youngkingdom/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-01-19 11:45:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: add paddleocr parser (#12513)

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

Add PaddleOCR as a new PDF parser.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Lin Manhui
2026-01-09 17:48:45 +08:00
committed by GitHub
parent 6abf55c048
commit 2e09db02f3
34 changed files with 1510 additions and 453 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
api/apps/llm_app.py
View File

@ -195,6 +195,9 @@ async def add_llm():
elif factory == "MinerU":
api_key = apikey_json(["api_key", "provider_order"])
elif factory == "PaddleOCR":
api_key = apikey_json(["api_key", "provider_order"])
llm = {
"tenant_id": current_user.id,
"llm_factory": factory,
@ -230,8 +233,7 @@ async def add_llm():
**extra,
)
try:
m, tc = await mdl.async_chat(None, [{"role": "user", "content": "Hello! How are you doing!"}],
{"temperature": 0.9})
m, tc = await mdl.async_chat(None, [{"role": "user", "content": "Hello! How are you doing!"}], {"temperature": 0.9})
if not tc and m.find("**ERROR**:") >= 0:
raise Exception(m)
except Exception as e:
@ -381,7 +383,7 @@ def list_app():
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}
llms = LLMService.get_all()
llms = [m.to_dict() for m in llms if m.status == StatusEnum.VALID.value and m.fid not in weighted and (m.fid == 'Builtin' or (m.llm_name + "@" + m.fid) in status)]
llms = [m.to_dict() for m in llms if m.status == StatusEnum.VALID.value and m.fid not in weighted and (m.fid == "Builtin" or (m.llm_name + "@" + m.fid) in status)]
for m in llms:
m["available"] = m["fid"] in facts or m["llm_name"].lower() == "flag-embedding" or m["fid"] in self_deployed
if "tei-" in os.getenv("COMPOSE_PROFILES", "") and m["model_type"] == LLMType.EMBEDDING and m["fid"] == "Builtin" and m["llm_name"] == os.getenv("TEI_MODEL", ""):