mirror of
https://github.com/csunny/DB-GPT.git
synced 2025-10-04 08:35:40 +00:00
929e7fe96b
1.delete CFG in embedding_engine api 2.add a text_splitter param in embedding_engine api 3.fmt
37 lines
1.1 KiB
Python
37 lines
1.1 KiB
Python
from typing import List, Optional
|
|
|
|
from langchain.schema import Document
|
|
from langchain.text_splitter import TextSplitter
|
|
|
|
from pilot.embedding_engine import SourceEmbedding, register
|
|
|
|
|
|
class StringEmbedding(SourceEmbedding):
|
|
"""string embedding for read string document."""
|
|
|
|
def __init__(
|
|
self,
|
|
file_path,
|
|
vector_store_config,
|
|
text_splitter: Optional[TextSplitter] = None,
|
|
):
|
|
"""Initialize raw text word path."""
|
|
super().__init__(file_path=file_path, vector_store_config=vector_store_config)
|
|
self.file_path = file_path
|
|
self.vector_store_config = vector_store_config
|
|
self.text_splitter = text_splitter or None
|
|
|
|
@register
|
|
def read(self):
|
|
"""Load from String path."""
|
|
metadata = {"source": "db_summary"}
|
|
return [Document(page_content=self.file_path, metadata=metadata)]
|
|
|
|
@register
|
|
def data_process(self, documents: List[Document]):
|
|
i = 0
|
|
for d in documents:
|
|
documents[i].page_content = d.page_content.replace("\n", "")
|
|
i += 1
|
|
return documents
|