Skip to content

v0.22.0
Compare
Choose a tag to compare
@collindutter collindutter released this 11 Jan 18:57
· 637 commits to dev since this release
v0.22.0
77f028c
This commit was created on github.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Verified
Learn about vigilant mode.

Added

  • PromptImageGenerationEngine for generating images from text prompts.
  • VariationImageGenerationEngine for generating variations of an input image according to a text prompt.
  • InpaintingImageGenerationEngine for modifying an input image according to a text prompt within the bounds of a mask defined by a mask image.
  • OutpaintingImageGenerationEngine for modifying an input image according to a text prompt outside the bounds of a mask defined by a mask image.
  • PromptImageGenerationClient for enabling an LLM to use the PromptImageGenerationEngine.
  • VariationImageGenerationClient for enabling an LLM to use the VariationImageGenerationEngine.
  • InpaintingImageGenerationClient for enabling an LLM to use the InpaintingImageGenerationEngine.
  • OutpaintingImageGenerationClient for enabling an LLM to use the OutpaintingImageGenerationEngine.
  • OpenAiImageGenerationDriver for use with OpenAI's image generation models.
  • LeonardoImageGenerationDriver for use with Leonoaro AI's image generation models.
  • AmazonBedrockImageGenerationDriver for use with Amazon Bedrock's image generation models; requires a Image Generation Model Driver.
  • BedrockTitanImageGenerationModelDriver for use with Amazon Bedrock's Titan image generation.
  • ImageArtifact for storing image data; used heavily by the image Engines, Tasks, and Drivers.
  • ImageLoader for loading images files into ImageArtifacts.
  • Support for all Tokenizers in OpenAiChatPromptDriver, enabling OpenAI drop-in clients such as Together AI.
  • AmazonSageMakerEmbeddingDriver for using Amazon SageMaker to generate embeddings. Thanks @KaushikIyer16!
  • Claude 2.1 support in AnthropicPromptDriver and AmazonBedrockPromptDriver via BedrockClaudePromptModelDriver.
  • CodeExecutionTask for executing code as a Task without the need for an LLM.
  • BedrockLlamaPromptModelDriver for using Llama models on Amazon Bedrock.

Fixed

  • MongoDbAtlasVectorStore namespace not being used properly when querying.
  • Miscellaneous type errors throughout the codebase.
  • Remove unused section from ToolTask system prompt template.
  • Structure execution args being cleared after run, preventing inspection of the Structure's input_task's input.
  • Unhandled SqlClient exception. Thanks @michal-repo!

Changed

  • BREAKING: Rename input_template field to input in Tasks that take a text input.
  • BREAKING: Rename BedrockTitanEmbeddingDriver to AmazonBedrockTitanEmbeddingDriver.
  • BREAKING: Rename AmazonBedrockStableDiffusionImageGenerationModelDriver to BedrockStableDiffusionImageGenerationModelDriver.
  • BREAKING: Rename AmazonBedrockTitanImageGenerationModelDriver to BedrockTitanImageGenerationModelDriver.
  • BREAKING: Rename ImageGenerationTask to PromptImageGenerationTask.
  • BREAKING: Rename ImageGenerationEngine to PromptImageGenerationEngine.
  • BREAKING: Rename ImageGenerationTool to PromptImageGenerationClient.
  • Improve system prompt generation with Claude 2.0.
  • Improve integration test coverage.
  • BaseTextInputTask to accept a str, TextArtifact or callable returning a TextArtifact.

Contributors

michal-repo and KaushikIyer16
Assets 2
Loading