remove unused import (#2679)

### What problem does this PR solve?

### Type of change

- [x] Refactoring

rag/app/audio.py

@@ -10,9 +10,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
-import io
 import re
-import numpy as np
 
 from api.db import LLMType
 from rag.nlp import rag_tokenizer

rag/app/book.py

@@ -15,9 +15,9 @@ import re
 from io import BytesIO
 
 from deepdoc.parser.utils import get_text
-from rag.nlp import bullets_category, is_english, tokenize, remove_contents_table, \
+from rag.nlp import bullets_category, is_english,remove_contents_table, \
-    hierarchical_merge, make_colon_as_title, naive_merge, random_choices, tokenize_table, add_positions, \
+    hierarchical_merge, make_colon_as_title, naive_merge, random_choices, tokenize_table, \
-    tokenize_chunks, find_codec
+    tokenize_chunks
 from rag.nlp import rag_tokenizer
 from deepdoc.parser import PdfParser, DocxParser, PlainParser, HtmlParser
 

rag/app/laws.py

@@ -10,7 +10,6 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
-import copy
 from tika import parser
 import re
 from io import BytesIO
@@ -18,8 +17,8 @@ from docx import Document
 
 from api.db import ParserType
 from deepdoc.parser.utils import get_text
-from rag.nlp import bullets_category, is_english, tokenize, remove_contents_table, hierarchical_merge, \
+from rag.nlp import bullets_category, remove_contents_table, hierarchical_merge, \
-    make_colon_as_title, add_positions, tokenize_chunks, find_codec, docx_question_level
+    make_colon_as_title, tokenize_chunks, docx_question_level
 from rag.nlp import rag_tokenizer
 from deepdoc.parser import PdfParser, DocxParser, PlainParser, HtmlParser
 from rag.settings import cron_logger

rag/app/manual.py

@@ -19,13 +19,13 @@ import re
 
 from api.db import ParserType
 from io import BytesIO
-from rag.nlp import rag_tokenizer, tokenize, tokenize_table, add_positions, bullets_category, title_frequency, tokenize_chunks, docx_question_level
+from rag.nlp import rag_tokenizer, tokenize, tokenize_table, bullets_category, title_frequency, tokenize_chunks, docx_question_level
-from deepdoc.parser import PdfParser, PlainParser
 from rag.utils import num_tokens_from_string
-from deepdoc.parser import PdfParser, ExcelParser, DocxParser
+from deepdoc.parser import PdfParser, PlainParser, DocxParser
 from docx import Document
 from PIL import Image
 
+
 class Pdf(PdfParser):
     def __init__(self):
         self.model_speciess = ParserType.MANUAL.value

rag/app/naive.py

@@ -25,6 +25,7 @@ from functools import reduce
 from markdown import markdown
 from docx.image.exceptions import UnrecognizedImageError
 
+
 class Docx(DocxParser):
     def __init__(self):
         pass
@@ -93,7 +94,7 @@ class Docx(DocxParser):
 
         tbls = []
         for tb in self.doc.tables:
-            html= "<table>"
+            html = "<table>"
             for r in tb.rows:
                 html += "<tr>"
                 i = 0
@@ -146,8 +147,6 @@ class Pdf(PdfParser):
 
 class Markdown(MarkdownParser):
     def __call__(self, filename, binary=None):
-        txt = ""
-        tbls = []
         if binary:
             encoding = find_codec(binary)
             txt = binary.decode(encoding, errors="ignore")

rag/app/paper.py

@@ -12,13 +12,11 @@
 #
 import copy
 import re
-from collections import Counter
 
 from api.db import ParserType
 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
 
 
 class Pdf(PdfParser):
@@ -135,7 +133,6 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
         Only pdf is supported.
         The abstract of the paper will be sliced as an entire chunk, and will not be sliced partly.
     """
-    pdf_parser = None
     if re.search(r"\.pdf$", filename, re.IGNORECASE):
         if not kwargs.get("parser_config", {}).get("layout_recognize", True):
             pdf_parser = PlainParser()

rag/app/qa.py

@@ -14,7 +14,6 @@ import re
 from copy import deepcopy
 from io import BytesIO
 from timeit import default_timer as timer
-from nltk import word_tokenize
 from openpyxl import load_workbook
 
 from deepdoc.parser.utils import get_text