Update app.py
Browse files
app.py
CHANGED
|
@@ -2,6 +2,7 @@ import os
|
|
| 2 |
import requests
|
| 3 |
from fastapi import FastAPI, HTTPException
|
| 4 |
from langchain_community.document_loaders import YoutubeLoader, UnstructuredPDFLoader, WebBaseLoader
|
|
|
|
| 5 |
|
| 6 |
app = FastAPI()
|
| 7 |
|
|
@@ -19,14 +20,15 @@ def extract_text(url: str, language: str = "ja", length: int = 150000):
|
|
| 19 |
text_content = str(docs)
|
| 20 |
elif url.endswith(".pdf"):
|
| 21 |
# PDFの場合
|
| 22 |
-
response = requests.get(url)
|
| 23 |
-
pdf_file_path = os.path.join("/app/downloads", os.path.basename(url))
|
| 24 |
-
with open(pdf_file_path, "wb") as pdf_file:
|
| 25 |
-
pdf_file.write(response.content)
|
| 26 |
# loader = UnstructuredPDFLoader(pdf_file_path)
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
text_content =
|
|
|
|
| 30 |
else:
|
| 31 |
# それ以外の場合
|
| 32 |
loader = WebBaseLoader(url)
|
|
|
|
| 2 |
import requests
|
| 3 |
from fastapi import FastAPI, HTTPException
|
| 4 |
from langchain_community.document_loaders import YoutubeLoader, UnstructuredPDFLoader, WebBaseLoader
|
| 5 |
+
from langchain_community.document_loaders import OnlinePDFLoader
|
| 6 |
|
| 7 |
app = FastAPI()
|
| 8 |
|
|
|
|
| 20 |
text_content = str(docs)
|
| 21 |
elif url.endswith(".pdf"):
|
| 22 |
# PDFの場合
|
| 23 |
+
# response = requests.get(url)
|
| 24 |
+
# pdf_file_path = os.path.join("/app/downloads", os.path.basename(url))
|
| 25 |
+
# with open(pdf_file_path, "wb") as pdf_file:
|
| 26 |
+
# pdf_file.write(response.content)
|
| 27 |
# loader = UnstructuredPDFLoader(pdf_file_path)
|
| 28 |
+
loader = OnlinePDFLoader(url)
|
| 29 |
+
docs = loader.load()
|
| 30 |
+
text_content = docs[0].page_content
|
| 31 |
+
# text_content = pdf_file_path
|
| 32 |
else:
|
| 33 |
# それ以外の場合
|
| 34 |
loader = WebBaseLoader(url)
|