33 lines
1.2 KiB
Python
33 lines
1.2 KiB
Python
from esperanto import LanguageModel
|
|
from langchain_core.language_models.chat_models import BaseChatModel
|
|
from loguru import logger
|
|
|
|
from open_notebook.domain.models import model_manager
|
|
from open_notebook.utils import token_count
|
|
|
|
|
|
async def provision_langchain_model(
|
|
content, model_id, default_type, **kwargs
|
|
) -> BaseChatModel:
|
|
"""
|
|
Returns the best model to use based on the context size and on whether there is a specific model being requested in Config.
|
|
If context > 105_000, returns the large_context_model
|
|
If model_id is specified in Config, returns that model
|
|
Otherwise, returns the default model for the given type
|
|
"""
|
|
tokens = token_count(content)
|
|
|
|
if tokens > 105_000:
|
|
logger.debug(
|
|
f"Using large context model because the content has {tokens} tokens"
|
|
)
|
|
model = await model_manager.get_default_model("large_context", **kwargs)
|
|
elif model_id:
|
|
model = await model_manager.get_model(model_id, **kwargs)
|
|
else:
|
|
model = await model_manager.get_default_model(default_type, **kwargs)
|
|
|
|
logger.debug(f"Using model: {model}")
|
|
assert isinstance(model, LanguageModel), f"Model is not a LanguageModel: {model}"
|
|
return model.to_langchain()
|