镜像自地址
https://github.com/binary-husky/gpt_academic.git
已同步 2025-12-09 07:56:48 +00:00
tiktoken做lazyload处理
这个提交包含在:
@@ -68,8 +68,8 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
|
||||
|
||||
# 递归地切割PDF文件
|
||||
from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
|
||||
from toolbox import get_conf
|
||||
enc = tiktoken.encoding_for_model("gpt-3.5-turbo")
|
||||
from request_llm.bridge_all import model_info
|
||||
enc = model_info["gpt-3.5-turbo"]['tokenizer']
|
||||
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
|
||||
paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
|
||||
txt=file_content, get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT)
|
||||
|
||||
在新工单中引用
屏蔽一个用户