* strip '/' and use osp.join
* grepped for MEMGPT_DIR, found more places to replace '/'
* typo
* grep pass over filesep
---------
Co-authored-by: Vivian Fang <hi@vivi.sh>
* trying to patch summarize when running with local llms
* moved token magic numbers to constants, made special localllm exception class (TODO catch these for retry), fix summarize bug where it exits early if empty list
* missing file
* raise an exception on no-op summary
* changed summarization logic to walk forwards in list until fraction of tokens in buffer is reached
* added same diff to sync agent
* reverted default max tokens to 8k, cleanup + more error wrapping for better error messages that get caught on retry
* patch for web UI context limit error propogation, using best guess for what the web UI error message is
* add webui token length exception
* remove print
* make no wrapper warning only pop up once
* cleanup
* Add errors to other wrappers
---------
Co-authored-by: Vivian Fang <hi@vivi.sh>
Currently, if you run the /memory command the application breaks if the LocalArchivalMemory
has no existing archival storage and defaults to the EmptyIndex. This is caused by EmptyIndex
not having a ref_doc_info implementation and throwing an Exception when that is used to print
the memory information to the console. This hot fix simply makes sure that we do not try to
use the function if using EmptyIndex and instead prints a message to the console indicating
an EmptyIndex is used.
* VectorIndex -> VectorStoreIndex
VectorStoreIndex is imported but non-existent VectorIndex is used.
* New wrapper for Zephyr family of models.
With inner thoughts.
* Update chat_completion_proxy.py for Zephyr Wrapper
