update loaders
This commit is contained in:
parent
68e593a64a
commit
5acea5e4fc
3
api.py
3
api.py
|
|
@ -16,9 +16,8 @@ from starlette.responses import RedirectResponse
|
||||||
|
|
||||||
from chains.local_doc_qa import LocalDocQA
|
from chains.local_doc_qa import LocalDocQA
|
||||||
from configs.model_config import (VS_ROOT_PATH, UPLOAD_ROOT_PATH, EMBEDDING_DEVICE,
|
from configs.model_config import (VS_ROOT_PATH, UPLOAD_ROOT_PATH, EMBEDDING_DEVICE,
|
||||||
EMBEDDING_MODEL, LLM_MODEL, NLTK_DATA_PATH,
|
EMBEDDING_MODEL, NLTK_DATA_PATH,
|
||||||
VECTOR_SEARCH_TOP_K, LLM_HISTORY_LEN, OPEN_CROSS_DOMAIN)
|
VECTOR_SEARCH_TOP_K, LLM_HISTORY_LEN, OPEN_CROSS_DOMAIN)
|
||||||
from agent import bing_search
|
|
||||||
import models.shared as shared
|
import models.shared as shared
|
||||||
from models.loader.args import parser
|
from models.loader.args import parser
|
||||||
from models.loader import LoaderCheckPoint
|
from models.loader import LoaderCheckPoint
|
||||||
|
|
|
||||||
|
|
@ -4,7 +4,10 @@ from typing import List
|
||||||
from langchain.document_loaders.unstructured import UnstructuredFileLoader
|
from langchain.document_loaders.unstructured import UnstructuredFileLoader
|
||||||
from paddleocr import PaddleOCR
|
from paddleocr import PaddleOCR
|
||||||
import os
|
import os
|
||||||
|
import nltk
|
||||||
|
from configs.model_config import NLTK_DATA_PATH
|
||||||
|
|
||||||
|
nltk.data.path = [NLTK_DATA_PATH] + nltk.data.path
|
||||||
|
|
||||||
class UnstructuredPaddleImageLoader(UnstructuredFileLoader):
|
class UnstructuredPaddleImageLoader(UnstructuredFileLoader):
|
||||||
"""Loader that uses unstructured to load image files, such as PNGs and JPGs."""
|
"""Loader that uses unstructured to load image files, such as PNGs and JPGs."""
|
||||||
|
|
|
||||||
|
|
@ -5,7 +5,10 @@ from langchain.document_loaders.unstructured import UnstructuredFileLoader
|
||||||
from paddleocr import PaddleOCR
|
from paddleocr import PaddleOCR
|
||||||
import os
|
import os
|
||||||
import fitz
|
import fitz
|
||||||
|
import nltk
|
||||||
|
from configs.model_config import NLTK_DATA_PATH
|
||||||
|
|
||||||
|
nltk.data.path = [NLTK_DATA_PATH] + nltk.data.path
|
||||||
|
|
||||||
class UnstructuredPaddlePDFLoader(UnstructuredFileLoader):
|
class UnstructuredPaddlePDFLoader(UnstructuredFileLoader):
|
||||||
"""Loader that uses unstructured to load image files, such as PNGs and JPGs."""
|
"""Loader that uses unstructured to load image files, such as PNGs and JPGs."""
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue