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 extractor component. (#10271)

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
2025-09-25 11:34:47 +08:00
committed by GitHub
parent 840b2b5809
commit 1b19d302c5
16 changed files with 379 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
rag/flow/tokenizer/tokenizer.py
View File

@ -120,8 +120,12 @@ class Tokenizer(ProcessBase):
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["content_ltks"] = rag_tokenizer.tokenize(ck["text"])
ck["content_sm_ltks"] = rag_tokenizer.fine_grained_tokenize(ck["content_ltks"])
if ck.get("summary"):
ck["content_ltks"] = rag_tokenizer.tokenize(ck["summary"])
ck["content_sm_ltks"] = rag_tokenizer.fine_grained_tokenize(ck["content_ltks"])
else:
ck["content_ltks"] = rag_tokenizer.tokenize(ck["text"])
ck["content_sm_ltks"] = rag_tokenizer.fine_grained_tokenize(ck["content_ltks"])
if i % 100 == 99:
self.callback(i * 1.0 / len(chunks) / parts)