Resolve merge conflict in README.md

Dockerfile

@@ -0,0 +1,10 @@
+FROM python:3.9-slim
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+CMD ["python", "app.py"]

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

app.py

@@ -0,0 +1,529 @@
+import dash
+import dash_bootstrap_components as dbc
+import pandas as pd
+from dash import dcc, html, callback_context
+from dash.dash_table import DataTable
+from dash.dependencies import Output, Input, State
+import plotly.express as px
+import spacy
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+from gliner_spacy.pipeline import GlinerSpacy
+import warnings
+import os
+import gc
+
+# Suppress specific warnings
+warnings.filterwarnings("ignore", message="The sentencepiece tokenizer")
+
+# Initialize Dash app
+app = dash.Dash(__name__, external_stylesheets=[dbc.themes.DARKLY, 'https://use.fontawesome.com/releases/v5.8.1/css/all.css'])
+server = app.server
+
+# Reference absolute file path 
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+CATEGORIES_FILE = os.path.join(BASE_DIR, 'google_categories.txt')
+
+# Configuration for GLiNER integration
+custom_spacy_config = {
+    "gliner_model": "urchade/gliner_small-v2.1",
+    "chunk_size": 128,
+    "labels": ["person", "organization", "location", "event", "work_of_art", "product", "service", "date", "number", "price", "address", "phone_number", "misc"],
+    "threshold": 0.5
+}
+
+# Model variables for lazy loading
+nlp = None
+sentence_model = None
+google_categories = []
+
+# Function to lazy load NLP model
+def get_nlp():
+    global nlp
+    if nlp is None:
+        try:
+            nlp = spacy.blank("en")
+            nlp.add_pipe("gliner_spacy", config=custom_spacy_config)
+        except Exception as e:
+            raise
+    return nlp
+
+# Function to lazy load sentence transformer model
+def get_sentence_model():
+    global sentence_model
+    if sentence_model is None:
+        sentence_model = SentenceTransformer('all-MiniLM-L6-v2')
+    return sentence_model
+
+# Load Google's content categories
+def load_google_categories():
+    global google_categories
+    if not google_categories:
+        try:
+            with open(CATEGORIES_FILE, 'r') as f:
+                google_categories = [line.strip() for line in f]
+        except Exception as e:
+            google_categories = []
+    return google_categories
+
+# Function to perform NER using GLiNER with spaCy
+def perform_ner(text):
+    try:
+        doc = get_nlp()(text)
+        return [(ent.text, ent.label_) for ent in doc.ents]
+    except Exception as e:
+        return []
+
+# Function to extract entities using GLiNER with spaCy
+def extract_entities(text):
+    try:
+        doc = get_nlp()(text)
+        entities = [(ent.text, ent.label_) for ent in doc.ents]
+        return entities if entities else ["No specific entities found"]
+    except Exception as e:
+        return ["Error extracting entities"]
+
+# Function to precompute category embeddings
+def compute_category_embeddings():
+    try:
+        categories = load_google_categories()
+        return get_sentence_model().encode(categories)
+    except Exception as e:
+        return []
+
+# Function to perform topic modeling using sentence transformers
+def perform_topic_modeling_from_similarities(similarities):
+    try:
+        categories = load_google_categories()
+        top_indices = similarities.argsort()[-3:][::-1]
+        
+        best_match = categories[top_indices[0]]
+        second_best = categories[top_indices[1]]
+        
+        if similarities[top_indices[0]] > similarities[top_indices[1]] * 1.1:
+            return best_match
+        else:
+            return f"{best_match} , {second_best}"
+    except Exception as e:
+        return "Error in topic modeling"
+
+# Function to sort keywords by intent feature
+def sort_by_keyword_feature(f):
+    if type(f) != str:
+        return "other"
+    f = f.lower()
+
+    informational_keywords = [
+        "advice", "help", "how do i", "how does", "how to", "ideas", "information", "tools", "list", 
+        "resources", "tips", "tutorial", "diy", "ways to", "what does", "what is", "what was", "where are", "where does", 
