Update app.py

app.py

@@ -1,355 +1,245 @@
 import os
-import threading
-from flask import Flask, render_template, request, jsonify
-from rss_processor import fetch_rss_feeds, process_and_store_articles, vector_db, download_from_hf_hub, upload_to_hf_hub, clean_text
-import logging
-import time
-from datetime import datetime
-import hashlib
-import glob
+import feedparser
 from langchain.vectorstores import Chroma
 from langchain.embeddings import HuggingFaceEmbeddings
-
-app = Flask(__name__)
+from langchain.docstore.document import Document
+import logging
+from huggingface_hub import HfApi, login, snapshot_download
+import shutil
+import rss_feeds
+from datetime import datetime, date
+import dateutil.parser
+import hashlib
+import re
 
 # Setup logging
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
-# Global flag to track background loading
-loading_complete = True  # Start as True to allow initial rendering
-last_update_time = time.time()
-last_data_hash = None  # Track the hash of the last data to detect changes
-
-def load_feeds_in_background():
-    global loading_complete, last_update_time
-    try:
-        logger.info("Starting background RSS feed fetch")
-        articles = fetch_rss_feeds()
-        logger.info(f"Fetched {len(articles)} articles")
-        process_and_store_articles(articles)
-        last_update_time = time.time()
-        logger.info("Background feed processing complete")
-        upload_to_hf_hub()
-    except Exception as e:
-        logger.error(f"Error in background feed loading: {e}")
-    finally:
-        loading_complete = True
-
-def get_all_docs_from_dbs():
-    """Aggregate documents and metadata from all Chroma DB folders."""
-    all_docs = {'documents': [], 'metadatas': []}
-    seen_ids = set()
-
-    for db_path in glob.glob("chroma_db*"):
-        if not os.path.isdir(db_path):
-            continue
-        try:
-            temp_vector_db = Chroma(
-                persist_directory=db_path,
-                embedding_function=HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2"),
-                collection_name="news_articles"
-            )
-            db_data = temp_vector_db.get(include=['documents', 'metadatas'])
-            if db_data.get('documents') and db_data.get('metadatas'):
-                for doc, meta in zip(db_data['documents'], db_data['metadatas']):
-                    doc_id = f"{meta.get('title', 'No Title')}|{meta.get('link', '')}|{meta.get('published', 'Unknown Date')}"
-                    if doc_id not in seen_ids:
-                        seen_ids.add(doc_id)
-                        all_docs['documents'].append(doc)
-                        all_docs['metadatas'].append(meta)
-        except Exception as e:
-            logger.error(f"Error loading DB {db_path}: {e}")
-    
-    return all_docs
-
-def compute_data_hash(categorized_articles):
-    """Compute a hash of the current articles to detect changes."""
-    if not categorized_articles:
+# Constants
+MAX_ARTICLES_PER_FEED = 10
+RSS_FEEDS = rss_feeds.RSS_FEEDS
+COLLECTION_NAME = "news_articles"
+HF_API_TOKEN = os.getenv("DEMO_HF_API_TOKEN", "YOUR_HF_API_TOKEN")
+REPO_ID = "broadfield-dev/news-rag-db"
+
+# Initialize Hugging Face API
+login(token=HF_API_TOKEN)
+hf_api = HfApi()
+
+def get_embedding_model():
+    """Returns a singleton instance of the embedding model to avoid reloading."""
+    if not hasattr(get_embedding_model, "model"):
+        get_embedding_model.model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+    return get_embedding_model.model
+
+def get_daily_db_dir():
+    """Returns the path for today's Chroma DB."""
+    return f"chroma_db_{date.today().isoformat()}"
+
+def clean_text(text):
+    """Clean text by removing HTML tags and extra whitespace."""
