Decart Plugin for Vision Agents
Decart integration for Vision Agents framework, enabling real-time video restyling capabilities.
It enables features such as:
- Real-time video transformation using generative AI models
- Dynamic style changing via prompts
- Seamless integration with Vision Agents video pipeline
Installation
uv add "vision-agents[decart]"
# or directly
uv add vision-agents-plugins-decart
Usage
This example shows how to use the RestylingProcessor to transform a user's video feed in real-time.
from vision_agents.core import User, Agent
from vision_agents.plugins import getstream, gemini, decart
processor = decart.RestylingProcessor(
initial_prompt="Studio Ghibli animation style",
model="lucy_2_rt",
)
agent = Agent(
edge=getstream.Edge(),
agent_user=User(name="Styled AI"),
instructions="Be helpful",
llm=gemini.Realtime(),
processors=[processor],
)
Dynamic Prompt Updates
You can register a function to update the style prompt dynamically based on the conversation:
@llm.register_function(
description="Change the video style prompt"
)
async def change_style(prompt: str) -> str:
await processor.update_prompt(prompt)
return f"Style changed to: {prompt}"
Reference Images ("costumes")
For models like Lucy that accept a reference image, pass it at construction
time and/or swap it atomically with a prompt via update_state:
processor = decart.RestylingProcessor(
model="lucy_2_rt",
initial_prompt="A person wearing a superhero costume",
initial_image="./costumes/superhero.png", # your own reference image
)
# Later — atomically change prompt + reference image
await processor.update_state(
prompt="A person wearing a wizard robe",
image="./costumes/wizard.png",
)
# Image-only update
await processor.update_state(image=b"<raw image bytes>")
initial_image and update_state(image=...) accept bytes, a local file
path, an http(s) URL, a data: URI, or a raw base64 string.
Configuration
The plugin requires a Decart API key. You can provide it in two ways:
- Set the environment variable
DECART_API_KEY - Pass it directly to the constructor:
RestylingProcessor(api_key="...")
Links
Metadata
Release files for vision-agents-plugins-decart 0.6.9
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| vision_agents_plugins_decart-0.6.9.tar.gz | 6.6 kB | Without provenance | Details for vision_agents_plugins_decart-0.6.9.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| vision_agents_plugins_decart-0.6.9-py3-none-any.whl | Python 3 | none | any | Details for vision_agents_plugins_decart-0.6.9-py3-none-any.whl |
Total release size: 13.9 kB
Release files / vision_agents_plugins_decart-0.6.9.tar.gz
| Download URL | vision_agents_plugins_decart-0.6.9.tar.gz |
|---|---|
| Size | 6.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
38812e9595c3f479c13a147937ebc202e2913ef3765a27c359c159fdd09c9c59
|
|
BLAKE2b-256 checksum How to use checksums |
154541abd295d85bf87d54caf80d4b549bb99d0cc918d744eb00063cd6f248ef
|
| Upload date | |
|
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_decart-0.6.9-py3-none-any.whl
| Download URL | vision_agents_plugins_decart-0.6.9-py3-none-any.whl |
|---|---|
| Size | 7.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e121313b9b0075dd2a6a07ac7392e6f6bdb515c49884df03869ca44540f41d51
|
|
BLAKE2b-256 checksum How to use checksums |
5b6472c8ccb3e828f3281152ccb62dcf27b1bad6cb5aadfcb4b983c4599ff844
|
| Upload date | |
|
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}
|
Security for vision-agents-plugins-decart 0.6.9
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.