Closed AumJavalgikar closed 9 months ago
The changes reflect an integration of a new memory_llm
parameter into the Program
class and the adjustment of memory management logic within the AI's architecture. BaseMemory
now includes new attributes for managing memory and LLM instances, while ReadOnlyMemory
emphasizes its immutable nature. The Summary
memory classes have been refactored to utilize a shared llm
instance, streamlining memory operations.
File Path | Change Summary |
---|---|
.../engine/_program.py |
Added memory_llm parameter to Program class; updated ConversationHistory usage; adjusted memory settings. |
.../memory/base.py & .../memory/summary.py |
Introduced llm and memory_threshold attributes; refactored to use shared llm instance. |
.../memory/read_only.py |
Removed __init__ method; clarified immutability in add_memory docstring. |
๐โจ To code, to build, a change we weave, Through lines of logic, we interleave. Memory's dance, a deft advance, In AI's realm, we enhance, enhance. ๐๐ฅ
Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?
Looks good to me . Merging this with main
fixing-memory branch This pull request fixes the following problems related to ai.memory:
You can now pass parameters to engine to specify an llm for memory, else it will use the engine's llm.
Summary by CodeRabbit
New Features
Documentation
Refactor