v0.2.4

Version 0.2.4. This release brings the following changes:

• Added support for reasoning models. VScan now allows configuring the amount of tokens a config can spend on a task, and setting the reasoning effort to be used in the process.
• The conversation screen got a major rewamp. Now it offers detailed information about token usage of the entire conversation, as well as individual generated messages. If the model includes reasoning in its output, it can be displayed separately for each response. The conversation list now also supports accessibility actions, letting the user to edit messages and regenerate responses.
• Updated the database of models. VScan now recognizes over 80 common large language models with vision support, including the latest releases of GPT, Claude, Gemini, Qwen, Gemma and Mistral.
• Added presets for Google and Mistral, updated existing presets for OpenAI, OpenRouter and NanoGPt.
• Fixed various minor bugs and issues. Changing model on the Options tab should now be immediately applied to the conversation, custom model identifiers should now work properly when defined in providers, the Options tab got slightly reorganized and should offer a better experience.

v0.2.3

Version 0.2.3. This release brings the following changes:

• There is now a standalone editor for entering the system prompt and user prompt. This editor has a large text field, which should make it easy to work with long and complex prompts.
• Various UI improvements and bug fixes.

v0.2.2

Version 0.2.2. This is a hotfix release of version 0.2.1, fixing a bug with displaying the bottom navigation bar.

v0.2.1

Version 0.2.1. This release brings quite a few important changes, see below:

• VScan can now be used with any OpenAI protocol compatible LLM server and model, making the app fully universal and independent. See the project's readme for more details about the new architecture and instructions on setting it up. Thanks to this change, now it's even possible to use self-hosted models, giving the users a full control over their data and privacy.
• VScan now recognizes 25 common proprietary, open-weight and open-source models, including LLMs from the GPT, Claude, Gemini, Gemma, Llama and Qwen families, while 5 different backends are supported out of the box. The users are indeed free to configure any provider or model they wish to use with the app, as far as it supports the required protocol.
• The main scanning screen undervent a slight redesign. It now features a multipurpose edit field, which by default can be used to send a message to the current conversation, but if the user activates the system prompt or user prompt button on the upper bar, they can also configure these parameters right from the scanning screen. It is still possible to use voice input for these actions, which can be performed by long-pressing the respective buttons, although this feature is not yet fully tuned up.
• Users can now also configure various actions for events such as pressing / long pressing volume buttons or shaking the phone. The actions include capturing a photo to be processed by a config, consulting a config or sending a message to the model by voice. The shaking event is not yet properly supported, a deeper sensor integration is on the roadmap.
• Auto describing saved images is now configurable and switched of by default, just like using the flashlight, in order to avoid surprises.

v0.2

v0.2

Version 0.2. VScan undervent a complete app rewamp, both in terms of design and philosophy. Version 0.2 features a highly efficiency and functionality focused interface. It adds, as the most important feature, the ability to save different configurations of system / user prompt, camera, GPT model, intended for a particular purpose determined by the user. These configurations can afterwards be easily selected or consulted, as well as be configured for a special purpose like describing images shared with the app. The following is the list of the most notable changes:

• Rewamped the user interface
• Added saving configuration profiles for various purposes
• Added support for sharing pictures with the app
• added support for the front camera
• Added an option to select GPT model per configuration
• Added captured image saving capability with auto-description
• Added conversation list with message copying capabilities
• Added an option to consult the captured image with various configurations
• Added support for asking questions and setting system / user prompt using voice from the main screen

v0.1.3

Version 0.1.3. This release makes the camera use the device orientation when taking pictures. Thanks to this change, the scan screen now uses the system orientation and does not influence taken images.

v0.1.2

Version 0.1.2.

• Added Camera shutter sound
• Replaced TTS messages with toasts, improving communication integration
• The camera shutter button on the scanning screen has been made to fill all available space, making it easy to find using Explore by touch
• Sending messages and setting the API key can be now done by submitting from the keyboard
• Various minor bug-fixes

v0.1.1

Version 0.1.1. This release fixes the versioning to be in sync with the code repository.

v0.1

Version 0.1. The initial release.