Spaces:
Running on Zero
Running on Zero
Download app.py from AIproject2008/TruthLens-AI: direct link, hf CLI and curl.
- Browser
- Download file 17.9 kB
-
https://huggingface.co/spaces/AIproject2008/TruthLens-AI/resolve/main/app.py
- Command line
-
hf download hf://spaces/AIproject2008/TruthLens-AI/app.py
-
curl -L -o app.py https://huggingface.co/spaces/AIproject2008/TruthLens-AI/resolve/main/app.py
17.9 kB
| import gradio as gr | |
| import spaces | |
| import torch | |
| import requests | |
| import feedparser | |
| import trafilatura | |
| import plotly.express as px | |
| import pandas as pd | |
| import html | |
| import re | |
| from urllib.parse import urlparse, quote_plus | |
| from transformers import ( | |
| AutoTokenizer, | |
| AutoModelForSequenceClassification | |
| ) | |
| # ===================================================== | |
| # 1. CONFIGURATION | |
| # ===================================================== | |
| APP_NAME = "TruthLens AI" | |
| MODEL_NAME = "cross-encoder/nli-deberta-v3-small" | |
| HEADERS = { | |
| "User-Agent": "TruthLensAI/1.0 Educational Project" | |
| } | |
| LABELS = [ | |
| "Contradicts", | |
| "Supports", | |
| "Unclear" | |
| ] | |
| # ===================================================== | |
| # 2. LOAD HUGGING FACE MODEL | |
| # ===================================================== | |
| # Load on CPU first. | |
| # GPU is used only inside the ZeroGPU function below. | |
| tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME) | |
| model = AutoModelForSequenceClassification.from_pretrained( | |
| MODEL_NAME | |
| ) | |
| model.eval() | |
| # ===================================================== | |
| # 3. EXTRACT NEWS ARTICLE | |
| # ===================================================== | |
| def extract_article(url): | |
| parsed = urlparse(url) | |
| if parsed.scheme not in ["http", "https"]: | |
| raise ValueError("Enter a valid HTTP or HTTPS URL.") | |
| if not parsed.hostname: | |
| raise ValueError("Invalid website address.") | |
| if parsed.hostname.lower() in [ | |
| "localhost", | |
| "127.0.0.1", | |
| "::1" | |
| ]: | |
| raise ValueError("This website address is not allowed.") | |
| response = requests.get( | |
| url, | |
| headers=HEADERS, | |
| timeout=20, | |
| stream=True | |
| ) | |
| response.raise_for_status() | |
| if int(response.headers.get("Content-Length", 0)) > 4_000_000: | |
| raise ValueError("Article page is too large.") | |
| content = response.raw.read(4_000_000) | |
| response.close() | |
| text = trafilatura.extract(content) | |
| metadata = trafilatura.extract_metadata(content) | |
| if not text: | |
| raise ValueError( | |
| "Could not extract article. " | |
| "The website may block automatic access." | |
| ) | |
| title = ( | |
| metadata.title | |
| if metadata and metadata.title | |
| else text[:150] | |
| ) | |
| return title, text[:10000] | |
| # ===================================================== | |
| # 4. SEARCH GOOGLE NEWS RSS | |
| # ===================================================== | |
| def search_news(claim): | |
| rss_url = ( | |
| "https://news.google.com/rss/search?q=" | |
| + quote_plus(claim) | |
| + "&hl=en-IN&gl=IN&ceid=IN:en" | |
| ) | |
| response = requests.get( | |
| rss_url, | |
| headers=HEADERS, | |
| timeout=20 | |
| ) | |
| response.raise_for_status() | |
| feed = feedparser.parse(response.content) | |
| sources = [] | |
| seen = set() | |
| for entry in feed.entries[:30]: | |
| source_info = entry.get("source", {}) | |
| publisher = source_info.get( | |
| "title", "Unknown publisher" | |
| ) | |
| publisher_url = source_info.get("href", "") | |
| link = entry.get("link", "") | |
| domain = ( | |
| urlparse(publisher_url).netloc | |
| if publisher_url | |
| else urlparse(link).netloc | |
| ) | |
| domain = domain.lower().replace("www.", "") | |
| if not domain or domain in seen: | |
| continue | |
| if urlparse(link).scheme not in ["http", "https"]: | |
| continue | |
| seen.add(domain) | |
| summary = re.sub( | |
| r"<[^>]*>", " ", | |
| entry.get("summary", "") | |
| ) | |
| summary = html.unescape(summary) | |
| title = entry.get("title", "") | |
| evidence = title + ". " + summary | |
| sources.append({ | |
