Update README and backend functionality for improved news application
- Enhanced README.md with a clearer project overview, features, technologies used, and installation instructions. - Updated vector dimension in config.py from 4096 to 1024 for Cohere embeddings. - Modified main.py to serve HTML responses for the home page, news fetching, and recommendations. - Improved error handling and ensured articles have links in the responses. - Cleaned up news_fetcher.py by removing unnecessary print statements. - Updated recommender.py to refine insights generation and summary extraction. - Added Jinja2 for templating and improved the project structure for better organization. - Included API documentation for better understanding of endpoints and usage.
This commit is contained in:
boladeE
+1
-1
@@ -26,7 +26,7 @@ RSS_FEEDS = [
|
||||
]
|
||||
|
||||
# Vector Database Settings
|
||||
VECTOR_DIMENSION = 4096 # Cohere embedding dimension
|
||||
VECTOR_DIMENSION = 1024 # Cohere embedding dimension
|
||||
TOP_K_RESULTS = 5
|
||||
|
||||
# Data Directories
|
||||
|
||||
+68
-21
@@ -1,5 +1,7 @@
|
||||
from fastapi import FastAPI, HTTPException
|
||||
from fastapi import FastAPI, HTTPException, Request
|
||||
from fastapi.middleware.cors import CORSMiddleware
|
||||
from fastapi.templating import Jinja2Templates
|
||||
from fastapi.responses import HTMLResponse
|
||||
from typing import List, Dict, Any
|
||||
import json
|
||||
import os
|
||||
@@ -12,6 +14,19 @@ from config import RAW_NEWS_DIR, PROCESSED_NEWS_DIR
|
||||
|
||||
app = FastAPI(title="DS Task AI News API")
|
||||
|
||||
# Configure templates
|
||||
templates = Jinja2Templates(directory="backend/templates")
|
||||
|
||||
# Add custom filters
|
||||
def from_json(value):
|
||||
"""Parse a JSON string into a Python object."""
|
||||
try:
|
||||
return json.loads(value)
|
||||
except (json.JSONDecodeError, TypeError):
|
||||
return None
|
||||
|
||||
templates.env.filters["from_json"] = from_json
|
||||
|
||||
# Add CORS middleware
|
||||
app.add_middleware(
|
||||
CORSMiddleware,
|
||||
@@ -27,34 +42,51 @@ embedding_generator = EmbeddingGenerator()
|
||||
vector_store = VectorStore()
|
||||
recommender = NewsRecommender()
|
||||
|
||||
@app.get("/")
|
||||
async def root():
|
||||
"""Root endpoint returning API information."""
|
||||
return {
|
||||
"name": "DS Task AI News API",
|
||||
"version": "1.0.0",
|
||||
"description": "AI-powered news retrieval and recommendation system"
|
||||
}
|
||||
@app.get("/", response_class=HTMLResponse)
|
||||
async def root(request: Request):
|
||||
"""Root endpoint returning the home page with links to other routes."""
|
||||
return templates.TemplateResponse(
|
||||
"home.html",
|
||||
{"request": request}
|
||||
)
|
||||
|
||||
@app.get("/fetch-news")
|
||||
async def fetch_news():
|
||||
@app.get("/fetch-news", response_class=HTMLResponse)
|
||||
async def fetch_news(request: Request):
|
||||
"""Fetch news from RSS feeds and store in vector database."""
|
||||
try:
|
||||
result = news_fetcher.process()
|
||||
if result["status"] == "error":
|
||||
raise HTTPException(status_code=404, detail=result["message"])
|
||||
|
||||
return result
|
||||
# Get the latest processed articles
|
||||
processed_files = sorted(os.listdir(PROCESSED_NEWS_DIR), reverse=True)
|
||||
if not processed_files:
|
||||
raise HTTPException(status_code=404, detail="No processed articles found")
|
||||
|
||||
latest_file = os.path.join(PROCESSED_NEWS_DIR, processed_files[0])
|
||||
with open(latest_file, 'r', encoding='utf-8') as f:
|
||||
articles = json.load(f)
|
||||
|
||||
# Ensure each article has a link
|
||||
for article in articles:
|
||||
if 'link' not in article or not article['link']:
|
||||
# If no link is available, use the article ID as a fallback
|
||||
article['link'] = f"/article/{article.get('id', '')}"
|
||||
|
||||
return templates.TemplateResponse(
|
||||
"news.html",
|
||||
{"request": request, "articles": articles}
|
||||
)
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
@app.get("/recommend-news")
|
||||
async def recommend_news(article_id: str = None, query: str = None):
|
||||
@app.get("/recommend-news", response_class=HTMLResponse)
|
||||
async def recommend_news(request: Request, article_id: str = None, query: str = None):
|
||||
"""Get news recommendations based on article ID or search query."""
