4 Commits

Author	SHA1	Message	Date
Reinier van der Leer	2eb346e06e	Improve prompting and prompt generation infrastructure (#5076) ... * Clean up prompt generation * Rename Performance Evaluations to Best Practices * Move specification of response format from system prompt to Agent.construct_base_prompt * Clean up PromptGenerator class * Add debug logging to AIConfig autogeneration * Clarify prompting and add support for multiple thought processes to Agent	2023-07-29 10:06:47 -07:00
James Collins	89c1f2d0c0	Remove dead agent manager (#4900) ... * Remove dead agent manager --------- Co-authored-by: Reinier van der Leer <github@pwuts.nl>	2023-07-08 23:50:12 +02:00
Erik Peterson	07d9b584f7	Correct and clean up JSON handling (#4655) ... * Correct and clean up JSON handling * Use ast for message history too * Lint * Add comments explaining why we use literal_eval * Add descriptions to llm_response_format schema * Parse responses in code blocks * Be more careful when parsing in code blocks * Lint	2023-06-13 09:54:50 -07:00
DGdev91	42a5a0ce13	Make prompt parameters configurable (#3375) ... Co-authored-by: Nicholas Tindle <nick@ntindle.com> Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>	2023-05-17 20:12:10 +03:00