github/DB-GPT
1
0
Fork 0
mirror of https://github.com/csunny/DB-GPT.git synced 2025-10-11 11:53:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix:knowledge_init path

Browse Source 
1.knowledge_init path
2.url embedding chunk
This commit is contained in:
aries_ckt
2023-07-03 16:09:18 +08:00
parent b831ee5863
commit 6b17a16bd0
2 changed files with 7 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
pilot/embedding_engine/url_embedding.py
View File

@@ -3,7 +3,7 @@ from typing import List
from bs4 import BeautifulSoup
from langchain.document_loaders import WebBaseLoader
from langchain.schema import Document
from langchain.text_splitter import CharacterTextSplitter
from langchain.text_splitter import CharacterTextSplitter, SpacyTextSplitter
from pilot.configs.config import Config
from pilot.configs.model_config import KNOWLEDGE_CHUNK_SPLIT_SIZE
@@ -33,7 +33,11 @@ class URLEmbedding(SourceEmbedding):
length_function=len,
)
else:
text_splitter = CHNDocumentSplitter(pdf=True, sentence_size=1000)
text_splitter = SpacyTextSplitter(
pipeline="zh_core_web_sm",
chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE,
chunk_overlap=100,
)
return loader.load_and_split(text_splitter)
@register