|
||||
try:
|
||||
if article_id:
|
||||
# Get article from vector store
|
||||
article = vector_store.search_similar([0] * 4096, top_k=1) # Placeholder vector
|
||||
article = vector_store.search_similar([0] * 1024, top_k=1) # Placeholder vector with correct dimension
|
||||
if not article:
|
||||
raise HTTPException(status_code=404, detail="Article not found")
|
||||
|
||||
@@ -76,13 +108,23 @@ async def recommend_news(article_id: str = None, query: str = None):
|
||||
if not similar_articles:
|
||||
raise HTTPException(status_code=404, detail="No similar articles found")
|
||||
|
||||
# Ensure each article has a link
|
||||
for article in similar_articles:
|
||||
if 'link' not in article or not article['link']:
|
||||
# If no link is available, use the article ID as a fallback
|
||||
article['link'] = f"/article/{article.get('id', '')}"
|
||||
|
||||
# Generate insights for the articles
|
||||
insights = recommender.analyze_articles(similar_articles)
|
||||
|
||||
return {
|
||||
"articles": similar_articles,
|
||||
"insights": insights
|
||||
}
|
||||
return templates.TemplateResponse(
|
||||
"recommendations.html",
|
||||
{
|
||||
"request": request,
|
||||
"articles": similar_articles,
|
||||
"insights": insights
|
||||
}
|
||||
)
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
@@ -91,12 +133,17 @@ async def get_article(article_id: str):
|
||||
"""Get a specific article and its summary."""
|
||||
try:
|
||||
# Search for the article
|
||||
articles = vector_store.search_similar([0] * 4096, top_k=1) # Placeholder vector
|
||||
articles = vector_store.search_similar([0] * 1024, top_k=1) # Placeholder vector with correct dimension
|
||||
if not articles:
|
||||
raise HTTPException(status_code=404, detail="Article not found")
|
||||
|
||||
article = articles[0]
|
||||
|
||||
# Ensure the article has a link
|
||||
if 'link' not in article or not article['link']:
|
||||
# If no link is available, use the article ID as a fallback
|
||||
article['link'] = f"/article/{article.get('id', '')}"
|
||||
|
||||
# Generate summary
|
||||
summary = recommender.generate_summary(article)
|
||||
|
||||
@@ -109,4 +156,4 @@ async def get_article(article_id: str):
|
||||
|
||||
if __name__ == "__main__":
|
||||
import uvicorn
|
||||
uvicorn.run(app, host="0.0.0.0", port=8000)
|
||||
uvicorn.run(app, host="localhost", port=8000)
|
||||
|
||||
@@ -174,5 +174,3 @@ class NewsFetcher:
|
||||
logger.info("News processing pipeline completed with status: %s", result["status"])
|
||||
return result
|
||||
|
||||
news_fetcher = NewsFetcher()
|
||||
print(news_fetcher.process())
|
||||
|
||||
+28
-6
@@ -1,6 +1,7 @@
|
||||
from groq import Groq
|
||||
from typing import List, Dict, Any
|
||||
from config import GROQ_API_KEY
|
||||
import json
|
||||
|
||||
class NewsRecommender:
|
||||
def __init__(self):
|
||||
@@ -11,7 +12,7 @@ class NewsRecommender:
|
||||
try:
|
||||
# Prepare the prompt
|
||||
articles_text = "\n\n".join([
|
||||
f"Title: {article['title']}\nContent: {article['content']}"
|
||||
f"Title: {article['title']}"
|
||||
for article in articles
|
||||
])
|
||||
|
||||
@@ -33,13 +34,34 @@ Format the response as a JSON with these keys: themes, insights, implications, r
|
||||
{"role": "system", "content": "You are a news analyst providing insights about technology and AI news."},
