Refactor file loader component

This commit is contained in:
Gabriel Luiz Freitas Almeida 2023-11-23 11:48:06 -03:00
commit ccfd8e8acd

View file

@ -1,119 +1,7 @@
from langflow import CustomComponent
from langchain.schema import Document
from typing import Any, Dict, List
loaders_info: List[Dict[str, Any]] = [
{
"loader": "AirbyteJSONLoader",
"name": "Airbyte JSON (.jsonl)",
"import": "langchain.document_loaders.AirbyteJSONLoader",
"defaultFor": ["jsonl"],
"allowdTypes": ["jsonl"],
},
{
"loader": "JSONLoader",
"name": "JSON (.json)",
"import": "langchain.document_loaders.JSONLoader",
"defaultFor": ["json"],
"allowdTypes": ["json"],
},
{
"loader": "BSHTMLLoader",
"name": "BeautifulSoup4 HTML (.html, .htm)",
"import": "langchain.document_loaders.BSHTMLLoader",
"allowdTypes": ["html", "htm"],
},
{
"loader": "CSVLoader",
"name": "CSV (.csv)",
"import": "langchain.document_loaders.CSVLoader",
"defaultFor": ["csv"],
"allowdTypes": ["csv"],
},
{
"loader": "CoNLLULoader",
"name": "CoNLL-U (.conllu)",
"import": "langchain.document_loaders.CoNLLULoader",
"defaultFor": ["conllu"],
"allowdTypes": ["conllu"],
},
{
"loader": "EverNoteLoader",
"name": "EverNote (.enex)",
"import": "langchain.document_loaders.EverNoteLoader",
"defaultFor": ["enex"],
"allowdTypes": ["enex"],
},
{
"loader": "FacebookChatLoader",
"name": "Facebook Chat (.json)",
"import": "langchain.document_loaders.FacebookChatLoader",
"allowdTypes": ["json"],
},
{
"loader": "OutlookMessageLoader",
"name": "Outlook Message (.msg)",
"import": "langchain.document_loaders.OutlookMessageLoader",
"defaultFor": ["msg"],
"allowdTypes": ["msg"],
},
{
"loader": "PyPDFLoader",
"name": "PyPDF (.pdf)",
"import": "langchain.document_loaders.PyPDFLoader",
"defaultFor": ["pdf"],
"allowdTypes": ["pdf"],
},
{
"loader": "STRLoader",
"name": "Subtitle (.str)",
"import": "langchain.document_loaders.STRLoader",
"defaultFor": ["str"],
"allowdTypes": ["str"],
},
{
"loader": "TextLoader",
"name": "Text (.txt)",
"import": "langchain.document_loaders.TextLoader",
"defaultFor": ["txt"],
"allowdTypes": ["txt"],
},
{
"loader": "UnstructuredEmailLoader",
"name": "Unstructured Email (.eml)",
"import": "langchain.document_loaders.UnstructuredEmailLoader",
"defaultFor": ["eml"],
"allowdTypes": ["eml"],
},
{
"loader": "UnstructuredHTMLLoader",
"name": "Unstructured HTML (.html, .htm)",
"import": "langchain.document_loaders.UnstructuredHTMLLoader",
"defaultFor": ["html", "htm"],
"allowdTypes": ["html", "htm"],
},
{
"loader": "UnstructuredMarkdownLoader",
"name": "Unstructured Markdown (.md)",
"import": "langchain.document_loaders.UnstructuredMarkdownLoader",
"defaultFor": ["md"],
"allowdTypes": ["md"],
},
{
"loader": "UnstructuredPowerPointLoader",
"name": "Unstructured PowerPoint (.pptx)",
"import": "langchain.document_loaders.UnstructuredPowerPointLoader",
"defaultFor": ["pptx"],
"allowdTypes": ["pptx"],
},
{
"loader": "UnstructuredWordLoader",
"name": "Unstructured Word (.docx)",
"import": "langchain.document_loaders.UnstructuredWordLoader",
"defaultFor": ["docx"],
"allowdTypes": ["docx"],
},
]
from langflow import CustomComponent
from langflow.utils.constants import LOADERS_INFO
class FileLoaderComponent(CustomComponent):
@ -122,12 +10,12 @@ class FileLoaderComponent(CustomComponent):
beta = True
def build_config(self):
loader_options = ["Automatic"] + [loader_info["name"] for loader_info in loaders_info]
loader_options = ["Automatic"] + [loader_info["name"] for loader_info in LOADERS_INFO]
file_types = []
suffixes = []
for loader_info in loaders_info:
for loader_info in LOADERS_INFO:
if "allowedTypes" in loader_info:
file_types.extend(loader_info["allowedTypes"])
suffixes.extend([f".{ext}" for ext in loader_info["allowedTypes"]])
@ -189,7 +77,7 @@ class FileLoaderComponent(CustomComponent):
# Mapeie o nome do loader selecionado para suas informações
selected_loader_info = None
for loader_info in loaders_info:
for loader_info in LOADERS_INFO:
if loader_info["name"] == loader:
selected_loader_info = loader_info
break
@ -200,7 +88,7 @@ class FileLoaderComponent(CustomComponent):
if loader == "Automatic":
# Determine o loader automaticamente com base na extensão do arquivo
default_loader_info = None
for info in loaders_info:
for info in LOADERS_INFO:
if "defaultFor" in info and file_type in info["defaultFor"]:
default_loader_info = info
break