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: 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

6
rag/svr/task_executor.py
View File

@ -370,14 +370,14 @@ async def build_chunks(task, progress_callback):
nursery.start_soon(doc_question_proposal, chat_mdl, d, task["parser_config"]["auto_questions"])
progress_callback(msg="Question generation {} chunks completed in {:.2f}s".format(len(docs), timer() - st))
if task["parser_config"].get("toc_extraction", True):
if task["parser_id"].lower() == "naive" and task["parser_config"].get("toc_extraction", False):
progress_callback(msg="Start to generate table of content ...")
chat_mdl = LLMBundle(task["tenant_id"], LLMType.CHAT, llm_name=task["llm_id"], lang=task["language"])
docs = sorted(docs, key=lambda d:(
d.get("page_num_int", 0)[0] if isinstance(d.get("page_num_int", 0), list) else d.get("page_num_int", 0),
d.get("top_int", 0)[0] if isinstance(d.get("top_int", 0), list) else d.get("top_int", 0)
))
toc: list[dict] = await run_toc_from_text([d["content_with_weight"] for d in docs], chat_mdl)
toc: list[dict] = await run_toc_from_text([d["content_with_weight"] for d in docs], chat_mdl, progress_callback)
logging.info("------------ T O C -------------\n"+json.dumps(toc, ensure_ascii=False, indent=' '))
ii = 0
while ii < len(toc):
@ -387,7 +387,7 @@ async def build_chunks(task, progress_callback):
toc[ii]["ids"] = [docs[idx]["id"]]
if ii == len(toc) -1:
break
for jj in range(idx+1, int(toc[ii+1]["chunk_id"])):
for jj in range(idx+1, int(toc[ii+1]["chunk_id"])+1):
toc[ii]["ids"].append(docs[jj]["id"])
except Exception as e:
logging.exception(e)