|
||||
{"role": "user", "content": prompt}
|
||||
],
|
||||
model="mixtral-8x7b-32768",
|
||||
model="llama3-70b-8192",
|
||||
temperature=0.7,
|
||||
max_tokens=1000
|
||||
max_tokens=500
|
||||
)
|
||||
|
||||
# Parse and return the analysis
|
||||
return completion.choices[0].message.content
|
||||
response_text = completion.choices[0].message.content
|
||||
|
||||
# Try to extract JSON from the response if it's wrapped in markdown code blocks
|
||||
if "```json" in response_text:
|
||||
json_str = response_text.split("```json")[1].split("```")[0].strip()
|
||||
try:
|
||||
return json.loads(json_str)
|
||||
except json.JSONDecodeError:
|
||||
pass
|
||||
elif "```" in response_text:
|
||||
json_str = response_text.split("```")[1].split("```")[0].strip()
|
||||
try:
|
||||
return json.loads(json_str)
|
||||
except json.JSONDecodeError:
|
||||
pass
|
||||
|
||||
# If we couldn't extract JSON, try to parse the entire response
|
||||
try:
|
||||
return json.loads(response_text)
|
||||
except json.JSONDecodeError:
|
||||
# If all parsing attempts fail, return the raw text
|
||||
return response_text
|
||||
except Exception as e:
|
||||
print(f"Error analyzing articles: {str(e)}")
|
||||
return {
|
||||
@@ -64,9 +86,9 @@ Please provide a concise summary focusing on the key points and implications."""
|
||||
{"role": "system", "content": "You are a news summarizer providing concise summaries of technology and AI news."},
|
||||
{"role": "user", "content": prompt}
|
||||
],
|
||||
model="mixtral-8x7b-32768",
|
||||
model="llama3-70b-8192",
|
||||
temperature=0.5,
|
||||
max_tokens=500
|
||||
max_tokens=250
|
||||
)
|
||||
|
||||
return completion.choices[0].message.content
|
||||
|
||||
@@ -9,3 +9,4 @@ pydantic==2.6.3
|
||||
python-multipart==0.0.9
|
||||
httpx==0.27.0
|
||||
beautifulsoup4==4.12.3
|
||||
jinja2==3.1.2
|
||||
|
||||
@@ -0,0 +1,34 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>{% block title %}DS Task AI News{% endblock %}</title>
|
||||
<link href="https://cdn.jsdelivr.net/npm/tailwindcss@2.2.19/dist/tailwind.min.css" rel="stylesheet">
|
||||
<style>
|
||||
.article-card {
|
||||
transition: transform 0.2s;
|
||||
}
|
||||
.article-card:hover {
|
||||
transform: translateY(-5px);
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
<body class="bg-gray-100 min-h-screen">
|
||||
<nav class="bg-blue-600 text-white p-4">
|
||||
<div class="container mx-auto">
|
||||
<h1 class="text-2xl font-bold">DS Task AI News</h1>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
<main class="container mx-auto px-4 py-8">
|
||||
{% block content %}{% endblock %}
|
||||
</main>
|
||||
|
||||
<footer class="bg-gray-800 text-white p-4 mt-8">
|
||||
<div class="container mx-auto text-center">
|
||||
<p>© 2024 DS Task AI News. All rights reserved.</p>
|
||||
</div>
|
||||
</footer>
|
||||
</body>
|
||||
</html>
|
||||
@@ -0,0 +1,54 @@
|
||||
{% extends "base.html" %}
|
||||
|
||||
{% block title %}Home - DS Task AI News{% endblock %}
|
||||
|
||||
{% block content %}
|
||||
<div class="max-w-4xl mx-auto">
|
||||
<div class="text-center mb-12">
|
||||
<h1 class="text-4xl font-bold text-gray-800 mb-4">Welcome to DS Task AI News</h1>
|
||||
<p class="text-xl text-gray-600">Your AI-powered news retrieval and recommendation system</p>
|
||||
</div>
|
||||
|
||||
