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 vision LLM PDF parser (#6173)

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

Add vision LLM PDF parser

### 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
2025-03-18 14:52:20 +08:00
committed by GitHub
parent 897fe85b5c
commit 5cf610af40
7 changed files with 413 additions and 102 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
api/db/services/llm_service.py
View File

@ -15,13 +15,12 @@
#
import logging
from api.db.services.user_service import TenantService
from rag.llm import EmbeddingModel, CvModel, ChatModel, RerankModel, Seq2txtModel, TTSModel
from api import settings
from api.db import LLMType
from api.db.db_models import DB
from api.db.db_models import LLMFactories, LLM, TenantLLM
from api.db.db_models import DB, LLM, LLMFactories, TenantLLM
from api.db.services.common_service import CommonService
from api.db.services.user_service import TenantService
from rag.llm import ChatModel, CvModel, EmbeddingModel, RerankModel, Seq2txtModel, TTSModel
class LLMFactoriesService(CommonService):
@ -266,6 +265,14 @@ class LLMBundle:
"LLMBundle.describe can't update token usage for {}/IMAGE2TEXT used_tokens: {}".format(self.tenant_id, used_tokens))
return txt
def describe_with_prompt(self, image, prompt):
txt, used_tokens = self.mdl.describe_with_prompt(image, prompt)
if not TenantLLMService.increase_usage(
self.tenant_id, self.llm_type, used_tokens):
logging.error(
"LLMBundle.describe can't update token usage for {}/IMAGE2TEXT used_tokens: {}".format(self.tenant_id, used_tokens))
return txt
def transcription(self, audio):
txt, used_tokens = self.mdl.transcription(audio)
if not TenantLLMService.increase_usage(