+        "where can", "where is", "where was", "when is", "when are", "when was", "where to", "who is", "who said", "who wrote", 
+        "who are", "why are", "who was", "why is", "examples", "explained", "meaning of", "definition", "benefits of", "uses of", 
+        "overview", "summary", "report", "study",  "analysis", "research", "insight", "data", "facts", "details", "background", 
+        "context", "news", "history", "documentation", "article", "paper", "blog", "forum", "discussion", "commentary", 
+        "opinion", "perspective", "viewpoint", "guide", "difference between", "types of"
+    ]
+
+    navigational_keywords = [
+        "facebook", "meta", "twitter", "site", "login", "account", "official website", "homepage", "portal", 
+        "signin", "register", "signup", "dashboard", "profile", "settings", "control panel", "main page", 
+        "user area", "admin", "control", "access", "entry", "webpage", "navigate", "home", "site map", 
+        "directory", "find", "search", "lookup", "index", "online", "internet", "web", "browser", "navigate to", 
+        "goto", "landing page", "url", "hyperlink", "link", "web address", "navigate", 
+        "web navigation", "website address", "app", "download", "status", "join"
+    ]
+
+    local_keywords = [
+        "closest", "close", "near me", "my area", "residential", "my zip", "my city", "nearby", "in town", 
+        "around here", "local", "near", "vicinity", "local area", "nearest", "surrounding", "within miles", 
+        "in my neighborhood", "district", "zone", "region", "near my location", "local services", "community", 
+        "local shop", "in my vicinity", "local store", "suburb", "urban area", "within walking distance", 
+        "around my place", "within my reach", "close by", "local office", "local branch", "near me now", 
+        "in my locale", "within the city", "local market", "in my town", "local spot", "local point", 
+        "local guide", "near my house", "local venue", "close to me", "within blocks", "local attractions", 
+        "local events", "address"
+    ]
+
+    commercial_keywords = [
+        "best", "affordable", "budget", "cheap", "expensive", "review", "top", "service", "cost", "average cost", 
+        "calculator", "provider", "company", "vs", "companies", "professional", "specialist", "compare", 
+        "comparison", "rating", "testimonials", "recommendation", "advisor", "consultant", "expert", "ranking", 
+        "leader", "top-rated", "best-selling", "trending", "featured", "highlighted", "recommended", "popular", 
+        "favorite", "preferred", "choice", "most reviewed", "highest rated", "highly recommended", "award-winning", 
+        "five-star", "customer favorite", "top pick", "critically acclaimed", "editor's choice", "people's choice", 
+        "top performer", "best value", "best overall", "best quality", "best price", "most trusted", "leading brand", 
+        "popular choice", "most popular", "fees", "pros and cons"
+    ]
+
+    transactional_keywords = [
+        "price", "quotes", "pricing", "purchase", "rates", "how much", "same day", "same-day", "buy", "order", 
+        "discount", "deal", "offers", "sale", "checkout", "book", "reservation", "reserve", "bargain", "coupon", 
+        "promo", "rebate", "clearance", "markdown", "buy one get one", "bogo", "special", "exclusive", "bundle", 
+        "package", "subscription", "membership", "payment", "installment", "financing", "contract", "billing", 
+        "invoice", "ticket", "admission", "entry", "enrollment", "register", "sign up", "pre-order", "e-commerce", 
+        "shopping cart"
+    ]
+
+    if any(keyword in f for keyword in informational_keywords):
+        return "informational"
+    if any(keyword in f for keyword in navigational_keywords):
+        return "navigational"
+    if any(keyword in f for keyword in local_keywords):
+        return "local"
+    if any(keyword in f for keyword in commercial_keywords):
+        return "commercial investigation"
+    if any(keyword in f for keyword in transactional_keywords):
+        return "transactional"
+
+    return "other"
+
+# Optimized batch processing of keywords
+def batch_process_keywords(keywords, batch_size=8):
