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

v2.0.0

• Revised system prompt
• Added LLM reranking to evidence
• Fixed bugs on keyfiltering to make it actually work
• Now catch exceptions in evidence

v1.12.0

• Added new parameter to set maximum concurrency in evidence gathering

v1.11.0

• Added support for fitz/PymuPDF reader for faster parsing times