v0.5.0pre3 - openAI retries

pre3 (#230)

v0.5.0pre2 - limit summary length

bump version (#228)

v0.5.0pre1 - use openAI structured output

Non-openai clients may not work with this pre-release

v0.4.3 - don't escape unicode system prompt

add unicode escape (#224)

* add unicode escape

* bump version

v0.4.2 - reduce DB connections

add delete nodes by group_id (#217)

* add delete nodes by group_id

* remove unused imports

* bump version

v0.4.1 - improve full text edge search performance

Update edge search (#216)

* update edge fulltext search

* bump version

v0.4.0 - Add reflexion and reduce ingestion and search latency

• add_episode now uses reflexion to achieve more accurate results during graph creation
• add_episode and search should now have reduced latency

v0.3.21 - handle empty search queries

return no results with empty search string (#206)

* return no results with empty search string

* update

* bump version

v0.3.20 - add bulk write operation and optional parallel runtime

Bulk add nodes and edges (#205)

* test

* only use parallel runtime if set to true

* add and test bulk add

* remove group_ids

* format

* bump version

* update readme

v0.3.19 - fix embedder issue

v0.3.19 - fix embedder issue