LLM 框架
用于在语言模型之上构建应用的主要编排库，按它们强加的抽象、以及日后移除这些抽象的难度来比较。
6 technologies
- LangChain framework Framework for composing language models with retrieval, tools and memory.
- LlamaIndex framework Data framework focused on ingesting, indexing and querying private knowledge.
- Hugging Face Transformers library Reference implementations and pretrained weights for transformer models, behind one API.
- PEFT library Parameter-efficient fine-tuning methods behind one interface.
- TRL library Training library for fine-tuning and aligning models on preference data.
- Haystack framework Framework for building retrieval and question-answering pipelines.