main

Dockerfile

@@ -0,0 +1,27 @@
+FROM python:3.10.9
+
+# Create user with home directory
+RUN useradd -m -u 1000 user
+
+# Switch to the created user
+USER user
+
+# Set environment variables
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH \
+    TRANSFORMERS_CACHE=/home/user/.cache
+
+# Create necessary directories with the right permissions
+RUN mkdir -p $HOME/.cache && chmod -R 777 $HOME/.cache
+
+# Set the working directory
+WORKDIR $HOME/Redaction
+
+# Copy project files to the working directory
+COPY --chown=user . $HOME/Redaction
+
+# Install dependencies
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+# Set the command to run the application
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,11 +1,11 @@
----
-title: Model
-emoji: 📚
-colorFrom: yellow
-colorTo: green
-sdk: docker
-pinned: false
-license: other
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Redaction
+emoji: 🔥
+colorFrom: indigo
+colorTo: gray
+sdk: docker
+pinned: false
+license: mit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

main.py

@@ -0,0 +1,39 @@
+import os
+os.environ["TRANSFORMERS_CACHE"] = "/.cache"
+
+import re
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+model_dir = 'edithram23/Redaction'
+tokenizer = AutoTokenizer.from_pretrained(model_dir)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_dir)
+
+def mask_generation(text):
+    import re
+    inputs = ["Mask Generation: " + text]
+    inputs = tokenizer(inputs, max_length=500, truncation=True, return_tensors="pt")
+    output = model.generate(**inputs, num_beams=8, do_sample=True, max_length=len(text)+10)
+    decoded_output = tokenizer.batch_decode(output, skip_special_tokens=True)[0]
+    predicted_title = decoded_output.strip()
+    pattern = r'\[.*?\]'
+    # Replace all occurrences of the pattern with [redacted]
+    redacted_text = re.sub(pattern, '[redacted]', predicted_title)
+    return redacted_text
+
+from fastapi import FastAPI
+import uvicorn
+
+app = FastAPI()
+
+@app.get("/")
+async def hello():
+    return {"msg" : "Live"}
+
+@app.post("/mask")
+async def mask_input(query):
+    output = mask_generation(query)
+    return {"data" : output}
+
+if __name__ == '__main__':
+    os.environ["TRANSFORMERS_CACHE"] = "/.cache"
+    uvicorn.run("main:app", host="0.0.0.0", port=7860, reload=True, workers=1)

requirements.txt

@@ -0,0 +1,4 @@
+fastapi==0.111.0
+transformers==4.41.2
+uvicorn==0.30.1
+torch