Added documentation (#219)
This commit is contained in:
@@ -2,6 +2,7 @@ from langchain.document_loaders import Docx2txtLoader
|
||||
|
||||
class DocxFileLoader:
|
||||
def load_data(self, url):
|
||||
''' Load data from a .docx file. '''
|
||||
loader = Docx2txtLoader(url)
|
||||
output = []
|
||||
data = loader.load()
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
class LocalQnaPairLoader:
|
||||
|
||||
def load_data(self, content):
|
||||
''' Load data from a local QnA pair. '''
|
||||
question, answer = content
|
||||
content = f"Q: {question}\nA: {answer}"
|
||||
meta_data = {
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
class LocalTextLoader:
|
||||
|
||||
def load_data(self, content):
|
||||
''' Load data from a local text file. '''
|
||||
meta_data = {
|
||||
"url": "local",
|
||||
}
|
||||
|
||||
@@ -6,6 +6,7 @@ from embedchain.utils import clean_string
|
||||
class PdfFileLoader:
|
||||
|
||||
def load_data(self, url):
|
||||
''' Load data from a PDF file. '''
|
||||
loader = PyPDFLoader(url)
|
||||
output = []
|
||||
pages = loader.load_and_split()
|
||||
|
||||
@@ -8,6 +8,7 @@ from embedchain.utils import clean_string
|
||||
class WebPageLoader:
|
||||
|
||||
def load_data(self, url):
|
||||
''' Load data from a web page. '''
|
||||
response = requests.get(url)
|
||||
data = response.content
|
||||
soup = BeautifulSoup(data, 'html.parser')
|
||||
|
||||
@@ -6,6 +6,7 @@ from embedchain.utils import clean_string
|
||||
class YoutubeVideoLoader:
|
||||
|
||||
def load_data(self, url):
|
||||
''' Load data from a Youtube video. '''
|
||||
loader = YoutubeLoader.from_youtube_url(url, add_video_info=True)
|
||||
doc = loader.load()
|
||||
output = []
|
||||
|
||||
Reference in New Issue
Block a user