+    if not text or not isinstance(text, str):
         return ""
-    # Create a sorted string representation of the articles for consistent hashing
-    data_str = ""
-    for cat, articles in sorted(categorized_articles.items()):
-        for article in sorted(articles, key=lambda x: x["published"]):
-            data_str += f"{cat}|{article['title']}|{article['link']}|{article['published']}|"
-    return hashlib.sha256(data_str.encode('utf-8')).hexdigest()
-
-@app.route('/')
-def index():
-    global loading_complete, last_update_time, last_data_hash
-
-    # Check if any DB exists; if not, download from Hugging Face
-    db_exists = any(os.path.exists(db_path) for db_path in glob.glob("chroma_db*"))
-    if not db_exists:
-        logger.info("No Chroma DB found, downloading from Hugging Face Hub...")
-        download_from_hf_hub()
-
-    # Start background RSS feed update
-    loading_complete = False
-    threading.Thread(target=load_feeds_in_background, daemon=True).start()
-
-    # Load existing data immediately
-    try:
-        all_docs = get_all_docs_from_dbs()
-        total_docs = len(all_docs['documents'])
-        logger.info(f"Total articles across all DBs at startup: {total_docs}")
-        if not all_docs.get('metadatas'):
-            logger.info("No articles in any DB yet")
-            return render_template("index.html", categorized_articles={}, has_articles=False, loading=True)
-
-        # Process and categorize articles with deduplication
-        enriched_articles = []
-        seen_keys = set()
-        for doc, meta in zip(all_docs['documents'], all_docs['metadatas']):
-            if not meta:
-                continue
-            title = meta.get("title", "No Title")
-            link = meta.get("link", "")
-            description = meta.get("original_description", "No Description")
-            published = meta.get("published", "Unknown Date").strip()
-
-            title = clean_text(title)
-            link = clean_text(link)
-            description = clean_text(description)
-
-            description_hash = hashlib.sha256(description.encode('utf-8')).hexdigest()
-            key = f"{title}|{link}|{published}|{description_hash}"
-            if key not in seen_keys:
-                seen_keys.add(key)
-                try:
-                    published = datetime.strptime(published, "%Y-%m-%d %H:%M:%S").isoformat() if "Unknown" not in published else published
-                except (ValueError, TypeError):
-                    published = "1970-01-01T00:00:00"
-                enriched_articles.append({
-                    "title": title,
-                    "link": link,
-                    "description": description,
-                    "category": meta.get("category", "Uncategorized"),
-                    "published": published,
-                    "image": meta.get("image", "svg"),
-                })
-
-        enriched_articles.sort(key=lambda x: x["published"], reverse=True)
-
-        categorized_articles = {}
-        for article in enriched_articles:
-            cat = article["category"]
-            if cat not in categorized_articles:
-                categorized_articles[cat] = []
-            categorized_articles[cat].append(article)
-
-        categorized_articles = dict(sorted(categorized_articles.items(), key=lambda x: x[0].lower()))
-
-        for cat in categorized_articles:
-            categorized_articles[cat] = sorted(categorized_articles[cat], key=lambda x: x["published"], reverse=True)[:10]
-            if len(categorized_articles[cat]) >= 2:
-                logger.debug(f"Category {cat} top 2: {categorized_articles[cat][0]['title']} | {categorized_articles[cat][1]['title']}")
-
-        # Compute initial data hash
-        last_data_hash = compute_data_hash(categorized_articles)
-
-        logger.info(f"Displaying articles at startup: {sum(len(articles) for articles in categorized_articles.values())} total")
-        return render_template("index.html", 
-                              categorized_articles=categorized_articles, 
-                              has_articles=True, 
-                              loading=True)
-    except Exception as e:
-        logger.error(f"Error retrieving articles at startup: {e}")
-        return render_template("index.html", categorized_articles={}, has_articles=False, loading=True)
-
-@app.route('/search', methods=['POST'])
-def search():
-    query = request.form.get('search')
-    if not query:
-        logger.info("Empty search query received")
-        return jsonify({"categorized_articles": {}, "has_articles": False, "loading": False})
-
-    try:
-        logger.info(f"Searching for: {query}")
-        all_docs = get_all_docs_from_dbs()
-        if not all_docs.get('metadatas'):
-            return jsonify({"categorized_articles": {}, "has_articles": False, "loading": False})
-
-        enriched_articles = []
-        seen_keys = set()
-        for doc, meta in zip(all_docs['documents'], all_docs['metadatas']):
-            if not meta:
