v3.0.0.dev3

• Added memory model

v3.0.0

Breaking changes in v3

See README

Release Notes:

• Added memory model
• Changed variable naming to be much more clear
• More types to avoid ambiguous dictionary/tuples
• Switched to using pydantic instead of dataclasses
• Removed non-core focus elements (caching, token counting, agents)
• Removed need to have texts/doc names in Docs, removing RAM problems
• Abstracted FAISS away, so any vector store can be used
• Removed ambiguous chunk/overlap defaults
• Added typewriter example to README
• Added caching example to README
• Made prompting more general
• Can pass by FileObj|Path|URL in add - (add, add_file, add_url)
• Reduce code duplication in unit tests
• Added more flexible typing, exported more types, added back reader default args

Contributors: @whitead and @Mason-McGough

v3.0.0.dev2

• Added more flexible typing, exported more types, added back reader default args

v3.0.0.dev1

Fixed pickling bug about missing attribute and updated README

v3.0.0.dev0

• Changed variable naming to be much more clear
• More types to avoid ambiguous dictionary/tuples
• Switched to using pydantic instead of dataclasses
• Removed non-core focus elements (caching, token counting, agents)
• Removed need to have texts/doc names in Docs, removing RAM problems
• Abstracted FAISS away, so any vector store can be used
• Removed ambiguous chunk/overlap defaults
• Added typewriter example to README
• Added caching example to README
• Made prompting more general
• Added unit tests for new name_in_text function
• Can pass by FileObj|Path|URL in add - (maybe add_path, add_file, add_url)
• Reduce code duplication in unit tests

v2.1.1

Fixed bug in add_text not adding to Docs if an existing store is present

v.2.1.0

• Added dockeys to contexts
• Now we check hash on both add_text and add

v2.0.3

• Made key_filters part of Answer object

v2.0.2

• Added hash to document previews

v2.0.1

• Removed extra print statement