+    processed_data = {'Keywords': [], 'Intent': [], 'NER Entities': [], 'Google Content Topics': []}
+    
+    try:
+        sentence_model = get_sentence_model()
+        category_embeddings = compute_category_embeddings()
+        
+        for i in range(0, len(keywords), batch_size):
+            batch = keywords[i:i+batch_size]
+            batch_embeddings = sentence_model.encode(batch, batch_size=batch_size, show_progress_bar=False)
+            
+            intents = [sort_by_keyword_feature(kw) for kw in batch]
+            entities = [extract_entities(kw) for kw in batch]
+            
+            similarities = cosine_similarity(batch_embeddings, category_embeddings)
+            Google_Content_Topics = [perform_topic_modeling_from_similarities(sim) for sim in similarities]
+            
+            processed_data['Keywords'].extend(batch)
+            processed_data['Intent'].extend(intents)
+            
+            processed_entities = []
+            for entity_list in entities:
+                entity_strings = []
+                for entity in entity_list:
+                    if isinstance(entity, tuple):
+                        entity_strings.append(f"{entity[0]} ({entity[1]})")
+                    else:
+                        entity_strings.append(str(entity))
+                processed_entities.append(", ".join(entity_strings))
+            
+            processed_data['NER Entities'].extend(processed_entities)
+            processed_data['Google Content Topics'].extend(Google_Content_Topics)
+            
+            # Force garbage collection
+            gc.collect()
+    
+    except Exception as e:
+        pass
+    
+    return processed_data
+
+# Main layout of the dashboard
+app.layout = dbc.Container([
+    dcc.Store(id='models-loaded', data=False),
+    dbc.NavbarSimple(
+    children=[
+        dbc.NavItem(dbc.NavLink("About", href="#about", external_link=True)),
+        dbc.NavItem(dbc.NavLink("Contact", href="#contact", external_link=True)),
+    ],
+    brand="KeyIntentNER-T",
+    brand_href="https://github.com/jeredhiggins/KeyIntentNER-T",
+    color="#151515",
+    dark=True,
+    brand_style={"background": "linear-gradient(to right, #ff7e5f, #feb47b)", "-webkit-background-clip": "text", "color": "transparent", "textShadow": "0 0 1px #ffffff, 0 0 3px #ff7e5f, 0 0 5px #ff7e5f"},
+),
+
+    dbc.Row(dbc.Col(html.H1('Keyword Intent, Named Entity Recognition (NER), & Google Topic Modeling Dashboard', className='text-center text-light mb-4 mt-4'))),
+
+    dbc.Row([
+        dbc.Col([
+            dbc.Label('Enter keywords (one per line, maximum of 100):', className='text-light'),
+            dcc.Textarea(id='keyword-input', value='', style={'width': '100%', 'height': 100}),
+            dbc.Button('Submit', id='submit-button', color='primary', className='mb-3', disabled=True),
+            dbc.Alert(id='alert', is_open=False, duration=4000, color='danger', className='my-2'),
+            dbc.Alert(id='processing-alert', is_open=False, color='info', className='my-2'),
+        ], width=6)
+    ], justify='center'),
+    
+    dbc.Row([
+        dbc.Col([
+            dcc.Loading(
+                id="loading",
+                type="default",
+                children=[html.Div(id="loading-output", className="my-4")]
+            ),
+        ], width=12)
+    ], justify='center', className="mb-4"),
+
+    dbc.Row(dbc.Col(dcc.Graph(id='bar-chart'), width=12)),
+
+    dbc.Row([
+        dbc.Col([
+            dbc.Label('View all keyword data for each intent category:', className='text-light mt-4'),
+            dcc.Dropdown(
+                id='table-intent-dropdown',
+                options=[],
+                placeholder='Select an Intent',
+                className='text-dark'
+            ),
+        ], width=6)
+    ], justify='center'),
+
+    dbc.Row(dbc.Col(
+        html.Div(id='keywords-table', style={'width': '100%'}),
+        width=12
+    )),
+
+    dbc.Row(dbc.Col(
+        dbc.Button('Download CSV For All Keywords', id='download-button', color='success', className='my-5', disabled=True),
+        width=12
+    ), justify='center'),
+