+    text = re.sub(r'<.*?>', '', text)
+    text = ' '.join(text.split())
+    return text.strip().lower()
+
+def fetch_rss_feeds():
+    articles = []
+    seen_keys = set()
+    for feed_url in RSS_FEEDS:
+        try:
+            logger.info(f"Fetching {feed_url}")
+            feed = feedparser.parse(feed_url)
+            if feed.bozo:
+                logger.warning(f"Parse error for {feed_url}: {feed.bozo_exception}")
                 continue
-            title = meta.get("title", "No Title")
-            link = meta.get("link", "")
-            description = meta.get("original_description", "No Description")
-            published = meta.get("published", "Unknown Date").strip()
+            article_count = 0
+            for entry in feed.entries:
+                if article_count >= MAX_ARTICLES_PER_FEED:
+                    break
+                title = entry.get("title", "No Title")
+                link = entry.get("link", "")
+                description = entry.get("summary", entry.get("description", ""))
+                
+                title = clean_text(title)
+                link = clean_text(link)
+                description = clean_text(description)
+
+                published = "Unknown Date"
+                for date_field in ["published", "updated", "created", "pubDate"]:
+                    if date_field in entry:
+                        try:
+                            parsed_date = dateutil.parser.parse(entry[date_field])
+                            published = parsed_date.strftime("%Y-%m-%d %H:%M:%S")
+                            break
+                        except (ValueError, TypeError) as e:
+                            logger.debug(f"Failed to parse {date_field} '{entry[date_field]}': {e}")
+                            continue
 
-            title = clean_text(title)
-            link = clean_text(link)
-            description = clean_text(description)
-
-            if query.lower() in title or query.lower() in description:
                 description_hash = hashlib.sha256(description.encode('utf-8')).hexdigest()
                 key = f"{title}|{link}|{published}|{description_hash}"
                 if key not in seen_keys:
                     seen_keys.add(key)
-                    enriched_articles.append({
+                    image = "svg"
+                    for img_source in [
+                        lambda e: clean_text(e.get("media_content", [{}])[0].get("url")) if e.get("media_content") else "",
+                        lambda e: clean_text(e.get("media_thumbnail", [{}])[0].get("url")) if e.get("media_thumbnail") else "",
+                        lambda e: clean_text(e.get("enclosure", {}).get("url")) if e.get("enclosure") else "",
+                        lambda e: clean_text(next((lnk.get("href") for lnk in e.get("links", []) if lnk.get("type", "").startswith("image")), "")),
+                    ]:
+                        try:
+                            img = img_source(entry)
+                            if img and img.strip():
+                                image = img
+                                break
+                        except (IndexError, AttributeError, TypeError):
+                            continue
+
+                    articles.append({
                         "title": title,
                         "link": link,
                         "description": description,
-                        "category": meta.get("category", "Uncategorized"),
                         "published": published,
-                        "image": meta.get("image", "svg"),
+                        "category": categorize_feed(feed_url),
+                        "image": image,
                     })
-
-        categorized_articles = {}
-        for article in enriched_articles:
-            cat = article["category"]
-            categorized_articles.setdefault(cat, []).append(article)
-
-        logger.info(f"Found {len(enriched_articles)} unique articles across {len(categorized_articles)} categories")
-        return jsonify({
-            "categorized_articles": categorized_articles,
-            "has_articles": bool(enriched_articles),
-            "loading": False
-        })
-    except Exception as e:
-        logger.error(f"Search error: {e}")
-        return jsonify({"categorized_articles": {}, "has_articles": False, "loading": False}), 500
-
-@app.route('/check_loading')
-def check_loading():
-    global loading_complete, last_update_time
-    if loading_complete:
-        return jsonify({"status": "complete", "last_update": last_update_time})
-    return jsonify({"status": "loading"}), 202
-
-@app.route('/get_updates')
-def get_updates():
-    global last_update_time, last_data_hash
+                    article_count += 1
+        except Exception as e:
+            logger.error(f"Error fetching {feed_url}: {e}")
+    logger.info(f"Total articles fetched: {len(articles)}")
+    return articles
+
+def categorize_feed(url):
+    """Categorize an RSS feed based on its URL."""
