v0.0.12

New parameters in llm decorator

support for llm_selector_rule_key to sub selection of LLM's to for consideration during selection. This enables you to enforce pick only some models (like GPT4 for instance) for particular prompts, or even for particular runs
support for function_source and memory_source to point pick properties/attributes of the instance prompt is bound to (aka self) as a source of functions and memories, so we won't need to send pass it in every time

v0.0.9

Version 0.0.9 (2023-06-17)

• fix some scenarios of LLM response that raised error
• save AIMessage with function call in output wrapper
• fix logging that we are out or stream context, when stream is not on

v0.0.8

Version 0.0.8 (2023-06-16)

• support for parsing via OpenAI functions 🚀
• support for controlling function_call
• add BIG_CONTEXT prompt type
• ton of bugfixes

v0.0.7

Version 0.0.7 (2023-06-15)

• fixed streaming capture
• better handling for missing docs for llm_function

v0.0.6

Version 0.0.6 (2023-06-15)

• fix some issues with async prompts

v0.0.5

Version 0.0.5 (2023-06-14)

• support for OpenAI functions 🚀

v0.0.4

Version 0.0.4 (2023-06-12)

• improved pydantic parser is not more tolerant to the casing (accepts pascalCase, snake_case, CamelCase field names, no matter what casing uses model)
• added boolean output parser

v0.0.3

• fix #2 - incorrect default LLM initialization enforcing OPENAI_API_KEY check
  (shoutout to @lukestanley who fixed it using Anthropic's LLM :)
• better pydantic and markdown output parser... now can self fix casing problems with keys (i.e. field in schema is "ceo_salary", now will accept "CEO salary" as well as "CeoSalary" and any other variations)

v0.0.2

• fixed typo that caused broken async executions 😅

0.0.1

• Initial release of the package.