Build AI methods with your coding agent, then run them anywhere: as an MCP for chatbots, as a webapp for people, or via API for your software.
add changelog
thomashebrard3337cd7dcb36
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 48a419980..f7597a8ba 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -1,5 +1,24 @@# Changelog+## [v0.6.6] - 2023-10-10++### Added+- Added a new method `verify_content_type` in the `Stuff` class to verify and convert content to the expected type.+- Added `cocode==0.0.6` to the development dependencies in `pyproject.toml`.++### Changed+- Updated `Stuff` class methods to use the new `verify_content_type` method for content verification.+- Updated `vertexai.toml` to change LLM IDs from preview models to released models: `gemini-2.5-pro` and `gemini-2.5-flash`.++### Removed+- Removed `reinitlibraries`, `rl`, `v`, and `init` targets from the Makefile.++## [v0.6.5] - 2025-07-21++### Fixed++- In the documentation, fixed the use of `execute_pipeline`.+## [v0.6.4] - 2025-07-19- Fixed the `README.md` link to the documentationdiff --git a/pyproject.toml b/pyproject.tomlindex 17f14a350..777a6a955 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -1,6 +1,6 @@[project]name = "pipelex"-version = "0.6.5"+version = "0.6.6"description = "Pipelex is an open-source dev tool based on a simple declarative language that lets you define replicable, structured, composable LLM pipelines."authors = [{ name = "Evotis S.A.S.", email = "[email protected]" }]maintainers = [{ name = "Pipelex staff", email = "[email protected]" }]