+    if not url or not isinstance(url, str):
+        logger.warning(f"Invalid URL provided for categorization: {url}")
+        return "Uncategorized"
+
+    url = url.lower().strip()
+
+    logger.debug(f"Categorizing URL: {url}")
+
+    if any(keyword in url for keyword in ["nature", "science.org", "arxiv.org", "plos.org", "annualreviews.org", "journals.uchicago.edu", "jneurosci.org", "cell.com", "nejm.org", "lancet.com"]):
+        return "Academic Papers"
+    elif any(keyword in url for keyword in ["reuters.com/business", "bloomberg.com", "ft.com", "marketwatch.com", "cnbc.com", "foxbusiness.com", "wsj.com", "bworldonline.com", "economist.com", "forbes.com"]):
+        return "Business"
+    elif any(keyword in url for keyword in ["investing.com", "cnbc.com/market", "marketwatch.com/market", "fool.co.uk", "zacks.com", "seekingalpha.com", "barrons.com", "yahoofinance.com"]):
+        return "Stocks & Markets"
+    elif any(keyword in url for keyword in ["whitehouse.gov", "state.gov", "commerce.gov", "transportation.gov", "ed.gov", "dol.gov", "justice.gov", "federalreserve.gov", "occ.gov", "sec.gov", "bls.gov", "usda.gov", "gao.gov", "cbo.gov", "fema.gov", "defense.gov", "hhs.gov", "energy.gov", "interior.gov"]):
+        return "Federal Government"
+    elif any(keyword in url for keyword in ["weather.gov", "metoffice.gov.uk", "accuweather.com", "weatherunderground.com", "noaa.gov", "wunderground.com", "climate.gov", "ecmwf.int", "bom.gov.au"]):
+        return "Weather"
+    elif any(keyword in url for keyword in ["data.worldbank.org", "imf.org", "un.org", "oecd.org", "statista.com", "kff.org", "who.int", "cdc.gov", "bea.gov", "census.gov", "fdic.gov"]):
+        return "Data & Statistics"
+    elif any(keyword in url for keyword in ["nasa", "spaceweatherlive", "space", "universetoday", "skyandtelescope", "esa"]):
+        return "Space"
+    elif any(keyword in url for keyword in ["sciencedaily", "quantamagazine", "smithsonianmag", "popsci", "discovermagazine", "scientificamerican", "newscientist", "livescience", "atlasobscura"]):
+        return "Science"
+    elif any(keyword in url for keyword in ["wired", "techcrunch", "arstechnica", "gizmodo", "theverge"]):
+        return "Tech"
+    elif any(keyword in url for keyword in ["horoscope", "astrostyle"]):
+        return "Astrology"
+    elif any(keyword in url for keyword in ["cnn_allpolitics", "bbci.co.uk/news/politics", "reuters.com/arc/outboundfeeds/newsletter-politics", "politico.com/rss/politics", "thehill"]):
+        return "Politics"
+    elif any(keyword in url for keyword in ["weather", "swpc.noaa.gov", "foxweather"]):
+        return "Earth Weather"
+    elif "vogue" in url:
+        return "Lifestyle"
+    elif any(keyword in url for keyword in ["phys.org", "aps.org", "physicsworld"]):
+        return "Physics"
+    else:
+        logger.warning(f"No matching category found for URL: {url}")
+        return "Uncategorized"
+
+def process_and_store_articles(articles):
+    db_path = get_daily_db_dir()
+    vector_db = Chroma(
+        persist_directory=db_path,
+        embedding_function=get_embedding_model(),
+        collection_name=COLLECTION_NAME
+    )
+    
     try:
-        all_docs = get_all_docs_from_dbs()
-        if not all_docs.get('metadatas'):
-            return jsonify({"articles": [], "last_update": last_update_time, "has_updates": False})
-
-        enriched_articles = []
-        seen_keys = set()
-        for doc, meta in zip(all_docs['documents'], all_docs['metadatas']):
-            if not meta:
-                continue
-            title = meta.get("title", "No Title")
-            link = meta.get("link", "")
-            description = meta.get("original_description", "No Description")
-            published = meta.get("published", "Unknown Date").strip()
-
-            title = clean_text(title)
-            link = clean_text(link)
-            description = clean_text(description)
+        existing_ids = set(vector_db.get(include=[])["ids"])
