Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
0.1.43
by @SimFG in https://github.com/zilliztech/GPTCache/pull/580
Full Changelog: https://github.com/zilliztech/GPTCache/compare/0.1.42...0.1.43
0.1.42
by @SimFG in https://github.com/zilliztech/GPTCache/pull/546
Full Changelog: https://github.com/zilliztech/GPTCache/compare/0.1.41...0.1.42
Full Changelog: https://github.com/zilliztech/GPTCache/compare/0.1.40...0.1.41
Full Changelog: https://github.com/zilliztech/GPTCache/compare/0.1.39.1...0.1.40
Full Changelog: https://github.com/zilliztech/GPTCache/compare/0.1.39...0.1.39.1
Full Changelog: https://github.com/zilliztech/GPTCache/compare/0.1.38...0.1.39
Full Changelog: https://github.com/zilliztech/GPTCache/compare/0.1.37...0.1.38
0.1.37
by @SimFG in https://github.com/zilliztech/GPTCache/pull/494
Full Changelog: https://github.com/zilliztech/GPTCache/compare/0.1.36...0.1.37
redis
and mongo
store examples in the reference doc by @SimFG in https://github.com/zilliztech/GPTCache/pull/477
Full Changelog: https://github.com/zilliztech/GPTCache/compare/0.1.35...0.1.36
0.1.35
by @SimFG in https://github.com/zilliztech/GPTCache/pull/473
Full Changelog: https://github.com/zilliztech/GPTCache/compare/0.1.34...0.1.35