Load local text files of any kind - code, txts, json etc (#1076)
This commit is contained in:
@@ -7,7 +7,7 @@ from embedchain.config import AddConfig
|
||||
from embedchain.data_formatter.data_formatter import DataFormatter
|
||||
from embedchain.helpers.json_serializable import register_deserializable
|
||||
from embedchain.loaders.base_loader import BaseLoader
|
||||
from embedchain.loaders.local_text import LocalTextLoader
|
||||
from embedchain.loaders.text_file import TextFileLoader
|
||||
from embedchain.utils import detect_datatype
|
||||
|
||||
|
||||
@@ -58,4 +58,4 @@ class DirectoryLoader(BaseLoader):
|
||||
)
|
||||
except Exception as e:
|
||||
self.errors.append(f"Error processing {file_path}: {e}")
|
||||
return LocalTextLoader()
|
||||
return TextFileLoader()
|
||||
|
||||
30
embedchain/loaders/text_file.py
Normal file
30
embedchain/loaders/text_file.py
Normal file
@@ -0,0 +1,30 @@
|
||||
import hashlib
|
||||
import os
|
||||
|
||||
from embedchain.helpers.json_serializable import register_deserializable
|
||||
from embedchain.loaders.base_loader import BaseLoader
|
||||
|
||||
|
||||
@register_deserializable
|
||||
class TextFileLoader(BaseLoader):
|
||||
def load_data(self, url: str):
|
||||
"""Load data from a text file located at a local path."""
|
||||
if not os.path.exists(url):
|
||||
raise FileNotFoundError(f"The file at {url} does not exist.")
|
||||
|
||||
with open(url, "r", encoding="utf-8") as file:
|
||||
content = file.read()
|
||||
|
||||
doc_id = hashlib.sha256((content + url).encode()).hexdigest()
|
||||
|
||||
meta_data = {"url": url, "file_size": os.path.getsize(url), "file_type": url.split(".")[-1]}
|
||||
|
||||
return {
|
||||
"doc_id": doc_id,
|
||||
"data": [
|
||||
{
|
||||
"content": content,
|
||||
"meta_data": meta_data,
|
||||
}
|
||||
],
|
||||
}
|
||||
Reference in New Issue
Block a user