Functionality

Category: Functionality

Description: Implemented several enhancements to the Groq transcription model, including an improved tooltip message for the Prompt field, displaying full language names in the UI, and renaming "Language" to "Input Language".

Impact: Users will benefit from clearer interface guidance and more intuitive language handling, enhancing overall user experience.

CATEGORY: Functionality

DESCRIPTION: Integrated the Firecrawl model into PromptForm, expanding model options for app building operations.

IMPACT: Users gain access to additional models, broadening their capabilities in AI-driven applications while enhancing flexibility.

CATEGORY: Functionality

DESCRIPTION: Resolved an issue where the "system prompt" was missing for the Claude model. Fix ensures system products are available as expected.

IMPACT: Users employing Claude for model operations will experience reliable prompt functionality, enhancing overall performance and consistency.

CATEGORY: Functionality

DESCRIPTION: Added loop functionality in the flow editor, enabling users to iterate through items in comma or newline lists, like "Apples, Bananas, Pears."

IMPACT: Provides enhanced control over prompt flows, allowing users to efficiently process and utilize list structures within applications.

CATEGORY: Functionality

DESCRIPTION: Introduced support for extended thinking with Claude 3.7, allowing up to 128k max tokens for richer AI interactions.

IMPACT: Users can engage in more complex and lengthy prompt interactions, expanding the potential for detailed AI responses.

CATEGORY: Functionality

DESCRIPTION: Implemented a website relation for the apps, aligning application and website management more closely.

IMPACT: Users benefit from improved integration between apps and their respective websites, ensuring coherent management and operation.

CATEGORY: Functionality

DESCRIPTION: Added the new Stable Diffusion 3.5 model from Stability AI, implementing the Medium variant for enhanced prompt chaining capabilities.

IMPACT: Users can leverage the advanced features of the updated model to create more captivating and creative AI-generated content efficiently.

CATEGORY: Functionality

DESCRIPTION: Corrected a bug causing unwanted "Save" text to appear during copy/paste operations in apps with the "Edit Results" option enabled.

IMPACT: Users will now have cleaner copy/paste outputs, enhancing their workflow efficiency.

CATEGORY: Functionality

DESCRIPTION: Implemented new credit charge methods including Combined Credits, Usage Credits Only, and Base Credits Only, offering flexible billing options for AI usage.

IMPACT: Allows partners to select billing options that best suit their application needs, offering greater control over pricing strategies.

CATEGORY: Functionality

DESCRIPTION: Introduced a billing section in website settings to charge credits based on API usage for features such as refinements, image actions, and including dynamic bot pricing.

IMPACT: Users can now set API cost values per 1 credit, to allow dynamically charging for AI usage, enhancing their monetization strategies.

CATEGORY: Functionality

DESCRIPTION: Removed the option of charging specifically for MidJourney image actions from the model section area, transitioning to a dynamic pricing method.

IMPACT: Simplifies the charging process by using a uniform usage credits method, streamlining user experience.

CATEGORY: Functionality

DESCRIPTION: Deprecated outdated Groq and Perplexity models, replacing them with updated versions for superior performance.

IMPACT: Users will benefit from improved performance and reliability with the newly integrated models, optimizing their application interactions.