github/DB-GPT
1
0
Fork 0
mirror of https://github.com/csunny/DB-GPT.git synced 2025-08-19 08:47:32 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'dev' of https://github.com/csunny/DB-GPT into llm_fxp

Browse Source
This commit is contained in:
csunny 2023-06-08 20:07:44 +08:00
commit eae38931fa
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
pilot/source_embedding/pdf_embedding.py
View File

@ -4,10 +4,10 @@ from typing import List
from langchain.document_loaders import PyPDFLoader from langchain.document_loaders import PyPDFLoader
from langchain.schema import Document from langchain.schema import Document
from langchain.text_splitter import SpacyTextSplitter
from pilot.configs.config import Config from pilot.configs.config import Config
from pilot.source_embedding import SourceEmbedding, register from pilot.source_embedding import SourceEmbedding, register
from pilot.source_embedding.chn_document_splitter import CHNDocumentSplitter
CFG = Config() CFG = Config()
@ -24,11 +24,11 @@ class PDFEmbedding(SourceEmbedding):
@register @register
def read(self): def read(self):
"""Load from pdf path.""" """Load from pdf path."""
# loader = UnstructuredPaddlePDFLoader(self.file_path)
loader = PyPDFLoader(self.file_path) loader = PyPDFLoader(self.file_path)
textsplitter = CHNDocumentSplitter( # textsplitter = CHNDocumentSplitter(
pdf=True, sentence_size=CFG.KNOWLEDGE_CHUNK_SIZE # pdf=True, sentence_size=CFG.KNOWLEDGE_CHUNK_SIZE
) # )
textsplitter = SpacyTextSplitter(pipeline='zh_core_web_sm', chunk_size=1000, chunk_overlap=200)
return loader.load_and_split(textsplitter) return loader.load_and_split(textsplitter)
@register @register