+    dcc.Download(id='download'),
+    dcc.Store(id='processed-data'),
+
+# Explanation content
+    dbc.Row([
+        dbc.Col([
+            html.Div([
+                dbc.Card([
+                    dbc.CardBody([
+                        html.H3([html.I(className="fas fa-info-circle mr-2"), "About KeyIntentNER-T"], className="card-title text-warning"),
+                        html.P("This tool provides valuable keyword insights for SEO and digital marketing professionals. Enter a list of keywords and get insights into Keyword Intent, NLP Entities extracted via NER (Named Entity Recognition), & Topics. I created KeyIntentNER-T as an example of how to use more modern NLP methods to gain insights into shorter text strings (keywords) and how this information may be understood by search engines using similar techniques.", className="card-text"), 
+                    ])
+                ], className="mb-4 shadow-sm"),
+                dbc.Row([
+                    dbc.Col([
+                        dbc.Card([
+                            dbc.CardBody([
+                                html.H3([html.I(className="fas fa-pen mr-2"), "Notes on the data"], className="card-title text-success"),
+                                dbc.ListGroup([
+                                    dbc.ListGroupItem([html.I(className="fas fa-check mr-2"), "Keyword Intent is determined using a custom function that looks for the presence of specific terms and then classifies it into one of six predefined intent categories: 'informational', 'navigational', 'local', 'commercial investigation', 'transactional', or 'other'."]),
+                                    dbc.ListGroupItem([html.I(className="fas fa-check mr-2"), "NLP Entities are determined using GLiNER, an advanced Named Entity Recognition (NER) model that is better at classifying shorter text strings. Additionally, Entitites are mapped to all Entity Types included in the Google Cloud Natural Language API."]),
+                                    dbc.ListGroupItem([html.I(className="fas fa-check mr-2"), "Topics are determined by matching keywords to topics from Google's well-known Content and Product taxonomies."]),
+                                    dbc.ListGroupItem([html.I(className="fas fa-check mr-2"), "Since this tool is doing a lot behind the scenes, keyword processing can take anywhere from 30 seconds up to ~2 minutes."]),
+                                ], flush=True)
+                            ])
+                        ], className="mb-4 shadow-sm")
+                    ], md=6),
+                    dbc.Col([
+                        dbc.Card([
+                            dbc.CardBody([
+                                html.H3([html.I(className="fas fa-chart-line mr-2"), "Benefits for SEO"], className="card-title text-info"),
+                                dbc.ListGroup([
+                                    dbc.ListGroupItem([html.I(className="fas fa-arrow-up mr-2"), "Improved content strategy by focusing your SEO efforts on creating more relevant/helpful content that addresses the search intent for keywords."]),
+                                    dbc.ListGroupItem([html.I(className="fas fa-bullseye mr-2"), "Enhanced keyword targeting by matching keywords to Google's well-known categories, ensuring your content is aligned with popular search themes."]),
+                                    dbc.ListGroupItem([html.I(className="fas fa-users mr-2"), "Better understanding of what kind of information a person is looking for."]),
+                                    dbc.ListGroupItem([html.I(className="fas fa-robot mr-2"), "Better understanding of how keywords can be interpreted by search engines."]),
+                                ], flush=True)
+                            ])
+                        ], className="mb-4 shadow-sm")
+                    ], md=6),
+                ]),
+                dbc.Card([
+                    dbc.CardBody([
+                        html.H3([html.I(className="fas fa-quote-left mr-2"), "GLiNER Model Citation"], className="card-title text-light"),
+                        html.P([
+                            "GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer. ",