| "publisher": publisher, | |
| "domain": domain, | |
| "title": title, | |
| "link": link, | |
| "evidence": evidence[:1800] | |
| }) | |
| if len(sources) >= 8: | |
| break | |
| return sources | |
| # ===================================================== | |
| # 5. AI FACT CHECKING USING HUGGING FACE | |
| # ===================================================== | |
| def analyse_evidence(claim, sources): | |
| results = [] | |
| # Move the model to GPU only during this function. | |
| model.to("cuda") | |
| try: | |
| for source in sources: | |
| evidence = source["evidence"] | |
| # Premise = evidence | |
| # Hypothesis = news claim | |
| inputs = tokenizer( | |
| evidence, | |
| claim, | |
| return_tensors="pt", | |
| truncation=True, | |
| max_length=384 | |
| ) | |
| inputs = { | |
| key: value.to("cuda") | |
| for key, value in inputs.items() | |
| } | |
| with torch.inference_mode(): | |
| output = model(**inputs) | |
| probabilities = torch.softmax( | |
| output.logits, | |
| dim=-1 | |
| )[0] | |
| scores = probabilities.cpu().tolist() | |
| # Model label order: | |
| # 0 = contradiction | |
| # 1 = entailment | |
| # 2 = neutral | |
| contradiction = scores[0] | |
| support = scores[1] | |
| unclear = scores[2] | |
| if support >= 0.45 and support > contradiction: | |
| verdict = "Supports" | |
| confidence = support | |
| elif ( | |
| contradiction >= 0.45 | |
| and contradiction > support | |
| ): | |
| verdict = "Contradicts" | |
| confidence = contradiction | |
| else: | |
| verdict = "Unclear" | |
| confidence = unclear | |
| results.append({ | |
| **source, | |
| "verdict": verdict, | |
| "confidence": round(confidence * 100, 1) | |
| }) | |
| finally: | |
| # Return model to CPU after analysis. | |
| model.to("cpu") | |
| if torch.cuda.is_available(): | |
| torch.cuda.empty_cache() | |
| return results | |
| # ===================================================== | |
| # 6. CALCULATE FINAL VERDICT | |
| # ===================================================== | |
| def calculate_verdict(results): | |
| counts = { | |
| "Supporting": 0, | |
| "Contradicting": 0, | |
| "Unclear": 0 | |
| } | |
| for item in results: | |
| if item["verdict"] == "Supports": | |
| counts["Supporting"] += 1 | |
| elif item["verdict"] == "Contradicts": | |
| counts["Contradicting"] += 1 | |
| else: | |
| counts["Unclear"] += 1 | |
| total = len(results) | |
| if total == 0: | |
| return "NON-VERIFIABLE", { | |
| "Supporting": 0, | |
| "Contradicting": 0, | |
| "Unclear": 100 | |
| } | |
| percentages = { | |
| key: round(value / total * 100, 1) | |
| for key, value in counts.items() | |
| } | |
| if total < 3: | |
| verdict = "NON-VERIFIABLE" | |
| elif percentages["Supporting"] >= 60: | |
| verdict = "LIKELY TRUE" | |
| elif percentages["Contradicting"] >= 60: | |
| verdict = "LIKELY FALSE" | |
| else: | |
| verdict = "NON-VERIFIABLE" | |
| return verdict, percentages | |
| # ===================================================== | |
| # 7. CREATE PERCENTAGE GRAPH | |
| # ===================================================== | |
| def create_graph(percentages): | |
| df = pd.DataFrame({ | |
| "Category": list(percentages.keys()), | |
| "Percentage": list(percentages.values()) | |
| }) | |
| fig = px.bar( | |
| df, | |
| x="Category", | |
| y="Percentage", | |
| color="Category", | |
| text="Percentage", | |
| range_y=[0, 110], | |
| color_discrete_map={ | |
| "Supporting": "#22C55E", | |
| "Contradicting": "#EF4444", | |
| "Unclear": "#F59E0B" | |
| }, | |
| title="Evidence Distribution" | |
| ) | |
| fig.update_traces( | |
| texttemplate="%{text}%", | |
| textposition="outside" | |
| ) | |
| fig.update_layout( | |
| template="plotly_dark", | |
| paper_bgcolor="#111827", | |
| plot_bgcolor="#111827", | |
| font_color="white", | |
| showlegend=False, | |
| yaxis_title="Percentage of sources", | |
| xaxis_title="" | |
| ) | |
| return fig | |
| # ===================================================== | |
| # 8. DISPLAY SOURCE CARDS | |
| # ===================================================== | |
| def create_source_cards(results): | |
| if not results: | |
| return "<h3>No matching sources found.</h3>" | |
| cards = "" | |
