github/DB-GPT
1
0
Fork 0
mirror of https://github.com/csunny/DB-GPT.git synced 2025-08-23 02:27:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix:embedding chunk update

Browse Source 
integrate RecursiveCharacterTextSplitter
This commit is contained in:
aries_ckt 2023-07-03 20:06:38 +08:00
parent 870c704ef4
commit 7ee68c905b
5 changed files with 45 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
pilot/embedding_engine/markdown_embedding.py
View File

@ -6,7 +6,7 @@ from typing import List
import markdown import markdown
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
from langchain.schema import Document from langchain.schema import Document
from langchain.text_splitter import SpacyTextSplitter, CharacterTextSplitter from langchain.text_splitter import SpacyTextSplitter, CharacterTextSplitter, RecursiveCharacterTextSplitter
from pilot.configs.config import Config from pilot.configs.config import Config
from pilot.embedding_engine import SourceEmbedding, register from pilot.embedding_engine import SourceEmbedding, register
@ -37,11 +37,14 @@ class MarkdownEmbedding(SourceEmbedding):
length_function=len, length_function=len,
) )
else: else:
text_splitter = SpacyTextSplitter( try:
pipeline="zh_core_web_sm", text_splitter = SpacyTextSplitter(
chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE, pipeline="zh_core_web_sm",
chunk_overlap=100, chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE,
) chunk_overlap=100,
)
except Exception:
text_splitter = RecursiveCharacterTextSplitter(chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE, chunk_overlap=50)
return loader.load_and_split(text_splitter) return loader.load_and_split(text_splitter)
@register @register

15
pilot/embedding_engine/pdf_embedding.py
View File

@ -4,7 +4,7 @@ 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, CharacterTextSplitter from langchain.text_splitter import SpacyTextSplitter, CharacterTextSplitter, RecursiveCharacterTextSplitter
from pilot.configs.config import Config from pilot.configs.config import Config
from pilot.embedding_engine import SourceEmbedding, register from pilot.embedding_engine import SourceEmbedding, register
@ -40,11 +40,14 @@ class PDFEmbedding(SourceEmbedding):
length_function=len, length_function=len,
) )
else: else:
text_splitter = SpacyTextSplitter( try:
pipeline="zh_core_web_sm", text_splitter = SpacyTextSplitter(
chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE, pipeline="zh_core_web_sm",
chunk_overlap=100, chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE,
) chunk_overlap=100,
)
except Exception:
text_splitter = RecursiveCharacterTextSplitter(chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE, chunk_overlap=50)
return loader.load_and_split(text_splitter) return loader.load_and_split(text_splitter)
@register @register

15
pilot/embedding_engine/ppt_embedding.py
View File

@ -4,7 +4,7 @@ from typing import List
from langchain.document_loaders import UnstructuredPowerPointLoader from langchain.document_loaders import UnstructuredPowerPointLoader
from langchain.schema import Document from langchain.schema import Document
from langchain.text_splitter import SpacyTextSplitter, CharacterTextSplitter from langchain.text_splitter import SpacyTextSplitter, CharacterTextSplitter, RecursiveCharacterTextSplitter
from pilot.configs.config import Config from pilot.configs.config import Config
from pilot.embedding_engine import SourceEmbedding, register from pilot.embedding_engine import SourceEmbedding, register
@ -38,11 +38,14 @@ class PPTEmbedding(SourceEmbedding):
length_function=len, length_function=len,
) )
else: else:
text_splitter = SpacyTextSplitter( try:
pipeline="zh_core_web_sm", text_splitter = SpacyTextSplitter(
chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE, pipeline="zh_core_web_sm",
chunk_overlap=100, chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE,
) chunk_overlap=100,
)
except Exception:
text_splitter = RecursiveCharacterTextSplitter(chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE, chunk_overlap=50)
return loader.load_and_split(text_splitter) return loader.load_and_split(text_splitter)
@register @register

15
pilot/embedding_engine/url_embedding.py
View File

@ -3,7 +3,7 @@ from typing import List
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
from langchain.document_loaders import WebBaseLoader from langchain.document_loaders import WebBaseLoader
from langchain.schema import Document from langchain.schema import Document
from langchain.text_splitter import CharacterTextSplitter, SpacyTextSplitter from langchain.text_splitter import CharacterTextSplitter, SpacyTextSplitter, RecursiveCharacterTextSplitter
from pilot.configs.config import Config from pilot.configs.config import Config
from pilot.configs.model_config import KNOWLEDGE_CHUNK_SPLIT_SIZE from pilot.configs.model_config import KNOWLEDGE_CHUNK_SPLIT_SIZE
@ -33,11 +33,14 @@ class URLEmbedding(SourceEmbedding):
length_function=len, length_function=len,
) )
else: else:
text_splitter = SpacyTextSplitter( try:
pipeline="zh_core_web_sm", text_splitter = SpacyTextSplitter(
chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE, pipeline="zh_core_web_sm",
chunk_overlap=100, chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE,
) chunk_overlap=100,
)
except Exception:
text_splitter = RecursiveCharacterTextSplitter(chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE, chunk_overlap=50)
return loader.load_and_split(text_splitter) return loader.load_and_split(text_splitter)
@register @register

15
pilot/embedding_engine/word_embedding.py
View File

@ -4,7 +4,7 @@ from typing import List
from langchain.document_loaders import UnstructuredWordDocumentLoader from langchain.document_loaders import UnstructuredWordDocumentLoader
from langchain.schema import Document from langchain.schema import Document
from langchain.text_splitter import CharacterTextSplitter, SpacyTextSplitter from langchain.text_splitter import CharacterTextSplitter, SpacyTextSplitter, RecursiveCharacterTextSplitter
from pilot.configs.config import Config from pilot.configs.config import Config
from pilot.embedding_engine import SourceEmbedding, register from pilot.embedding_engine import SourceEmbedding, register
@ -32,11 +32,14 @@ class WordEmbedding(SourceEmbedding):
length_function=len, length_function=len,
) )
else: else:
text_splitter = SpacyTextSplitter( try:
pipeline="zh_core_web_sm", text_splitter = SpacyTextSplitter(
chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE, pipeline="zh_core_web_sm",
chunk_overlap=100, chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE,
) chunk_overlap=100,
)
except Exception:
text_splitter = RecursiveCharacterTextSplitter(chunk_size=CFG.KNOWLEDGE_CHUNK_SIZE, chunk_overlap=50)
return loader.load_and_split(text_splitter) return loader.load_and_split(text_splitter)
@register @register