+                            html.Br(),
+                            "Authors: Urchade Zaratiana, Nadi Tomeh, Pierre Holat, Thierry Charnois.",
+                            html.Br(),
+                            "Year: 2023.",
+                            html.Br(),
+                            html.A([html.I(className="fas fa-external-link-alt mr-2"), "arXiv:2311.08526"], href="https://arxiv.org/abs/2311.08526", target="_blank", className="btn btn-outline-warning btn-sm mt-2")
+                        ], className="card-text"),
+                    ])
+                ], className="mb-4 shadow-sm")
+            ], id="about")
+        ], width=12)
+    ], className="mt-5"),
+
+    # Contact section
+    dbc.Row([
+        dbc.Col([
+            html.Div([
+                dbc.Card([
+                    dbc.CardBody([
+                        html.H3([html.I(className="fas fa-envelope mr-2"), "Contact"], className="card-title text-info"),
+                        html.P([
+                            "For questions or if you are interested in building custom SEO dash apps, contact me at: ",
+                            html.A("[email protected]", href="mailto:[email protected]", className="text-info")
+                        ], className="card-text"),
+                    ])
+                ], className="mb-4 shadow-sm")
+            ], id="contact")
+        ], width=12)
+    ], className="mt-4 mb-4"),
+
+# JS for smooth scrolling
+    html.Div([
+        html.Script('''
+            document.addEventListener("DOMContentLoaded", function() {
+                var links = document.querySelectorAll("a[href^='#']");
+                links.forEach(function(link) {
+                    link.addEventListener("click", function(e) {
+                        e.preventDefault();
+                        var targetId = this.getAttribute("href").substring(1);
+                        var targetElement = document.getElementById(targetId);
+                        if (targetElement) {
+                            targetElement.scrollIntoView({
+                                behavior: "smooth",
+                                block: "start"
+                            });
+                        }
+                    });
+                });
+            });
+        ''')
+    ]),
+
+], fluid=True)
+
+# Combined callback
+@app.callback(
+    [Output('models-loaded', 'data'),
+     Output('submit-button', 'disabled'),
+     Output('alert', 'is_open'),
+     Output('alert', 'children'),
+     Output('alert', 'color'),
+     Output('processed-data', 'data'),
+     Output('loading-output', 'children'),
+     Output('processing-alert', 'is_open'),
+     Output('processing-alert', 'children')],
+    [Input('models-loaded', 'data'),
+     Input('submit-button', 'n_clicks')],
+    [State('keyword-input', 'value')]
+)
+def combined_callback(loaded, n_clicks, keyword_input):
+    ctx = callback_context
+    triggered_id = ctx.triggered[0]['prop_id'].split('.')[0]
+
+    if triggered_id == 'models-loaded':
+        return handle_model_loading(loaded)
+    elif triggered_id == 'submit-button':
+        return handle_keyword_processing(n_clicks, keyword_input)
+    else:
+        # Default return values
+        return loaded, False, False, "", "success", None, '', False, ''
+
+def handle_model_loading(loaded):
+    if not loaded:
+        try:
+            # Lazy loading will occur when models are first used
+            return True, False, True, "Models ready to load", "success", None, '', False, ''
+        except Exception as e:
+            return False, True, True, f"Error preparing models: {str(e)}", "danger", None, '', False, ''
+    return loaded, not loaded, False, "", "success", None, '', False, ''
+
+def handle_keyword_processing(n_clicks, keyword_input):
+    if n_clicks is None or not keyword_input:
+        return True, False, False, "", "success", None, '', False, ''
+
+    keywords = [kw.strip() for kw in keyword_input.split('\n')[:100] if kw.strip()]
+    processed_data = batch_process_keywords(keywords)
+
+    return True, False, False, "", "success", processed_data, '', True, "Keyword processing complete!"
