Feat: add initial support for Mindmap (#10310)

### What problem does this PR solve?

Add initial support for Mindmap.

### Type of change

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

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
This commit is contained in:
Yongteng Lei
2025-09-26 19:45:01 +08:00
committed by GitHub
parent 76b1ee2a00
commit 4c0a89f262
8 changed files with 182 additions and 63 deletions

View File

@ -636,8 +636,6 @@ class DocumentService(CommonService):
prg = 0
finished = True
bad = 0
has_raptor = False
has_graphrag = False
e, doc = DocumentService.get_by_id(d["id"])
status = doc.run # TaskStatus.RUNNING.value
priority = 0
@ -649,25 +647,14 @@ class DocumentService(CommonService):
prg += t.progress if t.progress >= 0 else 0
if t.progress_msg.strip():
msg.append(t.progress_msg)
if t.task_type == "raptor":
has_raptor = True
elif t.task_type == "graphrag":
has_graphrag = True
priority = max(priority, t.priority)
prg /= len(tsks)
if finished and bad:
prg = -1
status = TaskStatus.FAIL.value
elif finished:
if (d["parser_config"].get("raptor") or {}).get("use_raptor") and not has_raptor:
queue_raptor_o_graphrag_tasks(d, "raptor", priority)
prg = 0.98 * len(tsks) / (len(tsks) + 1)
elif (d["parser_config"].get("graphrag") or {}).get("use_graphrag") and not has_graphrag:
queue_raptor_o_graphrag_tasks(d, "graphrag", priority)
prg = 0.98 * len(tsks) / (len(tsks) + 1)
else:
prg = 1
status = TaskStatus.DONE.value
prg = 1
status = TaskStatus.DONE.value
msg = "\n".join(sorted(msg))
info = {
@ -679,7 +666,7 @@ class DocumentService(CommonService):
info["progress"] = prg
if msg:
info["progress_msg"] = msg
if msg.endswith("created task graphrag") or msg.endswith("created task raptor"):
if msg.endswith("created task graphrag") or msg.endswith("created task raptor") or msg.endswith("created task mindmap"):
info["progress_msg"] += "\n%d tasks are ahead in the queue..."%get_queue_length(priority)
else:
info["progress_msg"] = "%d tasks are ahead in the queue..."%get_queue_length(priority)
@ -770,7 +757,8 @@ def queue_raptor_o_graphrag_tasks(doc, ty, priority, fake_doc_id="", doc_ids=[])
"from_page": 100000000,
"to_page": 100000000,
"task_type": ty,
"progress_msg": datetime.now().strftime("%H:%M:%S") + " created task " + ty
"progress_msg": datetime.now().strftime("%H:%M:%S") + " created task " + ty,
"begin_at": datetime.now(),
}
task = new_task()
@ -780,7 +768,7 @@ def queue_raptor_o_graphrag_tasks(doc, ty, priority, fake_doc_id="", doc_ids=[])
task["digest"] = hasher.hexdigest()
bulk_insert_into_db(Task, [task], True)
if ty in ["graphrag", "raptor"]:
if ty in ["graphrag", "raptor", "mindmap"]:
task["doc_ids"] = doc_ids
DocumentService.begin2parse(doc["id"])
assert REDIS_CONN.queue_product(get_svr_queue_name(priority), message=task), "Can't access Redis. Please check the Redis' status."