AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-08-12 18:19:13 +08:00
Code Issues Packages Projects Releases Wiki Activity

refine code to prevent exception (#1231)

Browse Source 
### What problem does this PR solve?


### Type of change

- [x] Refactoring
This commit is contained in:
KevinHuSh 2024-06-21 14:06:46 +08:00 committed by GitHub
parent 18f4a6b35c
commit 15bf9f8c25
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
rag/app/naive.py
View File

@ -153,7 +153,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
txt += l txt += l
sections = [] sections = []
for sec in txt.split("\n"): for sec in txt.split("\n"):
if num_tokens_from_string(sec) > 10 * parser_config.get("chunk_token_num", 128): if num_tokens_from_string(sec) > 10 * int(parser_config.get("chunk_token_num", 128)):
sections.append((sec[:int(len(sec)/2)], "")) sections.append((sec[:int(len(sec)/2)], ""))
sections.append((sec[int(len(sec)/2):], "")) sections.append((sec[int(len(sec)/2):], ""))
else: else:
@ -169,7 +169,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
elif re.search(r"\.json$", filename, re.IGNORECASE): elif re.search(r"\.json$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.") callback(0.1, "Start to parse.")
sections = JsonParser(parser_config.get("chunk_token_num", 128))(binary) sections = JsonParser(int(parser_config.get("chunk_token_num", 128)))(binary)
sections = [(l, "") for l in sections if l] sections = [(l, "") for l in sections if l]
callback(0.8, "Finish parsing.") callback(0.8, "Finish parsing.")
@ -187,8 +187,8 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
st = timer() st = timer()
chunks = naive_merge( chunks = naive_merge(
sections, parser_config.get( sections, int(parser_config.get(
"chunk_token_num", 128), parser_config.get( "chunk_token_num", 128)), parser_config.get(
"delimiter", "\n!?。；！？")) "delimiter", "\n!?。；！？"))
res.extend(tokenize_chunks(chunks, doc, eng, pdf_parser)) res.extend(tokenize_chunks(chunks, doc, eng, pdf_parser))