chore: remove unused code (#22501)

Co-authored-by: 刘江波 <jiangbo721@163.com>
This commit is contained in:
jiangbo721 2025-07-17 09:33:31 +08:00 committed by GitHub
parent d2933c2bfe
commit fb5c6dd644
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 63 deletions

View File

@ -38,69 +38,6 @@ _logger = logging.getLogger(__name__)
class AppRunner:
def get_pre_calculate_rest_tokens(
self,
app_record: App,
model_config: ModelConfigWithCredentialsEntity,
prompt_template_entity: PromptTemplateEntity,
inputs: Mapping[str, str],
files: Sequence["File"],
query: Optional[str] = None,
) -> int:
"""
Get pre calculate rest tokens
:param app_record: app record
:param model_config: model config entity
:param prompt_template_entity: prompt template entity
:param inputs: inputs
:param files: files
:param query: query
:return:
"""
# Invoke model
model_instance = ModelInstance(
provider_model_bundle=model_config.provider_model_bundle, model=model_config.model
)
model_context_tokens = model_config.model_schema.model_properties.get(ModelPropertyKey.CONTEXT_SIZE)
max_tokens = 0
for parameter_rule in model_config.model_schema.parameter_rules:
if parameter_rule.name == "max_tokens" or (
parameter_rule.use_template and parameter_rule.use_template == "max_tokens"
):
max_tokens = (
model_config.parameters.get(parameter_rule.name)
or model_config.parameters.get(parameter_rule.use_template or "")
) or 0
if model_context_tokens is None:
return -1
if max_tokens is None:
max_tokens = 0
# get prompt messages without memory and context
prompt_messages, stop = self.organize_prompt_messages(
app_record=app_record,
model_config=model_config,
prompt_template_entity=prompt_template_entity,
inputs=inputs,
files=files,
query=query,
)
prompt_tokens = model_instance.get_llm_num_tokens(prompt_messages)
rest_tokens: int = model_context_tokens - max_tokens - prompt_tokens
if rest_tokens < 0:
raise InvokeBadRequestError(
"Query or prefix prompt is too long, you can reduce the prefix prompt, "
"or shrink the max token, or switch to a llm with a larger token limit size."
)
return rest_tokens
def recalc_llm_max_tokens(
self, model_config: ModelConfigWithCredentialsEntity, prompt_messages: list[PromptMessage]
):