Add initial implementation of text classification API with Docker support

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 +1,56 @@
+from fastapi import FastAPI
+from fastapi.responses import JSONResponse
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+import tensorflow as tf
+import joblib
+import numpy as np
+from huggingface_hub import hf_hub_download
+import tensorflow as tf
+import joblib
+
+# Load the model and tokenizer from Hugging Face Hub
+model_path = hf_hub_download(repo_id="rio3210/amharic-hate-speech-using-rnn-bidirectional", filename="amharic_hate_speech_rnn_model.keras")
+tokenizer_path = hf_hub_download(repo_id="rio3210/amharic-hate-speech-using-rnn-bidirectional", filename="tokenizer.joblib")
+
+# Define the FastAPI application
+app = FastAPI()
+
+# Setup CORS
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Define the request body schema
+class ClassifyRequest(BaseModel):
+    text: str
+
+# Preprocessing function
+def preprocess_text(text: str, tokenizer, max_length: int = 100):
+    sequences = tokenizer.texts_to_sequences([text])  # Tokenize the input text
+    padded_sequences = tf.keras.preprocessing.sequence.pad_sequences(
+        sequences, maxlen=max_length, padding="post", truncating="post"
+    )
+    return padded_sequences
+
+# Classification route
+@app.post("/textclassify")
+def classify_text(request_body: ClassifyRequest):
+    text = request_body.text
+    processed_text = preprocess_text(text, tokenizer)  # Preprocess the input text
+    prediction = keras_model.predict(processed_text)  # Predict using the Keras model
+    label = "Hate" if prediction[0] > 0.5 else "Free"  # Threshold-based classification
+    confidence = float(prediction[0])  # Get confidence score
+
+    # Return the result
+    response = {"label": label, "confidence": confidence}
+    return JSONResponse(content=response, status_code=201)
+
+# Root 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 +1,9 @@
+nltk
+numpy
+pandas
+fastapi
+uvicorn[standard]
+scikit-learn
+tensorflow
+huggingface_hub
+joblib

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
+    
+