+    except Exception:
+        existing_ids = set()
 
+    docs_to_add = []
+    ids_to_add = []
+    
+    for article in articles:
+        try:
+            title = clean_text(article["title"])
+            link = clean_text(article["link"])
+            description = clean_text(article["description"])
+            published = article["published"]
             description_hash = hashlib.sha256(description.encode('utf-8')).hexdigest()
-            key = f"{title}|{link}|{published}|{description_hash}"
-            if key not in seen_keys:
-                seen_keys.add(key)
-                try:
-                    published = datetime.strptime(published, "%Y-%m-%d %H:%M:%S").isoformat() if "Unknown" not in published else published
-                except (ValueError, TypeError):
-                    published = "1970-01-01T00:00:00"
-                enriched_articles.append({
-                    "title": title,
-                    "link": link,
-                    "description": description,
-                    "category": meta.get("category", "Uncategorized"),
-                    "published": published,
-                    "image": meta.get("image", "svg"),
-                })
-
-        enriched_articles.sort(key=lambda x: x["published"], reverse=True)
-        categorized_articles = {}
-        for article in enriched_articles:
-            cat = article["category"]
-            if cat not in categorized_articles:
-                categorized_articles[cat] = []
-            key = f"{article['title']}|{article['link']}|{article['published']}"
-            if key not in [f"{a['title']}|{a['link']}|{a['published']}" for a in categorized_articles[cat]]:
-                categorized_articles[cat].append(article)
-
-        for cat in categorized_articles:
-            unique_articles = []
-            seen_cat_keys = set()
-            for article in sorted(categorized_articles[cat], key=lambda x: x["published"], reverse=True):
-                key = f"{clean_text(article['title'])}|{clean_text(article['link'])}|{article['published']}"
-                if key not in seen_cat_keys:
-                    seen_cat_keys.add(key)
-                    unique_articles.append(article)
-            categorized_articles[cat] = unique_articles[:10]
-
-        # Compute hash of new data
-        current_data_hash = compute_data_hash(categorized_articles)
-
-        # Compare with last data hash to determine if there are updates
-        has_updates = last_data_hash != current_data_hash
-        if has_updates:
-            logger.info("New RSS data detected, sending updates to frontend")
-            last_data_hash = current_data_hash
-            return jsonify({
-                "articles": categorized_articles,
-                "last_update": last_update_time,
-                "has_updates": True
-            })
-        else:
-            logger.info("No new RSS data, skipping update")
-            return jsonify({
-                "articles": {},
-                "last_update": last_update_time,
-                "has_updates": False
-            })
-    except Exception as e:
-        logger.error(f"Error fetching updates: {e}")
-        return jsonify({"articles": {}, "last_update": last_update_time, "has_updates": False}), 500
-
-@app.route('/get_all_articles/<category>')
-def get_all_articles(category):
-    try:
-        all_docs = get_all_docs_from_dbs()
-        if not all_docs.get('metadatas'):
-            return jsonify({"articles": [], "category": category})
-
-        enriched_articles = []
-        seen_keys = set()
-        for doc, meta in zip(all_docs['documents'], all_docs['metadatas']):
-            if not meta or meta.get("category") != category:
+            
+            doc_id = f"{title}|{link}|{published}|{description_hash}"
+            
+            if doc_id in existing_ids:
+                logger.debug(f"Skipping duplicate in DB {db_path}: {doc_id}")
                 continue
-            title = meta.get("title", "No Title")
