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

Feat: add splitter (#10161)

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


### Type of change
- [x] New Feature (non-breaking change which adds functionality)

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: Lynn <lynn_inf@hotmail.com>
Co-authored-by: chanx <1243304602@qq.com>
Co-authored-by: balibabu <cike8899@users.noreply.github.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>
This commit is contained in:
Kevin Hu
2025-09-19 10:15:19 +08:00
committed by GitHub
parent f9c7404bee
commit a1b947ffd6
81 changed files with 3083 additions and 799 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
api/db/db_models.py
View File

@ -646,6 +646,7 @@ class Knowledgebase(DataBaseModel):
vector_similarity_weight = FloatField(default=0.3, index=True)
parser_id = CharField(max_length=32, null=False, help_text="default parser ID", default=ParserType.NAIVE.value, index=True)
pipeline_id = CharField(max_length=32, null=True, help_text="Pipeline ID", index=True)
parser_config = JSONField(null=False, default={"pages": [[1, 1000000]]})
pagerank = IntegerField(default=0, index=False)
status = CharField(max_length=1, null=True, help_text="is it validate(0: wasted, 1: validate)", default="1", index=True)
@ -662,6 +663,7 @@ class Document(DataBaseModel):
thumbnail = TextField(null=True, help_text="thumbnail base64 string")
kb_id = CharField(max_length=256, null=False, index=True)
parser_id = CharField(max_length=32, null=False, help_text="default parser ID", index=True)
pipeline_id = CharField(max_length=32, null=True, help_text="pipleline ID", index=True)
parser_config = JSONField(null=False, default={"pages": [[1, 1000000]]})
source_type = CharField(max_length=128, null=False, default="local", help_text="where dose this document come from", index=True)
type = CharField(max_length=32, null=False, help_text="file extension", index=True)
@ -1020,7 +1022,6 @@ def migrate_db():
migrate(migrator.add_column("dialog", "meta_data_filter", JSONField(null=True, default={})))
except Exception:
pass
try:
migrate(migrator.alter_column_type("canvas_template", "title", JSONField(null=True, default=dict, help_text="Canvas title")))
except Exception:
@ -1037,4 +1038,12 @@ def migrate_db():
migrate(migrator.add_column("canvas_template", "canvas_category", CharField(max_length=32, null=False, default="agent_canvas", help_text="agent_canvas|dataflow_canvas", index=True)))
except Exception:
pass
try:
migrate(migrator.add_column("knowledgebase", "pipeline_id", CharField(max_length=32, null=True, help_text="default parser ID", index=True)))
except Exception:
pass
try:
migrate(migrator.add_column("document", "pipeline_id", CharField(max_length=32, null=True, help_text="default parser ID", index=True)))
except Exception:
pass
logging.disable(logging.NOTSET)