V0.2.2: support compress_json

What's Changed

• add feature: compress_json by @SiyunZhao in #120

Bug fixed

• Prevent duplicate torch_dtype kwargs by @yasyf in #115
• Feature(LLMLingua-2): fix the title by @iofu728 in #117
• Fix(LLMLingua-2): fix the chunk max seq by @pzs19 in #122
• Prereleased(LLMLinguia): fix the chuck issue and prepare for v0.2.2 by @pzs19, @QianhuiWu in #130

New Contributors

• @yasyf made their first contribution in #115

Full Changelog: v0.2.1...v0.2.2

V0.2.1: add LLMLingua-2

What's Changed

• Feature(LLMLingua-2): add LLMLingua-2 by @pzs19, @iofu728, @QianhuiWu in #111, #112

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

V0.2.0: support customized compression spec

What's Changed

• Feature (LLMLingua): support customized compression spec by @SiyunZhao in #96
• Feature(LLMLingua): add LangChain example by @iofu728 in #97
• Feature(LongLLMLingua): update conference by @iofu728 in #99
• Fix(LLMLingua): fix sentence-filter adding separator bug and add document by @SiyunZhao in #102
• Fix(LLMLingua): fix the release workflows by @iofu728 in #107, #108
• Release(LLMLingua): release v0.2.0 by @iofu728 in #109

Full Changelog: v0.1.6...v0.2.0

V0.1.6: support phi-2

What's Changed

• Feature(LLMLingua): add slide of AI Time. by @iofu728 in #42
• Feature(LLMLingua): add alt-gpt reference by @iofu728 in #56
• Feature(LLMLingua): support phi-2 by @iofu728 in #67
• Feature (LLMLingua): Add Docstring for PromptCompressor Class by @SiyunZhao in #69
• Feature(LLMLingua): update the FAQ by @iofu728 in #88

Bug Fixed

• Hotfix (LLMLingua): fix the out of range by @iofu728 in #87
• Fix (LLMLingua): fix the link of llama_index by @wlsdml1114 in #62
• Fix(LLMLingua): fix the force context ids and condition flag by @iofu728 in #59
• Fix (LLMLingua): Resolved a potential ZeroDivisionError caused by the actual compression ratio. by @davidberenstein1957 in #54
• Remove Duplicate Declaration of Loss Function by @Speuce in #38

New Contributors

• @Speuce made their first contribution in #38
• @davidberenstein1957 made their first contribution in #54
• @wlsdml1114 made their first contribution in #62

Full Changelog: v0.1.5...v0.1.6

V0.1.5: support mps

What's Changed

• Fix (LLMLingua): support mps, fix keep_flag out of dimension. by @iofu728 in #27
• Prerelease(LLMLingua): fix the license by @iofu728 in #32
• Fix typos by @bobchao in #26 and @eltociear in #30

New Contributors

• @bobchao made their first contribution in #26
• @eltociear made their first contribution in #30

Full Changelog: v0.1.4...v0.1.5

V0.1.4: support gpt-q

What's Changed

• Fixed(LLMLingua): fix the prefix dimension mismatch. by @iofu728 in #16
• Feature (LLMLingua): support GPT-Q by @iofu728 in #20

Full Changelog: v0.1.3...v0.1.4

V0.1.3: Add retrieval methods, examples, and project page

Features

• Add project page #9;
• Add examples #11;
• Support more reranker models and retrieval models #13;

Bug Fixed

• Fixed the 'context empty' issue #15;

What's Changed

• Feature(LLMLingua): release LLMLingua code & demo by @iofu728 in #2
• Feature(LLMLingua): update the news by @iofu728 in #9
• Feature(LLMLingua): add examples by @iofu728 in #11
• Feature(LongLLMLingua): support reranker model by @iofu728 in #13
• Fixed (LLMLingua): Resolved the issue where the context was coming up as empty by @iofu728 in #15

Full Changelog: v0.1.2...v0.1.3

V0.1.2: Release LLMLingua

Features

• LLMLingua Code;
• LongLLMLingua Code;
• LLMLingua Document;
• LLMLingua FAQ;
• LLMLingua HF Demo;
• LLMLingua Demo Video;

Full Changelog: https://github.com/microsoft/LLMLingua/commits/v0.1.2