<div class="grid grid-cols-1 md:grid-cols-2 gap-8">
|
||||
<!-- Fetch News Card -->
|
||||
<div class="bg-white rounded-lg shadow-md overflow-hidden hover:shadow-lg transition-shadow duration-300">
|
||||
<div class="p-6">
|
||||
<h2 class="text-2xl font-semibold text-gray-800 mb-4">Latest News</h2>
|
||||
<p class="text-gray-600 mb-6">View the latest news articles fetched from our RSS feeds.</p>
|
||||
<a href="/fetch-news" class="inline-block bg-blue-600 text-white px-6 py-3 rounded-md font-medium hover:bg-blue-700 transition-colors duration-300">
|
||||
View Latest News
|
||||
</a>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Recommend News Card -->
|
||||
<div class="bg-white rounded-lg shadow-md overflow-hidden hover:shadow-lg transition-shadow duration-300">
|
||||
<div class="p-6">
|
||||
<h2 class="text-2xl font-semibold text-gray-800 mb-4">News Recommendations</h2>
|
||||
<p class="text-gray-600 mb-6">Get personalized news recommendations based on your interests.</p>
|
||||
<div class="space-y-4">
|
||||
<a href="/recommend-news?query=technology" class="block bg-blue-600 text-white px-6 py-3 rounded-md font-medium hover:bg-blue-700 transition-colors duration-300 text-center">
|
||||
Technology News
|
||||
</a>
|
||||
<a href="/recommend-news?query=artificial intelligence" class="block bg-blue-600 text-white px-6 py-3 rounded-md font-medium hover:bg-blue-700 transition-colors duration-300 text-center">
|
||||
AI News
|
||||
</a>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="mt-12 bg-white rounded-lg shadow-md p-6">
|
||||
<h2 class="text-2xl font-semibold text-gray-800 mb-4">About This Application</h2>
|
||||
<p class="text-gray-600 mb-4">
|
||||
This application uses AI to fetch, process, and recommend news articles. It leverages:
|
||||
</p>
|
||||
<ul class="list-disc list-inside text-gray-600 space-y-2">
|
||||
<li>RSS feeds for news collection</li>
|
||||
<li>Cohere embeddings for semantic understanding</li>
|
||||
<li>Pinecone vector database for efficient retrieval</li>
|
||||
<li>AI-powered analysis for personalized recommendations</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
{% endblock %}
|
||||
@@ -0,0 +1,42 @@
|
||||
{% extends "base.html" %}
|
||||
|
||||
{% block title %}Latest News - DS Task AI News{% endblock %}
|
||||
|
||||
{% block content %}
|
||||
<div class="space-y-6">
|
||||
<h2 class="text-3xl font-bold text-gray-800 mb-6">Latest News Articles</h2>
|
||||
|
||||
<div class="grid grid-cols-1 md:grid-cols-2 lg:grid-cols-3 gap-6">
|
||||
{% for article in articles %}
|
||||
<article class="article-card bg-white rounded-lg shadow-md overflow-hidden">
|
||||
<div class="p-6">
|
||||
<h3 class="text-xl font-semibold text-gray-800 mb-2">
|
||||
<a href="{{ article.link }}" target="_blank" class="hover:text-blue-600">
|
||||
{{ article.title }}
|
||||
</a>
|
||||
</h3>
|
||||
<p class="text-gray-600 mb-4">{{ article.content[:200] }}...</p>
|
||||
<div class="flex justify-between items-center text-sm text-gray-500">
|
||||
<span>{{ article.source }}</span>
|
||||
<span>{{ article.published }}</span>
|
||||
</div>
|
||||
{% if article.categories %}
|
||||
<div class="mt-4 flex flex-wrap gap-2">
|
||||
{% for category in article.categories %}
|
||||
<span class="px-2 py-1 bg-blue-100 text-blue-800 rounded-full text-xs">
|
||||
