ec2bda4966
* mark depricated API section * CLI bug fixes for azure * check azure before running * Update README.md * Update README.md * bug fix with persona loading * remove print * make errors for cli flags more clear * format * fix imports * fix imports * add prints * update lock * update config fields * cleanup config loading * commit * remove asserts * refactor configure * put into different functions * add embedding default * pass in config * fixes * allow overriding openai embedding endpoint * black * trying to patch tests (some circular import errors) * update flags and docs * patched support for local llms using endpoint and endpoint type passed via configs, not env vars * missing files * fix naming * fix import * fix two runtime errors * patch ollama typo, move ollama model question pre-wrapper, modify question phrasing to include link to readthedocs, also have a default ollama model that has a tag included * disable debug messages * made error message for failed load more informative * don't print dynamic linking function warning unless --debug * updated tests to work with new cli workflow (disabled openai config test for now) * added skips for tests when vars are missing * update bad arg * revise test to soft pass on empty string too * don't run configure twice * extend timeout (try to pass against nltk download) * update defaults * typo with endpoint type default * patch runtime errors for when model is None * catching another case of 'x in model' when model is None (preemptively) * allow overrides to local llm related config params * made model wrapper selection from a list vs raw input * update test for select instead of input * Fixed bug in endpoint when using local->openai selection, also added validation loop to manual endpoint entry * updated error messages to be more informative with links to readthedocs * add back gpt3.5-turbo --------- Co-authored-by: cpacker <packercharles@gmail.com>
55 lines
1.8 KiB
Python
55 lines
1.8 KiB
Python
import os
|
|
import tiktoken
|
|
|
|
import memgpt.local_llm.llm_chat_completion_wrappers.airoboros as airoboros
|
|
import memgpt.local_llm.llm_chat_completion_wrappers.dolphin as dolphin
|
|
import memgpt.local_llm.llm_chat_completion_wrappers.zephyr as zephyr
|
|
|
|
|
|
class DotDict(dict):
|
|
"""Allow dot access on properties similar to OpenAI response object"""
|
|
|
|
def __getattr__(self, attr):
|
|
return self.get(attr)
|
|
|
|
def __setattr__(self, key, value):
|
|
self[key] = value
|
|
|
|
# following methods necessary for pickling
|
|
def __getstate__(self):
|
|
return vars(self)
|
|
|
|
def __setstate__(self, state):
|
|
vars(self).update(state)
|
|
|
|
|
|
def load_grammar_file(grammar):
|
|
# Set grammar
|
|
grammar_file = os.path.join(os.path.dirname(os.path.abspath(__file__)), "grammars", f"{grammar}.gbnf")
|
|
|
|
# Check if the file exists
|
|
if not os.path.isfile(grammar_file):
|
|
# If the file doesn't exist, raise a FileNotFoundError
|
|
raise FileNotFoundError(f"The grammar file {grammar_file} does not exist.")
|
|
|
|
with open(grammar_file, "r") as file:
|
|
grammar_str = file.read()
|
|
|
|
return grammar_str
|
|
|
|
|
|
def count_tokens(s: str, model: str = "gpt-4") -> int:
|
|
encoding = tiktoken.encoding_for_model(model)
|
|
return len(encoding.encode(s))
|
|
|
|
|
|
def get_available_wrappers() -> dict:
|
|
return {
|
|
"airoboros-l2-70b-2.1": airoboros.Airoboros21InnerMonologueWrapper(),
|
|
"airoboros-l2-70b-2.1-grammar": airoboros.Airoboros21InnerMonologueWrapper(include_opening_brace_in_prefix=False),
|
|
"dolphin-2.1-mistral-7b": dolphin.Dolphin21MistralWrapper(),
|
|
"dolphin-2.1-mistral-7b-grammar": dolphin.Dolphin21MistralWrapper(include_opening_brace_in_prefix=False),
|
|
"zephyr-7B": zephyr.ZephyrMistralInnerMonologueWrapper(),
|
|
"zephyr-7B-grammar": zephyr.ZephyrMistralInnerMonologueWrapper(include_opening_brace_in_prefix=False),
|
|
}
|