| for item in results: | |
| if item["verdict"] == "Supports": | |
| color = "#22C55E" | |
| elif item["verdict"] == "Contradicts": | |
| color = "#EF4444" | |
| else: | |
| color = "#F59E0B" | |
| publisher = html.escape(item["publisher"]) | |
| title = html.escape(item["title"]) | |
| domain = html.escape(item["domain"]) | |
| link = html.escape(item["link"], quote=True) | |
| cards += f""" | |
| <div style=" | |
| background:#1F2937; | |
| border:1px solid #374151; | |
| border-left:5px solid {color}; | |
| border-radius:14px; | |
| padding:18px; | |
| margin-bottom:14px; | |
| "> | |
| <div style=" | |
| display:flex; | |
| justify-content:space-between; | |
| flex-wrap:wrap; | |
| gap:10px; | |
| "> | |
| <b style="color:white;font-size:16px"> | |
| {publisher} | |
| </b> | |
| <b style="color:{color}"> | |
| {item['verdict'].upper()} | |
| </b> | |
| </div> | |
| <p style="color:#D1D5DB"> | |
| {title} | |
| </p> | |
| <small style="color:#9CA3AF"> | |
| {domain} | | |
| Model confidence: {item['confidence']}% | |
| </small> | |
| <br><br> | |
| <a href="{link}" | |
| target="_blank" | |
| rel="noopener noreferrer" | |
| style="color:#60A5FA"> | |
| Read original report β | |
| </a> | |
| </div> | |
| """ | |
| return cards | |
| # ===================================================== | |
| # 9. MAIN NEWS ANALYSIS | |
| # ===================================================== | |
| def run_analysis(url, custom_claim, progress=gr.Progress()): | |
| try: | |
| if not url or not url.strip(): | |
| raise ValueError( | |
| "Please enter a news article URL." | |
| ) | |
| progress(0.1, desc="Extracting news article...") | |
| title, article = extract_article(url) | |
| claim = ( | |
| custom_claim.strip() | |
| if custom_claim and custom_claim.strip() | |
| else title | |
| ) | |
| progress(0.3, desc="Searching news sources...") | |
| sources = search_news(claim) | |
| if not sources: | |
| percentages = { | |
| "Supporting": 0, | |
| "Contradicting": 0, | |
| "Unclear": 100 | |
| } | |
| return ( | |
| f"## π° {title}\n\n{article[:1500]}", | |
| "<h2 style='color:#F59E0B'>NON-VERIFIABLE</h2>" | |
| "<p>No matching independent reports were found.</p>", | |
| create_graph(percentages), | |
| "<p>No sources found.</p>", | |
| "Insufficient evidence to verify this news." | |
| ) | |
| progress( | |
| 0.5, | |
| desc="AI is comparing evidence from publishers..." | |
| ) | |
| results = analyse_evidence( | |
| claim, | |
| sources | |
| ) | |
| progress(0.85, desc="Generating final report...") | |
| verdict, percentages = calculate_verdict(results) | |
| graph = create_graph(percentages) | |
| source_cards = create_source_cards(results) | |
| if verdict == "LIKELY TRUE": | |
| color = "#22C55E" | |
| explanation = "Most collected sources support the claim." | |
| elif verdict == "LIKELY FALSE": | |
| color = "#EF4444" | |
| explanation = "Most collected sources contradict the claim." | |
| else: | |
| color = "#F59E0B" | |
| explanation = "Available evidence is insufficient or mixed." | |
| report = f""" | |
| <div style=" | |
| background:#111827; | |
| border:1px solid #374151; | |
| padding:24px; | |
| border-radius:16px; | |
| "> | |
| <p style="color:#9CA3AF"> | |
| FINAL VERDICT | |
| </p> | |
| <h1 style=" | |
| color:{color}; | |
| font-size:32px; | |
| "> | |
| {verdict} | |
| </h1> | |
| <p style="color:#D1D5DB"> | |
| {explanation} | |
| </p> | |
| <hr style="border-color:#374151"> | |
| <div style=" | |
| display:flex; | |
| justify-content:space-around; | |
| flex-wrap:wrap; | |
| gap:18px; | |
| "> | |
| <div> | |
| <h2 style="color:#22C55E"> | |
| {percentages['Supporting']}% | |
| </h2> | |
| <small>Supporting</small> | |
| </div> | |
| <div> | |
| <h2 style="color:#EF4444"> | |
| {percentages['Contradicting']}% | |
| </h2> | |
| <small>Contradicting</small> | |
| </div> | |
| <div> | |
| <h2 style="color:#F59E0B"> | |
| {percentages['Unclear']}% | |
| </h2> | |
| <small>Unclear</small> | |
| </div> | |
| </div> | |
| </div> | |
| """ | |
| summary = f""" | |
| ### AI Analysis Report | |
| **Claim analysed:** {claim} | |
| **Sources collected:** {len(results)} | |
| **AI model:** DeBERTa Natural Language Inference | |