{{ category }}
|
||||
</span>
|
||||
{% endfor %}
|
||||
</div>
|
||||
{% endif %}
|
||||
<div class="mt-4">
|
||||
<a href="{{ article.link }}" target="_blank" class="inline-block bg-blue-600 text-white px-4 py-2 rounded-md font-medium hover:bg-blue-700 transition-colors duration-300">
|
||||
Read More
|
||||
</a>
|
||||
</div>
|
||||
</div>
|
||||
</article>
|
||||
{% endfor %}
|
||||
</div>
|
||||
</div>
|
||||
{% endblock %}
|
||||
@@ -0,0 +1,157 @@
|
||||
{% extends "base.html" %}
|
||||
|
||||
{% block title %}Recommended News - DS Task AI News{% endblock %}
|
||||
|
||||
{% block content %}
|
||||
<div class="space-y-8">
|
||||
<div class="bg-white rounded-lg shadow-md p-6 mb-8">
|
||||
<h2 class="text-2xl font-bold text-gray-800 mb-4">AI Insights</h2>
|
||||
<div class="prose max-w-none">
|
||||
{% if insights %}
|
||||
{% if insights is string %}
|
||||
{# If insights is a string (JSON or markdown), try to parse it #}
|
||||
{% set insights_data = insights | from_json %}
|
||||
{% if insights_data %}
|
||||
<div class="space-y-6">
|
||||
{% if insights_data.themes %}
|
||||
<div>
|
||||
<h3 class="text-xl font-semibold text-gray-800 mb-2">Themes</h3>
|
||||
<ul class="list-disc list-inside space-y-1">
|
||||
{% for theme in insights_data.themes %}
|
||||
<li class="text-gray-700">{{ theme }}</li>
|
||||
{% endfor %}
|
||||
</ul>
|
||||
</div>
|
||||
{% endif %}
|
||||
|
||||
{% if insights_data.insights %}
|
||||
<div>
|
||||
<h3 class="text-xl font-semibold text-gray-800 mb-2">Key Insights</h3>
|
||||
<ul class="list-disc list-inside space-y-1">
|
||||
{% for insight in insights_data.insights %}
|
||||
<li class="text-gray-700">{{ insight }}</li>
|
||||
{% endfor %}
|
||||
</ul>
|
||||
</div>
|
||||
{% endif %}
|
||||
|
||||
{% if insights_data.implications %}
|
||||
<div>
|
||||
<h3 class="text-xl font-semibold text-gray-800 mb-2">Implications</h3>
|
||||
<ul class="list-disc list-inside space-y-1">
|
||||
{% for implication in insights_data.implications %}
|
||||
<li class="text-gray-700">{{ implication }}</li>
|
||||
{% endfor %}
|
||||
</ul>
|
||||
</div>
|
||||
{% endif %}
|
||||
|
||||
{% if insights_data.related_areas %}
|
||||
<div>
|
||||
<h3 class="text-xl font-semibold text-gray-800 mb-2">Related Areas</h3>
|
||||
<div class="flex flex-wrap gap-2">
|
||||
{% for area in insights_data.related_areas %}
|
||||
<span class="px-3 py-1 bg-blue-100 text-blue-800 rounded-full text-sm">
|
||||
{{ area }}
|
||||
</span>
|
||||
{% endfor %}
|
||||
</div>
|
||||
</div>
|
||||
{% endif %}
|
||||
</div>
|
||||
{% else %}
|
||||
{# If parsing failed, display the raw insights #}
|
||||
<div class="whitespace-pre-wrap">{{ insights }}</div>
|
||||
{% endif %}
|
||||
{% else %}
|
||||
{# If insights is already a dict/object #}
|
||||
<div class="space-y-6">
|
||||
{% if insights.themes %}
|
||||
<div>
|
||||
<h3 class="text-xl font-semibold text-gray-800 mb-2">Themes</h3>
|
||||
<ul class="list-disc list-inside space-y-1">
|
||||
{% for theme in insights.themes %}
|
||||
<li class="text-gray-700">{{ theme }}</li>
|
||||
{% endfor %}
|
||||
</ul>
|
||||
</div>
|
||||
{% endif %}
|
||||
|
||||
{% if insights.insights %}
|
||||
<div>
|
||||
<h3 class="text-xl font-semibold text-gray-800 mb-2">Key Insights</h3>
|
||||
<ul class="list-disc list-inside space-y-1">
|
||||
