Spaces:
Sleeping
Sleeping
Add application file
Browse files- Dockerfile +17 -0
- app.py +13 -0
- requirements.txt +9 -0
Dockerfile
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
|
2 |
+
# you will also find guides on how best to write your Dockerfile
|
3 |
+
|
4 |
+
FROM python:3.11
|
5 |
+
|
6 |
+
RUN useradd -m -u 1000 user
|
7 |
+
USER user
|
8 |
+
ENV PATH="/home/user/.local/bin:$PATH"
|
9 |
+
|
10 |
+
WORKDIR /app
|
11 |
+
|
12 |
+
COPY --chown=user ./requirements.txt requirements.txt
|
13 |
+
RUN pip install --no-cache-dir --upgrade -r requirements.txt
|
14 |
+
RUN apt update && apt install -y poppler-utils tesseract-ocr
|
15 |
+
|
16 |
+
COPY --chown=user . /app
|
17 |
+
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
|
app.py
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from fastapi import FastAPI, Query, HTTPException
|
2 |
+
from extractous import Extractor, TesseractOcrConfig
|
3 |
+
|
4 |
+
app = FastAPI()
|
5 |
+
|
6 |
+
@app.get("/")
|
7 |
+
def accepts_pdf_link(link: str = Query(..., description="The URL to pdf file")):
|
8 |
+
if not link.startswith(("http://", "https://")):
|
9 |
+
raise HTTPException(status_code=400, detail="Invalid URL format")
|
10 |
+
extractor = Extractor().set_ocr_config(TesseractOcrConfig())
|
11 |
+
extractor = extractor.set_xml_output(False)
|
12 |
+
content, metadata = extractor.extract_url_to_string(link)
|
13 |
+
return {"received_link": link, "content": content}
|
requirements.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
fastapi
|
2 |
+
uvicorn[standard]
|
3 |
+
google-genai
|
4 |
+
vecs
|
5 |
+
extractous
|
6 |
+
beautifulsoup4
|
7 |
+
markdownify
|
8 |
+
pdf2image
|
9 |
+
firebase-admin
|