-            link = meta.get("link", "")
-            description = meta.get("original_description", "No Description")
-            published = meta.get("published", "Unknown Date").strip()
 
-            title = clean_text(title)
-            link = clean_text(link)
-            description = clean_text(description)
-
-            description_hash = hashlib.sha256(description.encode('utf-8')).hexdigest()
-            key = f"{title}|{link}|{published}|{description_hash}"
-            if key not in seen_keys:
-                seen_keys.add(key)
-                try:
-                    published = datetime.strptime(published, "%Y-%m-%d %H:%M:%S").isoformat() if "Unknown" not in published else published
-                except (ValueError, TypeError):
-                    published = "1970-01-01T00:00:00"
-                enriched_articles.append({
-                    "title": title,
-                    "link": link,
-                    "description": description,
-                    "category": meta.get("category", "Uncategorized"),
-                    "published": published,
-                    "image": meta.get("image", "svg"),
-                })
+            metadata = {
+                "title": article["title"],
+                "link": article["link"],
+                "original_description": article["description"],
+                "published": article["published"],
+                "category": article["category"],
+                "image": article["image"],
+            }
+            doc = Document(page_content=description, metadata=metadata)
+            docs_to_add.append(doc)
+            ids_to_add.append(doc_id)
+            existing_ids.add(doc_id)
+        except Exception as e:
+            logger.error(f"Error processing article {article.get('title', 'N/A')}: {e}")
+    
+    if docs_to_add:
+        try:
+            vector_db.add_documents(documents=docs_to_add, ids=ids_to_add)
+            vector_db.persist()
+            logger.info(f"Added {len(docs_to_add)} new articles to DB {db_path}. Total in DB: {vector_db._collection.count()}")
+        except Exception as e:
+            logger.error(f"Error storing articles in {db_path}: {e}")
 
-        enriched_articles.sort(key=lambda x: x["published"], reverse=True)
-        return jsonify({"articles": enriched_articles, "category": category})
+def download_from_hf_hub():
+    try:
+        hf_api.create_repo(repo_id=REPO_ID, repo_type="dataset", exist_ok=True, token=HF_API_TOKEN)
+        logger.info(f"Downloading all DBs from {REPO_ID}...")
+        snapshot_download(
+            repo_id=REPO_ID,
+            repo_type="dataset",
+            local_dir=".",
+            local_dir_use_symlinks=False,
+            allow_patterns="chroma_db_*/**",
+            token=HF_API_TOKEN
+        )
+        logger.info("Finished downloading DBs.")
     except Exception as e:
-        logger.error(f"Error fetching all articles for category {category}: {e}")
-        return jsonify({"articles": [], "category": category}), 500
+        logger.error(f"Error downloading from Hugging Face Hub: {e}")
 
-@app.route('/card')
-def card_load():
-    return render_template("card.html")
+def upload_to_hf_hub():
+    db_path = get_daily_db_dir()
+    if os.path.exists(db_path):
+        try:
+            logger.info(f"Uploading updated Chroma DB '{db_path}' to {REPO_ID}...")
+            hf_api.upload_folder(
+                folder_path=db_path,
+                path_in_repo=db_path,
+                repo_id=REPO_ID,
+                repo_type="dataset",
+                token=HF_API_TOKEN
+            )
+            logger.info(f"Database folder '{db_path}' uploaded to: {REPO_ID}")
+        except Exception as e:
+            logger.error(f"Error uploading to Hugging Face Hub: {e}")
 
 if __name__ == "__main__":
-    app.run(host="0.0.0.0", port=7860)
+    download_from_hf_hub()
+    articles = fetch_rss_feeds()
+    process_and_store_articles(articles)
+    upload_to_hf_hub()