Duplicate from dog/fastapi-document-qa

Co-authored-by: Dr. President Admiral Roar Dreezy <dog@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,31 @@
+# Use the official Python 3.9 image
+FROM python:3.9
+
+RUN apt-get update && apt-get install -y \
+  tesseract-ocr-all \
+  && rm -rf /var/lib/apt/lists/*
+
+# Set the working directory to /code
+WORKDIR /code
+
+# Copy the current directory contents into the container at /code
+COPY ./requirements.txt /code/requirements.txt
+
+# Install requirements.txt 
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+# Set up a new user named "user" with user ID 1000
+RUN useradd -m -u 1000 user
+# Switch to the "user" user
+USER user
+# Set home to the user's home directory
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+# Set the working directory to the user's home directory
+WORKDIR $HOME/app
+
+# Copy the current directory contents into the container at $HOME/app setting the owner to the user
+COPY --chown=user . $HOME/app
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -0,0 +1,11 @@
+---
+title: Fastapi Document Qa
+emoji: 🐠
+colorFrom: gray
+colorTo: yellow
+sdk: docker
+pinned: false
+duplicated_from: dog/fastapi-document-qa
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

main.py

@@ -0,0 +1,34 @@
+from base64 import b64decode, b64encode
+from io import BytesIO
+
+from fastapi import FastAPI, File, Form
+from PIL import Image
+from transformers import pipeline
+
+
+description = """
+## DocQA with 🤗 transformers, FastAPI, and Docker
+
+This app shows how to do Document Question Answering using
+FastAPI in a Docker Space 🚀
+Check out the docs for the `/predict` endpoint below to try it out!
+"""
+
+# NOTE - we configure docs_url to serve the interactive Docs at the root path
+# of the app. This way, we can use the docs as a landing page for the app on Spaces.
+app = FastAPI(docs_url="/", description=description)
+
+pipe = pipeline("document-question-answering", model="impira/layoutlm-document-qa")
+
+
+@app.post("/predict")
+def predict(image_file: bytes = File(...), question: str = Form(...)):
+    """
+    Using the document-question-answering pipeline from `transformers`, take
+    a given input document (image) and a question about it, and return the
+    predicted answer. The model used is available on the hub at:
+    [`impira/layoutlm-document-qa`](https://huggingface.co/impira/layoutlm-document-qa).
+    """
+    image = Image.open(BytesIO(image_file))
+    output = pipe(image, question)
+    return output

requirements.txt

@@ -0,0 +1,8 @@
+fastapi==0.74.*
+requests==2.27.*
+uvicorn[standard]==0.17.*
+sentencepiece==0.1.*
+torch==1.11.*
+transformers[vision]==4.*
+pytesseract==0.3.10
+python-multipart==0.0.6