens Digital Pathology Workstation
PathoLens is a digital pathology workstation & AI workspace with a command-line launcher supporting Local Machine and Google Colab Cloud VM execution backends.
๐ Key Features
- Dual Deployment Target: Run completely locally on your hardware, or spin up a free Google Colab GPU-accelerated cloud VM with one command.
- Zero-friction Colab Deploy (Zero Code Uploads): The CLI uses PyPI directly. Instead of slow zip uploads of the codebase, it initiates a PyPI installation (
uv pip install) over Google's datacenter backbone (under 5 seconds) and only uploads the locally compiled static Next.js frontend (~6MBstatic.zip). - Dynamic Slide Directory Configuration: Switch slide folders dynamically inside the browser UI Settings modal without having to restart the backend. Point it to local directories (e.g.
/home/prime/slides) or Google Drive paths (/content/drive/MyDrive/...). - Edge AI Diagnostics: Supports local execution of the
gemma-4-E2B-it-litert-lmLiteRT model for local digital pathology clinical questions and diagnostics.
๐ฆ Installation
To install the CLI globally using uv:
uv tool install patholens
๐ ๏ธ Usage
Simply run:
patholens launch
This launches the onboarding wizard in your terminal:
โโโโโโโโโโโโโโโโโโโโโ โโโโโโโ โโโโ
โโโโโโโโ โ โโ โโโโโโโโโโโโโโโ โโโโโ cli v2.0.2
๐ฌ Digital Pathology Workstation & AI Workspace
} Environment: Cloud-Scalable / Multi-Tenant Ready
} Local Fallback: SQLite + Local Slide Storage
? Where would you like to run the PathoLens backend?
1) Local Machine (Your computer's CPU/GPU)
2) Google Colab VM (Free cloud CPU/GPU accelerators)
Option 1: Local Machine
Runs a local FastAPI backend and serves the Next.js frontend statically.
- Local AI option: You can choose to download the
litert_lmpackage and cache thegemma-4-E2B-it-litert-lmmodel for local inference. - Launch link: The CLI automatically opens your default browser at
http://localhost:8000.
Option 2: Google Colab VM
- Drive Integration: Prompts you to mount your Google Drive on the VM.
- Fast Setup: Installs
patholensfrom PyPI, uploads and extracts the frontendstatic.zip, installs slide bindings (libopenslide0), and opens a Cloudflare secure tunnel. - Direct Browser Launch: The CLI automatically grabs the public
*.trycloudflare.comtunnel URL and opens it in your web browser.
โ๏ธ Slide Directory Configuration
You can configure the active slide folder inside the browser UI dashboard.
- Click the Settings gear icon in the header.
- Input the absolute path to your slide directory (e.g.
/content/drive/MyDrive/Slideson Colab, or a local directory). - Click Save Settings. The backend updates its active path on the fly and immediately lists the
.svsfiles found in the folder.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file patholens-2.0.4.tar.gz.
File metadata
- Download URL: patholens-2.0.4.tar.gz
- Upload date:
- Size: 11.3 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
01e6fe08bb3a00f7812c06e1c915204978328df98f4218282133a341b41f8577
|
|
| MD5 |
77085bb3f2cf99f0942911c1776d2ca9
|
|
| BLAKE2b-256 |
4d99eadc4e0e124e2635dd7005d35eafeb02d2728fd997ac8462d9bfe9b6985a
|
File details
Details for the file patholens-2.0.4-py3-none-any.whl.
File metadata
- Download URL: patholens-2.0.4-py3-none-any.whl
- Upload date:
- Size: 11.4 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
11f97346fdde55288559412e233d10e144b82ac6a6835d50792f5191619b6bf2
|
|
| MD5 |
342442dd025cbc0a41781599807efae9
|
|
| BLAKE2b-256 |
083ff537cb73cb2f7e343fb0450727dfb62bc9677df04eb7e87defd232340a6f
|