pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

refine code (#595)

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

### Type of change

- [x] Refactoring
This commit is contained in:
KevinHuSh
2024-04-28 19:13:33 +08:00
committed by GitHub
parent aee8b48d2f
commit 8c07992b6c
24 changed files with 538 additions and 116 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
rag/app/paper.py
View File

@ -15,7 +15,7 @@ import re
from collections import Counter
from api.db import ParserType
from rag.nlp import huqie, tokenize, tokenize_table, add_positions, bullets_category, title_frequency, tokenize_chunks
from rag.nlp import rag_tokenizer, tokenize, tokenize_table, add_positions, bullets_category, title_frequency, tokenize_chunks
from deepdoc.parser import PdfParser, PlainParser
import numpy as np
from rag.utils import num_tokens_from_string
@ -153,10 +153,10 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
else:
raise NotImplementedError("file type not supported yet(pdf supported)")
doc = {"docnm_kwd": filename, "authors_tks": huqie.qie(paper["authors"]),
"title_tks": huqie.qie(paper["title"] if paper["title"] else filename)}
doc["title_sm_tks"] = huqie.qieqie(doc["title_tks"])
doc["authors_sm_tks"] = huqie.qieqie(doc["authors_tks"])
doc = {"docnm_kwd": filename, "authors_tks": rag_tokenizer.tokenize(paper["authors"]),
"title_tks": rag_tokenizer.tokenize(paper["title"] if paper["title"] else filename)}
doc["title_sm_tks"] = rag_tokenizer.fine_grained_tokenize(doc["title_tks"])
doc["authors_sm_tks"] = rag_tokenizer.fine_grained_tokenize(doc["authors_tks"])
# is it English
eng = lang.lower() == "english" # pdf_parser.is_english
print("It's English.....", eng)