check

.python-version

@@ -0,0 +1 @@
+3.12.0

main.py

@@ -0,0 +1,98 @@
+from fastapi import FastAPI, Request, Form
+from fastapi.responses import HTMLResponse
+from fastapi.staticfiles import StaticFiles
+from fastapi.templating import Jinja2Templates
+from pydantic import BaseModel
+from transformers import pipeline, AutoTokenizer, AutoModelForTokenClassification
+import numpy as np
+
+app = FastAPI()
+
+# Serve static files like CSS and JavaScript
+app.mount("/static", StaticFiles(directory="static"), name="static")
+
+# Set up Jinja2 templates
+templates = Jinja2Templates(directory="templates")
+
+# Load the Hugging Face model and tokenizer
+model_name = "IsmatS/xlm-roberta-az-ner"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForTokenClassification.from_pretrained(model_name)
+nlp_ner = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy="simple")
+
+label_mapping = {
+    "LABEL_0": "Other",
+    "LABEL_1": "Person",
+    "LABEL_2": "Location",
+    "LABEL_3": "Organization",
+    "LABEL_4": "Date",
+    "LABEL_5": "Time",
+    "LABEL_6": "Money",
+    "LABEL_7": "Percentage",
+    "LABEL_8": "Facility",
+    "LABEL_9": "Product",
+    "LABEL_10": "Event",
+    "LABEL_11": "Art",
+    "LABEL_12": "Law",
+    "LABEL_13": "Language",
+    "LABEL_14": "Government",
+    "LABEL_15": "Nationality or Religion",
+    "LABEL_16": "Ordinal",
+    "LABEL_17": "Cardinal",
+    "LABEL_18": "Disease",
+    "LABEL_19": "Contact",
+    "LABEL_20": "Proverb or Saying",
+    "LABEL_21": "Quantity",
+    "LABEL_22": "Miscellaneous",
+    "LABEL_23": "Position",
+    "LABEL_24": "Project"
+}
+
+def convert_numpy_types(obj):
+    if isinstance(obj, np.float32):
+        return float(obj)
+    elif isinstance(obj, np.int32):
+        return int(obj)
+    elif isinstance(obj, list):
+        return [convert_numpy_types(item) for item in obj]
+    elif isinstance(obj, dict):
+        return {key: convert_numpy_types(value) for key, value in obj.items()}
+    else:
+        return obj
+
+@app.get("/", response_class=HTMLResponse)
+async def index(request: Request):
+    return templates.TemplateResponse("index.html", {"request": request})
+
+@app.post("/predict/")
+async def predict_ner(text: str = Form(...)):
+    ner_results = nlp_ner(text)
+    
+    # Initialize dictionary to store entities by type
+    entities_by_type = {}
+
+    # Process each detected entity
+    for entity in ner_results:
+        # Get the human-readable label
+        entity_type = label_mapping.get(entity["entity_group"], entity["entity_group"])
+        
+        # Filter out non-entities (label "Other" in this case)
+        if entity_type == "Other":
+            continue
+        
+        # Add entity to the dictionary by its type
+        if entity_type not in entities_by_type:
+            entities_by_type[entity_type] = []  # Initialize list for new entity type
+        
+        # Append the entity word to the corresponding type list
+        entities_by_type[entity_type].append(entity["word"])
+
+    return {"entities": entities_by_type}
+
+
+# Run with uvicorn main:app --reload
+# curl -X POST "http://127.0.0.1:8000/predict/" \
+# -H "Content-Type: application/json" \
+# -d '{"text": "Bakı şəhərində Azərbaycan Respublikasının prezidenti İlham Əliyev."}'
+
+# 2014 - cu ilde Azərbaycan Respublikasının prezidenti İlham Əliyev Salyanda olub.

requirements.txt

@@ -1,13 +1,35 @@
+annotated-types==0.7.0
+anyio==4.6.2.post1
 certifi==2024.8.30
 charset-normalizer==3.4.0
+click==8.1.7
+fastapi==0.115.4
 filelock==3.16.1
 fsspec==2024.10.0
+h11==0.14.0
 huggingface-hub==0.26.2
 idna==3.10
+Jinja2==3.1.4
+MarkupSafe==3.0.2
+mpmath==1.3.0
+networkx==3.4.2
+numpy==2.1.3
 packaging==24.1
-python-dotenv==1.0.1
+pydantic==2.9.2
+pydantic_core==2.23.4
+python-multipart==0.0.17
 PyYAML==6.0.2
+regex==2024.9.11
 requests==2.32.3
+safetensors==0.4.5
+setuptools==75.3.0
+sniffio==1.3.1
+starlette==0.41.2
+sympy==1.13.1
+tokenizers==0.20.1
+torch==2.5.1
 tqdm==4.66.6
+transformers==4.46.1
 typing_extensions==4.12.2
 urllib3==2.2.3
+uvicorn==0.32.0

