Spaces:
Paused
Paused
File size: 1,752 Bytes
ab2ded1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 |
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import io
import numpy as np
from PIL import Image
from api.db import LLMType
from api.db.services.llm_service import LLMBundle
from rag.nlp import tokenize
from deepdoc.vision import OCR
ocr = OCR()
def chunk(filename, binary, tenant_id, lang, callback=None, **kwargs):
img = Image.open(io.BytesIO(binary)).convert('RGB')
doc = {
"docnm_kwd": filename,
"image": img
}
bxs = ocr(np.array(img))
txt = "\n".join([t[0] for _, t in bxs if t[0]])
eng = lang.lower() == "english"
callback(0.4, "Finish OCR: (%s ...)" % txt[:12])
if (eng and len(txt.split(" ")) > 32) or len(txt) > 32:
tokenize(doc, txt, eng)
callback(0.8, "OCR results is too long to use CV LLM.")
return [doc]
try:
callback(0.4, "Use CV LLM to describe the picture.")
cv_mdl = LLMBundle(tenant_id, LLMType.IMAGE2TEXT, lang=lang)
ans = cv_mdl.describe(binary)
callback(0.8, "CV LLM respond: %s ..." % ans[:32])
txt += "\n" + ans
tokenize(doc, txt, eng)
return [doc]
except Exception as e:
callback(prog=-1, msg=str(e))
return []
|