Upload 6 files

Dockerfile

@@ -0,0 +1,21 @@
+# Base image
+FROM python:3.9
+
+# Set working directory
+WORKDIR /app
+
+# Copy the application files
+COPY app.py .
+COPY TextSimilarity.py .
+COPY requirements.txt .
+COPY utils.py .
+
+# Install dependencies
+RUN pip3 install -r requirements.txt
+RUN python3 download_model.py
+
+# Expose the port
+EXPOSE 8000
+
+# Run the application
+CMD ["python3", "app.py"]

TextSimilarity.ipynb

@@ -0,0 +1,141 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Some weights of the model checkpoint at xlm-roberta-large were not used when initializing XLMRobertaModel: ['lm_head.layer_norm.weight', 'lm_head.dense.bias', 'lm_head.dense.weight', 'lm_head.bias', 'lm_head.decoder.weight', 'lm_head.layer_norm.bias']\n",
+      "- This IS expected if you are initializing XLMRobertaModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
+      "- This IS NOT expected if you are initializing XLMRobertaModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "torch.Size([4, 768])\n"
+     ]
+    }
+   ],
+   "source": [
+    "from multilingual_clip import pt_multilingual_clip\n",
+    "import transformers\n",
+    "\n",
+    "texts = [\n",
+    "    'Three blind horses listening to Mozart.',\n",
+    "    'Älgen är skogens konung!',\n",
+    "    'Wie leben Eisbären in der Antarktis?',\n",
+    "    'Вы знали, что все белые медведи левши?'\n",
+    "]\n",
+    "model_name = 'M-CLIP/XLM-Roberta-Large-Vit-L-14'\n",
+    "\n",
+    "# Load Model & Tokenizer\n",
+    "model = pt_multilingual_clip.MultilingualCLIP.from_pretrained(model_name)\n",
+    "tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)\n",
+    "\n",
+    "embeddings = model.forward(texts, tokenizer)\n",
+    "print(embeddings.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "texts = [\n",
+    "    'Aku sayang kamu',\n",
+    "    'Aku benci kamu',\n",
+    "]\n",
+    "embeddings = model.forward(texts, tokenizer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings_1, embeddings_2 = embeddings\n",
+    "embeddings_1 = embeddings_1.cpu().detach().numpy()\n",
+    "embeddings_2 = embeddings_2.cpu().detach().numpy()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "from numpy.linalg import norm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.967305\n"
+     ]
+    }
+   ],
+   "source": [
+    "cosine = np.dot(embeddings_1,embeddings_2)/(norm(embeddings_1)*norm(embeddings_2))\n",
+    "print(cosine)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.13"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "ad2bdc8ecc057115af97d19610ffacc2b4e99fae6737bb82f5d7fb13d2f2c186"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

TextSimilarity.py

@@ -0,0 +1,28 @@
+from multilingual_clip import pt_multilingual_clip
+from numpy.linalg import norm
+import transformers
+import numpy as np
+import torch
+
+# M-CLIP/XLM-Roberta-Large-Vit-L-14
+# M-CLIP/XLM-Roberta-Large-Vit-B-16Plus
+
+
+class TextSimilarity:
+    def __init__(self, name_model="M-CLIP/XLM-Roberta-Large-Vit-B-32"):
+        self.name_model = name_model
+        self.device = torch.device(
+            "cuda:0" if torch.cuda.is_available() else "cpu")
+        self.tokenizer = transformers.AutoTokenizer.from_pretrained(
+            self.name_model)
+        self.model = pt_multilingual_clip.MultilingualCLIP.from_pretrained(
+            self.name_model)
+        self.model.eval()
+
+    def predict(self, text_1, text_2):
+        with torch.no_grad():
+            embeddings = self.model.forward([text_1, text_2], self.tokenizer)
+            embeddings_1, embeddings_2 = embeddings.cpu().detach().numpy()
+        cosine = np.dot(embeddings_1, embeddings_2) / \
+            (norm(embeddings_1)*norm(embeddings_2))
+        return cosine

app.py

@@ -0,0 +1,51 @@
+import uvicorn
+from utils import check_score
+from pydantic import BaseModel
+from fastapi import FastAPI, status
+from TextSimilarity import TextSimilarity
+from starlette.responses import JSONResponse
+from fastapi.middleware.cors import CORSMiddleware
+
+
+class RequestBody(BaseModel):
+    text_1: str
+    text_2: str
+
+
+app = FastAPI(docs_url=None, redoc_url=None)
+text_similarity = TextSimilarity()
+
+origins = ['*']
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=origins,
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+
+)
+
+
+@app.post("/penilaian")
+async def penilaian(data_request: RequestBody):
+    if not data_request.text_2:
+        return JSONResponse({
+            "probability": 0,
+            "score": 0
+        }, status_code=status.HTTP_200_OK)
+    try:
+        probability = text_similarity.predict(
+            data_request.text_1, data_request.text_2)
+        return_value = check_score(float(probability))
+        return JSONResponse(
+            return_value, status_code=status.HTTP_200_OK)
+    except Exception as e:
+        print(e)
+        return JSONResponse({
+            "errors": "Please contact your administrator"
+        }, status_code=status.HTTP_500_INTERNAL_SERVER_ERROR)
+
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="localhost", port=53640)

requirements.txt

@@ -0,0 +1,8 @@
+pydantic==1.8.2
+starlette==0.14.2
+transformers==4.30.0
+numpy==3.9
+uvicorn[standard]
+fastapi
+torch>=1.13.1
+torchvision>=0.14.1

utils.py

@@ -0,0 +1,17 @@
+def check_score(probability: float):
+    return_value = {
+        "probability": probability,
+        "score": 0,
+    }
+    if 0.95 <= probability <= 1:
+        return_value["score"] = 4
+        return return_value
+    elif 0.89 <= probability <= 0.95:
+        return_value["score"] = 3
+        return return_value
+    elif 0.75 <= probability <= 0.89:
+        return_value["score"] = 2
+        return return_value
+    elif probability <= 0.75:
+        return_value["score"] = 1
+        return return_value