+
+# Callback for updating the bar chart
+@app.callback(
+    Output('bar-chart', 'figure'),
+    [Input('processed-data', 'data')]
+)
+def update_bar_chart(processed_data):
+    if processed_data is None:
+        return {
+            'data': [],
+            'layout': {
+                'height': 0,
+                'annotations': [{
+                    'text': '',
+                    'xref': 'paper',
+                    'yref': 'paper',
+                    'showarrow': False,
+                    'font': {'size': 28}
+                }]
+            }
+        }
+
+    df = pd.DataFrame(processed_data)
+    intent_counts = df['Intent'].value_counts().reset_index()
+    intent_counts.columns = ['Intent', 'Count']
+
+    fig = px.bar(intent_counts, x='Intent', y='Count', color='Intent', 
+                 title='Keyword Intent Distribution', 
+                 color_discrete_sequence=px.colors.qualitative.Dark2)
+    
+    fig.update_layout(
+        plot_bgcolor='#222222',
+        paper_bgcolor='#222222',
+        font_color='white',
+        height=400,
+        legend=dict(
+            orientation="h",
+            yanchor="bottom",
+            y=1.02,
+            xanchor="right",
+            x=1
+        )
+    )
+
+    return fig
+
+# Callback for updating the dropdown and download button
+@app.callback(
+    [Output('table-intent-dropdown', 'options'),
+     Output('download-button', 'disabled')],
+    [Input('processed-data', 'data')]
+)
+def update_dropdown_and_button(processed_data):
+    if processed_data is None:
+        return [], True
+
+    df = pd.DataFrame(processed_data)
+    intents = df['Intent'].unique()
+    options = [{'label': intent, 'value': intent} for intent in intents]
+    return options, False
+
+# Callback for updating the keywords table
+@app.callback(
+    Output('keywords-table', 'children'),
+    [Input('table-intent-dropdown', 'value')],
+    [State('processed-data', 'data')]
+)
+def update_keywords_table(selected_intent, processed_data):
+    if processed_data is None or selected_intent is None:
+        return html.Div()
+
+    df = pd.DataFrame(processed_data)
+    filtered_df = df[df['Intent'] == selected_intent]
+
+    table = DataTable(
+        columns=[{"name": i, "id": i} for i in filtered_df.columns],
+        data=filtered_df.to_dict('records'),
+        style_table={'overflowX': 'auto'},
+        style_cell={'textAlign': 'left', 'whiteSpace': 'normal', 'height': 'auto', 'minWidth': '100px', 'width': '100px', 'maxWidth': '100px'},
+        style_header={'backgroundColor': 'rgb(30, 30, 30)', 'color': 'white'},
+        style_data={'backgroundColor': 'rgb(50, 50, 50)', 'color': 'white'},
+        sort_action='native',
+        page_action='native',
+        page_current=0
+    )
+    return table
+
+# Callback for downloading CSV
+@app.callback(
+    Output('download', 'data'),
+    [Input('download-button', 'n_clicks')],
+    [State('processed-data', 'data')]
+)
+def download_csv(n_clicks, processed_data):
+    if n_clicks is None or processed_data is None:
+        return None
+
+    df = pd.DataFrame(processed_data)
+    csv_string = df.to_csv(index=False, encoding='utf-8')
+    return dict(content=csv_string, filename="KeyIntentNER-T_keyword_analysis.csv")
+
+# Modified the server run command for HuggingFace Spaces
+if __name__ == "__main__":
+    app.run_server(debug=False, host="0.0.0.0", port=7860)

requirements.txt

@@ -0,0 +1,9 @@
+dash
+dash-bootstrap-components
+pandas
+plotly
+spacy
+sentence-transformers
+scikit-learn
+gliner-spacy
+gunicorn