* patch TEI error in load (now get different error)
* more hiding of MOCKLLM
* fix embedding dim
* refactored bandaid patches into custom embedding class return object patch
* add folder generation
* disable default temp until more testing is done
* apply embedding payload patch to search, add input checking for better runtime error messages
* streamlined memory pressure warning now that heartbeats get forced
* Raise a custom keyerror instead of basic keyerror to clarify issue to LLM processor
* remove self value from error message passed to LLM processor
* simplify error message propogated to llm processor
* stripped LLM_MAX_TOKENS constant, instead it's a dictionary, and context_window is set via the config (defaults to 8k)
* pass context window in the calls to local llm APIs
* safety check
* remove dead imports
* context_length -> context_window
* add default for agent.load
* in configure, ask for the model context window if not specified via dictionary
* fix default, also make message about OPENAI_API_BASE missing more informative
* make openai default embedding if openai is default llm
* make openai on top of list
* typo
* also make local the default for embeddings if you're using localllm instead of the locallm endpoint
* provide --context_window flag to memgpt run
* fix runtime error
* stray comments
* stray comment
* Remove AsyncAgent and async from cli
Refactor agent.py memory.py
Refactor interface.py
Refactor main.py
Refactor openai_tools.py
Refactor cli/cli.py
stray asyncs
save
make legacy embeddings not use async
Refactor presets
Remove deleted function from import
* remove stray prints
* typo
* another stray print
* patch test
---------
Co-authored-by: cpacker <packercharles@gmail.com>
* 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
