pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 12:32:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Feat: debugging toc part. (#10486)

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

#10436

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Kevin Hu
2025-10-11 18:45:21 +08:00
committed by GitHub
parent a0d5f81098
commit 7d2f65671f
6 changed files with 32 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
rag/flow/splitter/schema.py
View File

@ -25,7 +25,7 @@ class SplitterFromUpstream(BaseModel):
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)
output_format: Literal["json", "markdown", "text", "html", "chunks"] | 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")

4
rag/flow/tokenizer/tokenizer.py
View File

@ -126,7 +126,7 @@ class Tokenizer(ProcessBase):
if ck.get("summary"):
ck["content_ltks"] = rag_tokenizer.tokenize(str(ck["summary"]))
ck["content_sm_ltks"] = rag_tokenizer.fine_grained_tokenize(ck["content_ltks"])
else:
elif ck.get("text"):
ck["content_ltks"] = rag_tokenizer.tokenize(ck["text"])
ck["content_sm_ltks"] = rag_tokenizer.fine_grained_tokenize(ck["content_ltks"])
if i % 100 == 99:
@ -155,6 +155,8 @@ class Tokenizer(ProcessBase):
for i, ck in enumerate(chunks):
ck["title_tks"] = rag_tokenizer.tokenize(re.sub(r"\.[a-zA-Z]+$", "", from_upstream.name))
ck["title_sm_tks"] = rag_tokenizer.fine_grained_tokenize(ck["title_tks"])
if not ck.get("text"):
continue
ck["content_ltks"] = rag_tokenizer.tokenize(ck["text"])
ck["content_sm_ltks"] = rag_tokenizer.fine_grained_tokenize(ck["content_ltks"])
if i % 100 == 99: