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

Light GraphRAG (#4585)

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

#4543

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Kevin Hu
2025-01-22 19:43:14 +08:00
committed by GitHub
parent 1a367664f1
commit dd0ebbea35
55 changed files with 5461 additions and 4000 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
rag/app/book.py
View File

@ -88,9 +88,9 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
callback(0.8, "Finish parsing.")
elif re.search(r"\.pdf$", filename, re.IGNORECASE):
pdf_parser = Pdf() if kwargs.get(
"parser_config", {}).get(
"layout_recognize", True) else PlainParser()
pdf_parser = Pdf()
if kwargs.get("layout_recognize", "DeepDOC") == "Plain Text":
pdf_parser = PlainParser()
sections, tbls = pdf_parser(filename if not binary else binary,
from_page=from_page, to_page=to_page, callback=callback)

2
rag/app/email.py
View File

@ -40,7 +40,7 @@ def chunk(
eng = lang.lower() == "english" # is_english(cks)
parser_config = kwargs.get(
"parser_config",
{"chunk_token_num": 128, "delimiter": "\n!?。；！？", "layout_recognize": True},
{"chunk_token_num": 128, "delimiter": "\n!?。；！？", "layout_recognize": "DeepDOC"},
)
doc = {
"docnm_kwd": filename,

48
rag/app/knowledge_graph.py
View File

@ -1,48 +0,0 @@
#
# Copyright 2025 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 re
from graphrag.index import build_knowledge_graph_chunks
from rag.app import naive
from rag.nlp import rag_tokenizer, tokenize_chunks
def chunk(filename, binary, tenant_id, from_page=0, to_page=100000,
lang="Chinese", callback=None, **kwargs):
parser_config = kwargs.get(
"parser_config", {
"chunk_token_num": 512, "delimiter": "\n!?;。；！？", "layout_recognize": True})
eng = lang.lower() == "english"
parser_config["layout_recognize"] = True
sections = naive.chunk(filename, binary, from_page=from_page, to_page=to_page, section_only=True,
parser_config=parser_config, callback=callback)
chunks = build_knowledge_graph_chunks(tenant_id, sections, callback,
parser_config.get("entity_types", ["organization", "person", "location", "event", "time"])
)
for c in chunks:
c["docnm_kwd"] = filename
doc = {
"docnm_kwd": filename,
"title_tks": rag_tokenizer.tokenize(re.sub(r"\.[a-zA-Z]+$", "", filename)),
"knowledge_graph_kwd": "text"
}
doc["title_sm_tks"] = rag_tokenizer.fine_grained_tokenize(doc["title_tks"])
chunks.extend(tokenize_chunks(sections, doc, eng))
return chunks

6
rag/app/laws.py
View File

@ -162,9 +162,9 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
return tokenize_chunks(chunks, doc, eng, None)
elif re.search(r"\.pdf$", filename, re.IGNORECASE):
pdf_parser = Pdf() if kwargs.get(
"parser_config", {}).get(
"layout_recognize", True) else PlainParser()
pdf_parser = Pdf()
if kwargs.get("layout_recognize", "DeepDOC") == "Plain Text":
pdf_parser = PlainParser()
for txt, poss in pdf_parser(filename if not binary else binary,
from_page=from_page, to_page=to_page, callback=callback)[0]:
sections.append(txt + poss)

6
rag/app/manual.py
View File

@ -184,9 +184,9 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
# is it English
eng = lang.lower() == "english" # pdf_parser.is_english
if re.search(r"\.pdf$", filename, re.IGNORECASE):
pdf_parser = Pdf() if kwargs.get(
"parser_config", {}).get(
"layout_recognize", True) else PlainParser()
pdf_parser = Pdf()
if kwargs.get("layout_recognize", "DeepDOC") == "Plain Text":
pdf_parser = PlainParser()
sections, tbls = pdf_parser(filename if not binary else binary,
from_page=from_page, to_page=to_page, callback=callback)
if sections and len(sections[0]) < 3:

9
rag/app/naive.py
View File

@ -202,7 +202,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
is_english = lang.lower() == "english" # is_english(cks)
parser_config = kwargs.get(
"parser_config", {
"chunk_token_num": 128, "delimiter": "\n!?。；！？", "layout_recognize": True})
"chunk_token_num": 128, "delimiter": "\n!?。；！？", "layout_recognize": "DeepDOC"})
doc = {
"docnm_kwd": filename,
"title_tks": rag_tokenizer.tokenize(re.sub(r"\.[a-zA-Z]+$", "", filename))
@ -231,8 +231,11 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
return res
elif re.search(r"\.pdf$", filename, re.IGNORECASE):
pdf_parser = Pdf() if parser_config.get("layout_recognize", True) else PlainParser()
sections, tables = pdf_parser(filename if not binary else binary, from_page=from_page, to_page=to_page, callback=callback)
pdf_parser = Pdf()
if parser_config.get("layout_recognize", "DeepDOC") == "Plain Text":
pdf_parser = PlainParser()
sections, tables = pdf_parser(filename if not binary else binary, from_page=from_page, to_page=to_page,
callback=callback)
res = tokenize_table(tables, doc, is_english)
elif re.search(r"\.xlsx?$", filename, re.IGNORECASE):

6
rag/app/one.py
View File

@ -84,9 +84,9 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
callback(0.8, "Finish parsing.")
elif re.search(r"\.pdf$", filename, re.IGNORECASE):
pdf_parser = Pdf() if kwargs.get(
"parser_config", {}).get(
"layout_recognize", True) else PlainParser()
pdf_parser = Pdf()
if kwargs.get("layout_recognize", "DeepDOC") == "Plain Text":
pdf_parser = PlainParser()
sections, _ = pdf_parser(
filename if not binary else binary, to_page=to_page, callback=callback)
sections = [s for s, _ in sections if s]

2
rag/app/paper.py
View File

@ -144,7 +144,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
The abstract of the paper will be sliced as an entire chunk, and will not be sliced partly.
"""
if re.search(r"\.pdf$", filename, re.IGNORECASE):
if not kwargs.get("parser_config", {}).get("layout_recognize", True):
if kwargs.get("parser_config", {}).get("layout_recognize", "DeepDOC") == "Plain Text":
pdf_parser = PlainParser()
paper = {
"title": filename,

6
rag/app/presentation.py
View File

@ -119,9 +119,9 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
res.append(d)
return res
elif re.search(r"\.pdf$", filename, re.IGNORECASE):
pdf_parser = Pdf() if kwargs.get(
"parser_config", {}).get(
"layout_recognize", True) else PlainPdf()
pdf_parser = Pdf()
if kwargs.get("layout_recognize", "DeepDOC") == "Plain Text":
pdf_parser = PlainParser()
for pn, (txt, img) in enumerate(pdf_parser(filename, binary,
from_page=from_page, to_page=to_page, callback=callback)):
d = copy.deepcopy(doc)