static/app.js

@@ -0,0 +1,42 @@
+document.getElementById("nerForm").addEventListener("submit", async function (e) {
+    e.preventDefault();
+    const text = document.getElementById("textInput").value;
+    const response = await fetch("/predict/", {
+        method: "POST",
+        headers: { "Content-Type": "application/x-www-form-urlencoded" },
+        body: new URLSearchParams({ text })
+    });
+    const result = await response.json();
+    
+    // Display results in a structured format
+    displayResults(result.entities);
+});
+
+function displayResults(entities) {
+    const resultsDiv = document.getElementById("resultsContent");
+    resultsDiv.innerHTML = ""; // Clear previous results
+
+    // Check if any entities are returned
+    if (Object.keys(entities).length === 0) {
+        resultsDiv.innerHTML = "<p>No high-confidence entities found.</p>";
+        return;
+    }
+
+    // Display entities grouped by type in the desired format
+    Object.entries(entities).forEach(([entityType, words]) => {
+        const entityGroup = document.createElement("div");
+        entityGroup.classList.add("entity-group");
+
+        const title = document.createElement("h3");
+        title.textContent = entityType; // Display entity type (e.g., Date, Government)
+        entityGroup.appendChild(title);
+
+        words.forEach(word => {
+            const entityEl = document.createElement("p");
+            entityEl.textContent = word; // Display the actual entity word
+            entityGroup.appendChild(entityEl);
+        });
+
+        resultsDiv.appendChild(entityGroup);
+    });
+}

static/style.css

@@ -0,0 +1,124 @@
+/* Basic Reset */
+* {
+    box-sizing: border-box;
+    margin: 0;
+    padding: 0;
+}
+
+/* Body Styling */
+body {
+    font-family: Arial, sans-serif;
+    display: flex;
+    justify-content: center;
+    align-items: center;
+    min-height: 100vh;
+    background-color: #f4f4f9;
+    margin: 0;
+    padding: 20px;
+}
+
+/* Container Styling */
+.container {
+    width: 100%;
+    max-width: 600px;
+    text-align: center;
+    background: white;
+    border-radius: 8px;
+    box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
+    padding: 20px;
+}
+
+/* Title and Description */
+h1 {
+    font-size: 24px;
+    color: #333;
+    margin-bottom: 10px;
+}
+
+p {
+    font-size: 16px;
+    color: #666;
+    margin-bottom: 20px;
+}
+
+/* Form and Button Styling */
+textarea {
+    width: 100%;
+    height: 100px;
+    padding: 10px;
+    font-size: 16px;
+    border: 1px solid #ddd;
+    border-radius: 5px;
+    margin-bottom: 10px;
+    resize: vertical;
+}
+
+button {
+    padding: 10px 20px;
+    font-size: 16px;
+    color: #fff;
+    background-color: #007bff;
+    border: none;
+    border-radius: 5px;
+    cursor: pointer;
+    transition: background-color 0.3s;
+}
+
+button:hover {
+    background-color: #0056b3;
+}
+
+/* Results Section Styling */
+.results-section {
+    margin-top: 20px;
+    text-align: left;
+}
+
+.results-section h2 {
+    font-size: 20px;
+    color: #333;
+    margin-bottom: 10px;
+}
+
+/* Entity Group Styling */
+.entity-group {
+    margin-bottom: 15px;
+    padding: 10px;
+    border: 1px solid #ddd;
+    border-radius: 5px;
+    background-color: #fafafa;
+}
+
+.entity-group h3 {
+    font-size: 18px;
+    color: #007bff;
+    margin-bottom: 8px;
+}
+
+.entity-group p {
+    font-size: 16px;
+    color: #555;
+}
+
+/* Responsive Design */
+@media (max-width: 600px) {
+    .container {
+        width: 90%;
+    }
+
+    h1 {
+        font-size: 20px;
+    }
+
+    button {
+        font-size: 14px;
+    }
+
+    .results-section h2, .entity-group h3 {
+        font-size: 18px;
+    }
+
+    textarea {
+        height: 80px;
+    }
+}

templates/index.html

@@ -0,0 +1,27 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Named Entity Recognition</title>
+    <link rel="stylesheet" href="/static/style.css">
+</head>
+<body>
+    <div class="container">
+        <h1>Named Entity Recognition</h1>
+        <p>Enter your text below to analyze entities and see their types, such as Date, Person, or Location.</p>
+        
+        <form id="nerForm">
+            <!-- Add the default sentence as a value in the textarea -->
+            <textarea id="textInput" name="text">2014 - cu ilde Azərbaycan Respublikasının prezidenti İlham Əliyev Salyanda olub.</textarea>
+            <button type="submit">Analyze</button>
+        </form>
+        
+        <div id="results" class="results-section">
+            <h2>Results</h2>
+            <div id="resultsContent"></div> <!-- Display JSON here -->
+        </div>
+    </div>
+    <script src="/static/app.js"></script>
+</body>
+</html>