Skip to content

Releases: paulomtts/py-ai-toolkit

Feat: convenience method for generate task subtrees

01 Jan 11:13

Choose a tag to compare

Convenience method for generating task subtrees with auto-validation & self-healing.

Feat: embeddings

28 Dec 20:50

Choose a tag to compare

Support for embedding generation.

Fix: split validations issues

28 Dec 17:10

Choose a tag to compare

FIxed an issue with split validations where validation nodes would output strings due to mismatching overloads.

Enh: create_validation_nodes overloads

28 Dec 16:43

Choose a tag to compare

Added overloads to create_validation_nodes()

Feat: split validation nodes

28 Dec 16:36

Choose a tag to compare

Validation can now be split with one node per test.

Fix: eval issues

28 Dec 16:29

Choose a tag to compare

  • Eval issues now follow the _eval naming pattern for prompting purposes
  • Only failed tests are fed back into the task's eval for reprocessing

Fix: .task() issue

28 Dec 15:44

Choose a tag to compare

Fixed an issue where BaseWorkflow.task() would return a boolean instead of the node's output.

Fix: exposed LLMConfig import

28 Dec 15:36

Choose a tag to compare

Exposed missing LLMConfig import.

Fix: create_validation_nodes output evals

28 Dec 15:27

Choose a tag to compare

create_validation_nodes now evaluates outputs from source node at runtime.

BaseValidation & others

28 Dec 15:16

Choose a tag to compare

  • Added BaseValidation class & builder method (in BaseWorkflow).
  • Enhanced type injection to inherit all Field properties from the parent class.
  • Alternative models made available for validation nodes.