| **Evidence distribution:** | |
| - Supporting: {percentages['Supporting']}% | |
| - Contradicting: {percentages['Contradicting']}% | |
| - Unclear: {percentages['Unclear']}% | |
| ### Important limitations | |
| The percentages represent the distribution of source assessments, | |
| NOT the probability that the news is true. | |
| The system searches Google News RSS and does not cover | |
| the entire internet. | |
| Publishers may repeat the same original report, so their | |
| coverage is not necessarily independent. | |
| AI predictions can be incorrect. Always check the | |
| original reports before accepting a verdict. | |
| """ | |
| progress(1.0, desc="Verification complete!") | |
| return ( | |
| f"## π° {title}\n\n{article[:1800]}", | |
| report, | |
| graph, | |
| source_cards, | |
| summary | |
| ) | |
| except Exception as error: | |
| error_message = html.escape(str(error)) | |
| return ( | |
| "## Article Analysis", | |
| f""" | |
| <h2 style="color:#F59E0B"> | |
| NON-VERIFIABLE | |
| </h2> | |
| <p>{error_message}</p> | |
| """, | |
| create_graph({ | |
| "Supporting": 0, | |
| "Contradicting": 0, | |
| "Unclear": 100 | |
| }), | |
| "<p>Source information unavailable.</p>", | |
| "Please check the URL and try again." | |
| ) | |
| # ===================================================== | |
| # 10. GRADIO DESIGN | |
| # ===================================================== | |
| CUSTOM_CSS = """ | |
| .gradio-container { | |
| max-width: 1150px !important; | |
| margin: auto !important; | |
| } | |
| #analyze-button { | |
| background: linear-gradient(90deg,#2563EB,#7C3AED); | |
| color: white; | |
| border: none; | |
| } | |
| #main-header { | |
| text-align: center; | |
| padding: 25px 10px; | |
| } | |
| #main-header h1 { | |
| font-size: 42px; | |
| background: linear-gradient(90deg,#60A5FA,#A78BFA); | |
| -webkit-background-clip: text; | |
| color: transparent; | |
| } | |
| """ | |
| with gr.Blocks( | |
| theme=gr.themes.Soft( | |
| primary_hue="blue", | |
| secondary_hue="purple", | |
| neutral_hue="slate" | |
| ), | |
| css=CUSTOM_CSS, | |
| title="TruthLens AI" | |
| ) as demo: | |
| # HEADER | |
| gr.HTML(""" | |
| <div id="main-header"> | |
| <div style="font-size:48px"> | |
| π | |
| </div> | |
| <h1> | |
| TRUTHLENS AI | |
| </h1> | |
| <p style=" | |
| color:#94A3B8; | |
| font-size:17px; | |
| "> | |
| BEYOND HEADLINES. TOWARDS TRUTH. | |
| </p> | |
| <p style="color:#64748B"> | |
| AI-powered multi-source news verification | |
| </p> | |
| </div> | |
| """) | |
| # INPUT AREA | |
| with gr.Group(): | |
| gr.Markdown("## π Verify a News Article") | |
| url_input = gr.Textbox( | |
| label="News Article URL", | |
| placeholder="Paste your news article link here..." | |
| ) | |
| claim_input = gr.Textbox( | |
| label="Specific claim (optional)", | |
| placeholder="Enter a specific statement to verify, or leave blank to use the headline.", | |
| lines=2 | |
| ) | |
| analyze_button = gr.Button( | |
| "π ANALYSE NEWS", | |
| variant="primary", | |
| elem_id="analyze-button" | |
| ) | |
| gr.Markdown("---") | |
| # ARTICLE | |
| article_output = gr.Markdown( | |
| label="Extracted News Article" | |
| ) | |
| # DASHBOARD | |
| gr.Markdown("## π Verification Dashboard") | |
| verdict_output = gr.HTML() | |
| graph_output = gr.Plot( | |
| label="Evidence Percentage Graph" | |
| ) | |
| # SOURCES | |
| gr.Markdown("## π News Sources") | |
| source_output = gr.HTML() | |
| # AI REPORT | |
| gr.Markdown("## π§ AI Analysis Report") | |
| summary_output = gr.Markdown() | |
| # FOOTER | |
| gr.HTML(""" | |
| <div style=" | |
| text-align:center; | |
| padding:25px; | |
| color:#64748B; | |
| "> | |
| <b>TRUTHLENS AI</b> | |
| <p> | |
| An educational artificial intelligence project. | |
| </p> | |
| <small> | |
| AI-assisted results are not guaranteed factual conclusions. | |
| </small> | |
| </div> | |
| """) | |
| # BUTTON ACTION | |
| analyze_button.click( | |
| fn=run_analysis, | |
| inputs=[ | |
| url_input, | |
| claim_input | |
| ], | |
| outputs=[ | |
| article_output, | |
| verdict_output, | |
| graph_output, | |
| source_output, | |
| summary_output | |
| ] | |
| ) | |
| demo.queue().launch() |