setup

Dockerfile

@@ -0,0 +1,16 @@
+# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./packges.txt packges.txt
+RUN pip install --no-cache-dir --upgrade -r packges.txt
+
+COPY --chown=user . /app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,38 @@
+from fastapi import FastAPI
+from fastapi.responses import JSONResponse
+from fastapi.middleware.cors import CORSMiddleware
+from textclassifier import TextClassifier
+from dto import ClassifyRequest
+
+from transformers import pipeline
+
+hub_model_id = "NathyB/Hate-Speech-Detection-in-Amharic-Language-mBERT"
+text_classifier = pipeline("text-classification", model=hub_model_id)
+
+
+app = FastAPI()
+
+# Setup cors
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+
+@app.post("/textclassify")
+def classifyText(request_body:ClassifyRequest):
+    text = request_body.text
+    summary = TextClassifier(text_classifier).classify(text)
+    return JSONResponse(content=summary, status_code=201)
+
+
+
+
+# Get route
+@app.get("/")
+def home():
+    return {"hello":"world"}

dto.py

@@ -0,0 +1,11 @@
+from datetime import datetime
+from typing import List
+from typing import Optional
+
+from pydantic import BaseModel
+from pydantic import Field
+
+
+class ClassifyRequest(BaseModel):
+    """Text Summarize request model."""
+    text: str = Field(..., description="The text you want to summarize", examples=["ወጣቱ አክሎም ትግራይ ክልል ከጦርነቱ ማግሥት አንፃራዊ  ..."])

packges.txt

@@ -0,0 +1,10 @@
+nltk
+numpy
+fastapi
+pandas
+scikit-learn
+transformers
+torch
+torchvision
+torchaudio
+uvicorn[standard]

textclassifier.py

@@ -0,0 +1,13 @@
+class TextClassifier:
+
+    def __init__(self, model) -> None:
+        self.text_classifier = model
+
+    def classify(self,text):
+
+        data = self.text_classifier(text)[0]
+        print("response from hugging \n", data)
+
+        return data
+    
+