pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2026-01-23 11:36:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: empty chunk issue. (#12638)

Browse Source 
#12570

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Kevin Hu
2026-01-15 17:46:21 +08:00
committed by GitHub
parent 2167e3a3c0
commit cec06bfb5d
2 changed files with 8 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
api/apps/llm_app.py
View File

@ -373,13 +373,14 @@ def my_llms():
@manager.route("/list", methods=["GET"]) # noqa: F821 @manager.route("/list", methods=["GET"]) # noqa: F821
@login_required @login_required
def list_app(): async def list_app():
self_deployed = ["FastEmbed", "Ollama", "Xinference", "LocalAI", "LM-Studio", "GPUStack"] self_deployed = ["FastEmbed", "Ollama", "Xinference", "LocalAI", "LM-Studio", "GPUStack"]
weighted = [] weighted = []
model_type = request.args.get("model_type") model_type = request.args.get("model_type")
tenant_id = current_user.id
try: try:
TenantLLMService.ensure_mineru_from_env(current_user.id) TenantLLMService.ensure_mineru_from_env(tenant_id)
objs = TenantLLMService.query(tenant_id=current_user.id) objs = TenantLLMService.query(tenant_id=tenant_id)
facts = set([o.to_dict()["llm_factory"] for o in objs if o.api_key and o.status == StatusEnum.VALID.value]) facts = set([o.to_dict()["llm_factory"] for o in objs if o.api_key and o.status == StatusEnum.VALID.value])
status = {(o.llm_name + "@" + o.llm_factory) for o in objs if o.status == StatusEnum.VALID.value} status = {(o.llm_name + "@" + o.llm_factory) for o in objs if o.status == StatusEnum.VALID.value}
llms = LLMService.get_all() llms = LLMService.get_all()

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

@ -93,6 +93,8 @@ class Splitter(ProcessBase):
split_sec = re.split(r"(%s)" % custom_pattern, c, flags=re.DOTALL) split_sec = re.split(r"(%s)" % custom_pattern, c, flags=re.DOTALL)
if split_sec: if split_sec:
for j in range(0, len(split_sec), 2): for j in range(0, len(split_sec), 2):
if not split_sec[j].strip():
continue
docs.append({ docs.append({
"text": split_sec[j], "text": split_sec[j],
"mom": c "mom": c
@ -156,6 +158,8 @@ class Splitter(ProcessBase):
if split_sec: if split_sec:
c["mom"] = c["text"] c["mom"] = c["text"]
for j in range(0, len(split_sec), 2): for j in range(0, len(split_sec), 2):
if not split_sec[j].strip():
continue
cc = deepcopy(c) cc = deepcopy(c)
cc["text"] = split_sec[j] cc["text"] = split_sec[j]
docs.append(cc) docs.append(cc)