Skip to main content
LLM provider factories + the LangGraph checkpoint/store registries. The chat-model and embedding factories cache per (provider, kwargs) and import their langchain provider package lazily inside the build; the registry accessors return the running event loop’s singletons that pool checkpoint/store connection resources. Importing this package pulls langchain_core / langgraph — that is the opt-in boundary (the tai42_kit top level stays vendor-free).

​
checkpoint_registry

tai42_kit.llm.checkpoint.checkpoint_registry.checkpoint_registry
Return the CheckpointRegistry for the running event loop. One registry per loop; after close_all() the next call builds a fresh registry instead of returning the closed one.

​
get_embedding

tai42_kit.llm.embedding.get_embedding
Build (or return the cached) Embeddings client for provider with the given kwargs. Parameters

​
get_embedding_async

tai42_kit.llm.embedding.get_embedding_async
Build (or return the cached) Embeddings client for provider, off the event loop. Parameters

​
get_llm

tai42_kit.llm.models.get_llm
Build (or return the cached) chat model for provider with the given kwargs. Parameters

​
get_llm_async

tai42_kit.llm.models.get_llm_async
Build the chat model for provider in a worker thread, off the event loop. Parameters

​
store_registry

tai42_kit.llm.store.store_registry.store_registry
Return the StoreRegistry for the running event loop. One registry per loop; after close_all() the next call builds a fresh registry instead of returning the closed one.