This commit is contained in:
Timothy Jaeryang Baek
2026-03-17 17:58:01 -05:00
parent fcf7208352
commit de3317e26b
220 changed files with 17200 additions and 22836 deletions

View File

@@ -29,18 +29,18 @@ class ExternalDocumentLoader(BaseLoader):
self.user = user
def load(self) -> List[Document]:
with open(self.file_path, "rb") as f:
with open(self.file_path, 'rb') as f:
data = f.read()
headers = {}
if self.mime_type is not None:
headers["Content-Type"] = self.mime_type
headers['Content-Type'] = self.mime_type
if self.api_key is not None:
headers["Authorization"] = f"Bearer {self.api_key}"
headers['Authorization'] = f'Bearer {self.api_key}'
try:
headers["X-Filename"] = quote(os.path.basename(self.file_path))
headers['X-Filename'] = quote(os.path.basename(self.file_path))
except Exception:
pass
@@ -48,24 +48,23 @@ class ExternalDocumentLoader(BaseLoader):
headers = include_user_info_headers(headers, self.user)
url = self.url
if url.endswith("/"):
if url.endswith('/'):
url = url[:-1]
try:
response = requests.put(f"{url}/process", data=data, headers=headers)
response = requests.put(f'{url}/process', data=data, headers=headers)
except Exception as e:
log.error(f"Error connecting to endpoint: {e}")
raise Exception(f"Error connecting to endpoint: {e}")
log.error(f'Error connecting to endpoint: {e}')
raise Exception(f'Error connecting to endpoint: {e}')
if response.ok:
response_data = response.json()
if response_data:
if isinstance(response_data, dict):
return [
Document(
page_content=response_data.get("page_content"),
metadata=response_data.get("metadata"),
page_content=response_data.get('page_content'),
metadata=response_data.get('metadata'),
)
]
elif isinstance(response_data, list):
@@ -73,17 +72,15 @@ class ExternalDocumentLoader(BaseLoader):
for document in response_data:
documents.append(
Document(
page_content=document.get("page_content"),
metadata=document.get("metadata"),
page_content=document.get('page_content'),
metadata=document.get('metadata'),
)
)
return documents
else:
raise Exception("Error loading document: Unable to parse content")
raise Exception('Error loading document: Unable to parse content')
else:
raise Exception("Error loading document: No content returned")
raise Exception('Error loading document: No content returned')
else:
raise Exception(
f"Error loading document: {response.status_code} {response.text}"
)
raise Exception(f'Error loading document: {response.status_code} {response.text}')