mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-12-08 20:42:30 +08:00
d86d7061ea
### What problem does this PR solve? Improve how to get total token count for AnthropicCV ### Type of change - [x] Refactoring
80 lines
2.3 KiB
Python
80 lines
2.3 KiB
Python
#
|
|
# Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
import os
|
|
|
|
import tiktoken
|
|
|
|
from api.utils.file_utils import get_project_base_directory
|
|
|
|
|
|
def singleton(cls, *args, **kw):
|
|
instances = {}
|
|
|
|
def _singleton():
|
|
key = str(cls) + str(os.getpid())
|
|
if key not in instances:
|
|
instances[key] = cls(*args, **kw)
|
|
return instances[key]
|
|
|
|
return _singleton
|
|
|
|
tiktoken_cache_dir = get_project_base_directory()
|
|
os.environ["TIKTOKEN_CACHE_DIR"] = tiktoken_cache_dir
|
|
# encoder = tiktoken.encoding_for_model("gpt-3.5-turbo")
|
|
encoder = tiktoken.get_encoding("cl100k_base")
|
|
|
|
|
|
def num_tokens_from_string(string: str) -> int:
|
|
"""Returns the number of tokens in a text string."""
|
|
try:
|
|
return len(encoder.encode(string))
|
|
except Exception:
|
|
return 0
|
|
|
|
def total_token_count_from_response(resp):
|
|
if hasattr(resp, "usage") and hasattr(resp.usage, "total_tokens"):
|
|
try:
|
|
return resp.usage.total_tokens
|
|
except Exception:
|
|
pass
|
|
|
|
if hasattr(resp, "usage_metadata") and hasattr(resp.usage_metadata, "total_tokens"):
|
|
try:
|
|
return resp.usage_metadata.total_tokens
|
|
except Exception:
|
|
pass
|
|
|
|
if 'usage' in resp and 'total_tokens' in resp['usage']:
|
|
try:
|
|
return resp["usage"]["total_tokens"]
|
|
except Exception:
|
|
pass
|
|
|
|
if 'usage' in resp and 'input_tokens' in resp['usage'] and 'output_tokens' in resp['usage']:
|
|
try:
|
|
return resp["usage"]["input_tokens"] + resp["usage"]["output_tokens"]
|
|
except Exception:
|
|
pass
|
|
return 0
|
|
|
|
|
|
def truncate(string: str, max_len: int) -> str:
|
|
"""Returns truncated text if the length of text exceed max_len."""
|
|
return encoder.decode(encoder.encode(string)[:max_len])
|
|
|
|
|