pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-25 16:26:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

Feat: debug extractor... (#10294)

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

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Kevin Hu
2025-09-26 10:51:05 +08:00
committed by GitHub
parent ff49454501
commit c7efaab30e
10 changed files with 27 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@ -31,7 +31,7 @@ class TokenizerFromUpstream(BaseModel):
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: list[str] | None = Field(default=None, alias="html")
html_result: str | None = Field(default=None, alias="html")
model_config = ConfigDict(populate_by_name=True, extra="forbid")

2
rag/flow/tokenizer/tokenizer.py
View File

@ -119,7 +119,7 @@ class Tokenizer(ProcessBase):
if ck.get("questions"):
ck["question_tks"] = rag_tokenizer.tokenize("\n".join(ck["questions"]))
if ck.get("keywords"):
ck["important_tks"] = rag_tokenizer.tokenize("\n".join(ck["keywords"]))
ck["important_tks"] = rag_tokenizer.tokenize(",".join(ck["keywords"]))
if ck.get("summary"):
ck["content_ltks"] = rag_tokenizer.tokenize(ck["summary"])
ck["content_sm_ltks"] = rag_tokenizer.fine_grained_tokenize(ck["content_ltks"])