Skip to main content

VLM-RECog

A Python library for zero-shot object detection and segmentation using Vision-Language Models (VLMs), built on Google's Gemini 2.5 Flash model.

Installation

pip install vlm-recog
export GEMINI_API_KEY=<your_api_key>

Requirements

  • Python 3.11+
  • Google Gemini API key (set as GEMINI_API_KEY environment variable)

Quick Start

from PIL import Image
from vlm_recog.detection import detect
from vlm_recog.visualization import draw_detections

# Load an image
image = Image.open("path/to/image.jpg")

# Detect objects by text labels
result = detect(image, ["dog", "bicycle", "person"])

# Visualize results
output_image = draw_detections(image, result)
output_image.show()

Demo

output

Metadata

Release files for vlm-recog 0.1.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for vlm-recog 0.1.2
File Size Uploaded Provenance Actions
vlm_recog-0.1.2.tar.gz 940.1 kB Without provenance Details for vlm_recog-0.1.2.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for vlm-recog 0.1.2
File Interpreter ABI Platform Actions
vlm_recog-0.1.2-py3-none-any.whl Python 3 none any Details for vlm_recog-0.1.2-py3-none-any.whl

Total release size: 947.0 kB

Release files / vlm_recog-0.1.2.tar.gz

Download URL vlm_recog-0.1.2.tar.gz
Size 940.1 kB
Tags Source
SHA-256 checksum
How to use checksums
b7964c0540c672437ac41ab51fd1df97e748cbc5de68a9356a9c8ed8ae9a22bc
BLAKE2b-256 checksum
How to use checksums
6489960535e15c2a03fb01f9c542ff070a76e0e1f2c41ccd47d660185675fcb1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.5.13

Release files / vlm_recog-0.1.2-py3-none-any.whl

Download URL vlm_recog-0.1.2-py3-none-any.whl
Size 6.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
ad93614a7ae81031cc1e3f8ded12c9a7eeb1e981e1e6fb95f0efedaafa633217
BLAKE2b-256 checksum
How to use checksums
9c3e408c4a3f23dc9d4c9e8c96c7cd88ddce78950825ad607704f39010b02cc9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.5.13

Security for vlm-recog 0.1.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page