⛓️v0.3.6 - langchain v0.3 support and typing fixes

• langchain v0.3 support
• typing fixes

⛓️v0.3.4 - azure, groq and fixes

• support for azure openai
• support for groq json mode
• multiple small bug fixes
• added new openai model identifiers (gpt-4o and turbo)
• simplifying config files
• update deps

⛓️ v0.3.3 - fix jinja format instructions

• fix format instructions when using jinja

⛓️ v0.3.2 - claude3 support

✨ ruff fmt

⛓️v0.3.0 - funcchain dependencies

Introducing a dependency injection system like you know from FastAPI!

⛓️ v0.2.3

• fix .env loading with settings
• fix input dict type
• fix prefix for model selection
• fix support for new openai models
• fix default settings.llm handling
• improved README shields

⛓️ v0.2.2

• support for primitive dict types
• improved local model info
• fix in output type selector
• fix .env loading
• fix langchain deprecation warning

⛓️v0.2.1 - fix fix + small improvements

• fix primitive type parsing when using openai
• Fix typo strem_to -> stream_to by @ahuang11 in #17
• fix README.md by @shroominic in #25
• fix pop model_name by @ahuang11 in #24
• add ollama_base_url setting by @jquesnelle in #21
• add system prompt to chain by @ahuang11 in #20
• improve chat handlers

New Contributors

• @ahuang11 made their first contribution in #17
• @jquesnelle made their first contribution in #21

Full Changelog: v0.2.0...v0.2.1

⛓️v0.2.0 - new features + docs

NEW DOCUMENTATION:
https://shroominic.github.io/funcchain/

IMPROVEMENTS:
🔗 langchain lcel compatibility (runnable decorator)
🔍 primitive type parsers
🔄 dynamic chat routers
📄 full jinja2 templating
🚦 enums, literal output types
🦙 llamacpp + ollama support
📡 openai json mode streaming
🔁 auto retry for pydantic validations
👁️ better vision support
✍️ create custom parsing types
🏗️ codebase restructuring
⬆️ updated deps

Full Changelog: v0.1.10...v0.2.0

⛓️ v0.2.0-alpha.1

• settings namespace changes to lowercase (breaking)
• easy local model support
• function input arguments ignore everything not string
• more tests
• auto gguf model download from huggingface
• dependency split into
  • core pip install funcchain
  • local pip install "funcchain[local]"
  • openai pip install "funcchain[openai]"
  • all pip install "funcchain[all]"
• internal code structure improvements