Initial project setup

.gitignore

@@ -0,0 +1,112 @@
+# .gitignore for DS Task AI News Project
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+### Environment ###
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Virtual environment
+pythonenv*
+
+### IDE ###
+# VS Code
+.vscode/
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+
+# PyCharm
+.idea/
+*.iml
+*.ipr
+*.iws
+
+### Data Files ###
+# Raw and processed news
+data/raw_news/
+data/processed_news/
+*.csv
+*.json
+*.parquet
+*.feather
+*.pkl
+*.pickle
+*.db
+*.sqlite
+
+# Vector database files
+*.faiss
+*.index
+*.bin
+*.vec
+
+### Logs ###
+*.log
+logs/
+
+### OS Generated ###
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+
+### Groq/Cohere Cache ###
+.cache/
+model_cache/
+
+### Test Files ###
+test_output/
+benchmark_results/
+
+### Documentation ###
+docs/_build/

backend/config.py

@@ -0,0 +1,13 @@
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+class Config:
+    COHERE_API_KEY = os.getenv("COHERE_API_KEY")
+    GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+    RSS_FEEDS = [
+        "http://rss.nytimes.com/services/xml/rss/nyt/Technology.xml",
+        "https://feeds.bbci.co.uk/news/technology/rss.xml"
+    ]
+    VECTOR_DB_PATH = "data/vector_db.index"

backend/embeddings.py

@@ -0,0 +1,8 @@
+import cohere
+from backend.config import Config
+
+co = cohere.Client(Config.COHERE_API_KEY)
+
+def get_embeddings(texts):
+    response = co.embed(texts=texts, model="embed-english-v3.0")
+    return response.embeddings

backend/main.py

@@ -0,0 +1,20 @@
+from fastapi import FastAPI
+from backend.news_fetcher import fetch_news
+from backend.recommender import recommend_similar
+from backend.config import Config
+
+app = FastAPI()
+
+@app.get("/fetch-news")
+async def get_latest_news():
+    all_news = []
+    for feed in Config.RSS_FEEDS:
+        all_news.extend(fetch_news(feed))
+    return {"news": all_news}
+
+
+@app.get("/recommend")
+async def recommend_news(article_id: str):
+    sample_text = "AI breakthroughs in 2024"
+    similar_ids = recommend_similar(sample_text)
+    return {"similar_articles": similar_ids}

backend/news_fetcher.py

@@ -0,0 +1,26 @@
+# backend/news_fetcher.py
+from datetime import datetime
+import feedparser
+
+def fetch_news(rss_url):
+    feed = feedparser.parse(rss_url)
+    articles = []
+    for entry in feed.entries:
+        try:
+            # Try parsing with timezone first
+            pub_date = datetime.strptime(entry.published, "%a, %d %b %Y %H:%M:%S %z")
+        except ValueError:
+            try:
+                # Fallback to GMT format without timezone
+                pub_date = datetime.strptime(entry.published, "%a, %d %b %Y %H:%M:%S %Z")
+            except ValueError:
+                # Final fallback - use current time if parsing fails
+                pub_date = datetime.now()
+        
+        articles.append({
+            "title": entry.title,
+            "content": entry.description,
+            "published": pub_date,
+            "source": rss_url
+        })
+    return articles

backend/recommender.py

@@ -0,0 +1,8 @@
+from backend.embeddings import get_embeddings
+from backend.vector_store import VectorDB
+
+db = VectorDB()
+
+def recommend_similar(article_text, top_k=3):
+    query_embed = get_embeddings([article_text])[0]
+    return db.search(query_embed, k=top_k)

backend/requirements.txt

@@ -0,0 +1,7 @@
+fastapi
+uvicorn
+feedparser
+cohere
+python-dotenv
+groq
+numpy

backend/vector_store.py

@@ -0,0 +1,14 @@
+import numpy as np
+import faiss
+from backend.config import Config
+
+class VectorDB:
+    def __init__(self):
+        self.index = faiss.IndexFlatL2(768)  # Cohere embedding dim
+        
+    def add_vectors(self, ids, embeddings):
+        self.index.add(np.array(embeddings).astype('float32'))
+    
+    def search(self, query_embedding, k=5):
+        distances, indices = self.index.search(np.array([query_embedding]), k)
+        return indices[0]