Roboflow Plugin

Object detection using Roboflow's hosted inference API for vision-agents.

Installation

uv add "vision-agents[roboflow]"
# or directly
uv add vision-agents-plugins-roboflow

Quick Start

from vision_agents.plugins import roboflow
from vision_agents.core import Agent

# A Roboflow processor for cloud inference and
# pre-trained models from Roboflow Universe https://universe.roboflow.com/.
processor = roboflow.RoboflowCloudDetectionProcessor(
    api_key="your_api_key",  # or set ROBOFLOW_API_KEY env var
    api_url="https://detect.roboflow.com",  # or set ROBOFLOW_API_URL env var
    model_id="football-players-detection-3zvbc/20",
    classes=["player"],
    conf_threshold=0.5,
    fps=3,
)

# You can also use a Roboflow processor with local inference and RF-DETR models.
processor = roboflow.RoboflowLocalDetectionProcessor(
    model_id="rfdetr-seg-preview",
    conf_threshold=0.5,
    classes=["person"],
    fps=3,
    # You can pass a custom model as "model" parameter here.
    # The model must be an instance of `rfdetr.RFDETR()` class.
    # model=MyRF_DETRModel()
)

# Use in an agent
agent = Agent(
    processors=[processor],
    llm=your_llm,
    # ... other components
)

Full Example

See example/roboflow_example.py for a complete working example with a video call agent that uses Roboflow detection.

RoboflowCloudDetectionProcessor Configuration

model_id: Roboflow Universe model id. Example - "football-players-detection-3zvbc/20".
api_key: Roboflow API key. If not provided, will use ROBOFLOW_API_KEY env variable.
api_url: Roboflow API url. If not provided, will use ROBOFLOW_API_URL env variable.
conf_threshold: Confidence threshold for detections (0 - 1.0). Default - 0.5.
fps: Frame processing rate. Default - 5.
classes: an optional list of class names to be detected. Example - ["person", "sports ball"] Verify that the classes a supported by the given model. Default - None (all classes are detected). annotate: if True, annotate the detected objects with boxes and labels. Default - True.
dim_background_factor: how much to dim the background around detected objects from 0 to 1.0. Effective only when annotate=True. Default - 0.0 (no dimming).
client: an optional custom instance of inference_sdk.InferenceHTTPClient.

RoboflowLocalDetectionProcessor Configuration

model_id: identifier of the model to be used. Available models are: "rfdetr-base", "rfdetr-large", "rfdetr-nano", "rfdetr-small", "rfdetr-medium", " rfdetr-seg-preview". Default - "rfdetr-seg-preview".
conf_threshold: Confidence threshold for detections (0 - 1.0). Default - 0.5.
fps: Frame processing rate. Default - 10.
classes: optional list of class names to be detected. Example: ["person", "sports ball"] Verify that the classes a supported by the given model. Default - None (all classes are detected).
annotate: if True, annotate the detected objects with boxes and labels. Default - True.
dim_background_factor: how much to dim the background around detected objects from 0 to 1.0. Effective only when annotate=True. Default - 0.0 (no dimming).
model: optional instance of RFDETRModel to be used for detections. Use it provide a model of choosing with custom parameters.

Testing

# Run all tests
pytest plugins/roboflow/tests/ -v

# Run specific tests
pytest plugins/roboflow/tests/test_roboflow.py -v

Dependencies

vision-agents - Core framework
numpy>=2.0.0 - Array operations
rfdetr>=1.3.0 - RF-DETR models for local object detection
inference-sdk>=0.26.1 - Roboflow SDK for cloud inference

Metadata

Release files for vision-agents-plugins-roboflow 0.6.9

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

Source distribution (sdist)

Source distribution for vision-agents-plugins-roboflow 0.6.9
File	Size	Uploaded
vision_agents_plugins_roboflow-0.6.9.tar.gz	11.6 kB	Aug 13, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for vision-agents-plugins-roboflow 0.6.9
File	Interpreter	ABI	Platform	Reset
vision_agents_plugins_roboflow-0.6.9-py3-none-any.whl 12.8 kB Aug 13, 2026	Python 3	none	any	Details

Total release size: 24.4 kB

Release files / vision_agents_plugins_roboflow-0.6.9.tar.gz

Download URL	vision_agents_plugins_roboflow-0.6.9.tar.gz
Size	11.6 kB
Tags	Source
SHA-256 checksum How to use checksums	`6ca882afb3b0429b383af27958ba669caa5594e3b9bbd3000804700291a21347`
BLAKE2b-256 checksum How to use checksums	`62c354a9f14add378d64dc880151bca06227129d2908379c8fe376a692d7a325`
Upload date	Aug 13, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.10.10 {"installer":{"name":"uv","version":"0.10.10","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}`

Release files / vision_agents_plugins_roboflow-0.6.9-py3-none-any.whl

Download URL	vision_agents_plugins_roboflow-0.6.9-py3-none-any.whl
Size	12.8 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`b446d8f1ff978a82c9c4356fa5952169dc8d58ac18f82d1ffd1fc42aba07f16a`
BLAKE2b-256 checksum How to use checksums	`f5909a39a8dcc11dc7cfd2ec507e4e1e14556488b347ab4b5263f798c900c66e`
Upload date	Aug 13, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.10.10 {"installer":{"name":"uv","version":"0.10.10","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}`