mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-12-08 20:42:30 +08:00
Feat: Use data pipeline to visualize the parsing configuration of the knowledge base (#10423)
### What problem does this PR solve? #9869 ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: jinhai <haijin.chn@gmail.com> Signed-off-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: chanx <1243304602@qq.com> Co-authored-by: balibabu <cike8899@users.noreply.github.com> Co-authored-by: Lynn <lynn_inf@hotmail.com> Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com> Co-authored-by: huangzl <huangzl@shinemo.com> Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com> Co-authored-by: Wilmer <33392318@qq.com> Co-authored-by: Adrian Weidig <adrianweidig@gmx.net> Co-authored-by: Zhichang Yu <yuzhichang@gmail.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Yongteng Lei <yongtengrey@outlook.com> Co-authored-by: Liu An <asiro@qq.com> Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com> Co-authored-by: BadwomanCraZY <511528396@qq.com> Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com> Co-authored-by: Russell Valentine <russ@coldstonelabs.org> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Billy Bao <newyorkupperbay@gmail.com> Co-authored-by: Zhedong Cen <cenzhedong2@126.com> Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com> Co-authored-by: TensorNull <tensor.null@gmail.com> Co-authored-by: TeslaZY <TeslaZY@outlook.com> Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com> Co-authored-by: AB <aj@Ajays-MacBook-Air.local> Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com> Co-authored-by: He Wang <wanghechn@qq.com> Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com> Co-authored-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com> Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box> Co-authored-by: Stephen Hu <stephenhu@seismic.com> Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com> Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com> Co-authored-by: mxc <mxc@example.com> Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com> Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com> Co-authored-by: mcoder6425 <mcoder64@gmail.com> Co-authored-by: lemsn <lemsn@msn.com> Co-authored-by: lemsn <lemsn@126.com> Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com> Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com> Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>
This commit is contained in:
15
rag/flow/splitter/__init__.py
Normal file
15
rag/flow/splitter/__init__.py
Normal file
@ -0,0 +1,15 @@
|
||||
#
|
||||
# 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.
|
||||
|
||||
38
rag/flow/splitter/schema.py
Normal file
38
rag/flow/splitter/schema.py
Normal file
@ -0,0 +1,38 @@
|
||||
#
|
||||
# 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.
|
||||
from typing import Any, Literal
|
||||
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
|
||||
class SplitterFromUpstream(BaseModel):
|
||||
created_time: float | None = Field(default=None, alias="_created_time")
|
||||
elapsed_time: float | None = Field(default=None, alias="_elapsed_time")
|
||||
|
||||
name: str
|
||||
file: dict | None = Field(default=None)
|
||||
chunks: list[dict[str, Any]] | None = Field(default=None)
|
||||
|
||||
output_format: Literal["json", "markdown", "text", "html"] | None = Field(default=None)
|
||||
|
||||
json_result: list[dict[str, Any]] | None = Field(default=None, alias="json")
|
||||
markdown_result: str | None = Field(default=None, alias="markdown")
|
||||
text_result: str | None = Field(default=None, alias="text")
|
||||
html_result: str | None = Field(default=None, alias="html")
|
||||
|
||||
model_config = ConfigDict(populate_by_name=True, extra="forbid")
|
||||
|
||||
# def to_dict(self, *, exclude_none: bool = True) -> dict:
|
||||
# return self.model_dump(by_alias=True, exclude_none=exclude_none)
|
||||
111
rag/flow/splitter/splitter.py
Normal file
111
rag/flow/splitter/splitter.py
Normal file
@ -0,0 +1,111 @@
|
||||
#
|
||||
# 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 random
|
||||
from functools import partial
|
||||
|
||||
import trio
|
||||
|
||||
from api.utils import get_uuid
|
||||
from api.utils.base64_image import id2image, image2id
|
||||
from deepdoc.parser.pdf_parser import RAGFlowPdfParser
|
||||
from rag.flow.base import ProcessBase, ProcessParamBase
|
||||
from rag.flow.splitter.schema import SplitterFromUpstream
|
||||
from rag.nlp import naive_merge, naive_merge_with_images
|
||||
from rag.utils.storage_factory import STORAGE_IMPL
|
||||
|
||||
|
||||
class SplitterParam(ProcessParamBase):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.chunk_token_size = 512
|
||||
self.delimiters = ["\n"]
|
||||
self.overlapped_percent = 0
|
||||
|
||||
def check(self):
|
||||
self.check_empty(self.delimiters, "Delimiters.")
|
||||
self.check_positive_integer(self.chunk_token_size, "Chunk token size.")
|
||||
self.check_decimal_float(self.overlapped_percent, "Overlapped percentage: [0, 1)")
|
||||
|
||||
def get_input_form(self) -> dict[str, dict]:
|
||||
return {}
|
||||
|
||||
|
||||
class Splitter(ProcessBase):
|
||||
component_name = "Splitter"
|
||||
|
||||
async def _invoke(self, **kwargs):
|
||||
try:
|
||||
from_upstream = SplitterFromUpstream.model_validate(kwargs)
|
||||
except Exception as e:
|
||||
self.set_output("_ERROR", f"Input error: {str(e)}")
|
||||
return
|
||||
|
||||
deli = ""
|
||||
for d in self._param.delimiters:
|
||||
if len(d) > 1:
|
||||
deli += f"`{d}`"
|
||||
else:
|
||||
deli += d
|
||||
|
||||
self.set_output("output_format", "chunks")
|
||||
self.callback(random.randint(1, 5) / 100.0, "Start to split into chunks.")
|
||||
if from_upstream.output_format in ["markdown", "text", "html"]:
|
||||
if from_upstream.output_format == "markdown":
|
||||
payload = from_upstream.markdown_result
|
||||
elif from_upstream.output_format == "text":
|
||||
payload = from_upstream.text_result
|
||||
else: # == "html"
|
||||
payload = from_upstream.html_result
|
||||
|
||||
if not payload:
|
||||
payload = ""
|
||||
|
||||
cks = naive_merge(
|
||||
payload,
|
||||
self._param.chunk_token_size,
|
||||
deli,
|
||||
self._param.overlapped_percent,
|
||||
)
|
||||
self.set_output("chunks", [{"text": c.strip()} for c in cks if c.strip()])
|
||||
|
||||
self.callback(1, "Done.")
|
||||
return
|
||||
|
||||
# json
|
||||
sections, section_images = [], []
|
||||
for o in from_upstream.json_result or []:
|
||||
sections.append((o.get("text", ""), o.get("position_tag", "")))
|
||||
section_images.append(id2image(o.get("img_id"), partial(STORAGE_IMPL.get)))
|
||||
|
||||
chunks, images = naive_merge_with_images(
|
||||
sections,
|
||||
section_images,
|
||||
self._param.chunk_token_size,
|
||||
deli,
|
||||
self._param.overlapped_percent,
|
||||
)
|
||||
cks = [
|
||||
{
|
||||
"text": RAGFlowPdfParser.remove_tag(c),
|
||||
"image": img,
|
||||
"positions": [[pos[0][-1]+1, *pos[1:]] for pos in RAGFlowPdfParser.extract_positions(c)],
|
||||
}
|
||||
for c, img in zip(chunks, images) if c.strip()
|
||||
]
|
||||
async with trio.open_nursery() as nursery:
|
||||
for d in cks:
|
||||
nursery.start_soon(image2id, d, partial(STORAGE_IMPL.put), get_uuid())
|
||||
self.set_output("chunks", cks)
|
||||
self.callback(1, "Done.")
|
||||
Reference in New Issue
Block a user