{% for insight in insights.insights %}
|
||||
<li class="text-gray-700">{{ insight }}</li>
|
||||
{% endfor %}
|
||||
</ul>
|
||||
</div>
|
||||
{% endif %}
|
||||
|
||||
{% if insights.implications %}
|
||||
<div>
|
||||
<h3 class="text-xl font-semibold text-gray-800 mb-2">Implications</h3>
|
||||
<ul class="list-disc list-inside space-y-1">
|
||||
{% for implication in insights.implications %}
|
||||
<li class="text-gray-700">{{ implication }}</li>
|
||||
{% endfor %}
|
||||
</ul>
|
||||
</div>
|
||||
{% endif %}
|
||||
|
||||
{% if insights.related_areas %}
|
||||
<div>
|
||||
<h3 class="text-xl font-semibold text-gray-800 mb-2">Related Areas</h3>
|
||||
<div class="flex flex-wrap gap-2">
|
||||
{% for area in insights.related_areas %}
|
||||
<span class="px-3 py-1 bg-blue-100 text-blue-800 rounded-full text-sm">
|
||||
{{ area }}
|
||||
</span>
|
||||
{% endfor %}
|
||||
</div>
|
||||
</div>
|
||||
{% endif %}
|
||||
</div>
|
||||
{% endif %}
|
||||
{% else %}
|
||||
<p class="text-gray-600">No insights available for these articles.</p>
|
||||
{% endif %}
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<h2 class="text-3xl font-bold text-gray-800 mb-6">Recommended Articles</h2>
|
||||
|
||||
<div class="grid grid-cols-1 md:grid-cols-2 lg:grid-cols-3 gap-6">
|
||||
{% for article in articles %}
|
||||
<article class="article-card bg-white rounded-lg shadow-md overflow-hidden">
|
||||
<div class="p-6">
|
||||
<h3 class="text-xl font-semibold text-gray-800 mb-2">
|
||||
<a href="{{ article.link }}" target="_blank" class="hover:text-blue-600">
|
||||
{{ article.title }}
|
||||
</a>
|
||||
</h3>
|
||||
<p class="text-gray-600 mb-4">{{ article.content[:200] }}...</p>
|
||||
<div class="flex justify-between items-center text-sm text-gray-500">
|
||||
<span>{{ article.source }}</span>
|
||||
<span>{{ article.published }}</span>
|
||||
</div>
|
||||
{% if article.categories %}
|
||||
<div class="mt-4 flex flex-wrap gap-2">
|
||||
{% for category in article.categories %}
|
||||
<span class="px-2 py-1 bg-blue-100 text-blue-800 rounded-full text-xs">
|
||||
{{ category }}
|
||||
</span>
|
||||
{% endfor %}
|
||||
</div>
|
||||
{% endif %}
|
||||
<div class="mt-4">
|
||||
<a href="{{ article.link }}" target="_blank" class="inline-block bg-blue-600 text-white px-4 py-2 rounded-md font-medium hover:bg-blue-700 transition-colors duration-300">
|
||||
Read More
|
||||
</a>
|
||||
</div>
|
||||
</div>
|
||||
</article>
|
||||
{% endfor %}
|
||||
</div>
|
||||
</div>
|
||||
{% endblock %}
|
||||
@@ -2,7 +2,6 @@ from pinecone import Pinecone, ServerlessSpec
|
||||
from typing import List, Dict, Any
|
||||
from config import (
|
||||
PINECONE_API_KEY,
|
||||
PINECONE_ENVIRONMENT,
|
||||
PINECONE_INDEX_NAME,
|
||||
VECTOR_DIMENSION,
|
||||
TOP_K_RESULTS
|
||||
@@ -16,13 +15,17 @@ class VectorStore:
|
||||
|
||||
def _ensure_index(self):
|
||||
"""Ensure the Pinecone index exists, create if it doesn't."""
|
||||
# Check if index exists, create if it doesn't
|
||||
if self.index_name not in self.pinecone.list_indexes().names():
|
||||
# Create a new index with the correct dimension
|
||||
self.pinecone.create_index(
|
||||
name=self.index_name,
|
||||
dimension=VECTOR_DIMENSION,
|
||||
metric="cosine",
|
||||
spec=ServerlessSpec(cloud="aws", region="us-east-1")
|
||||
)
|
||||
print(f"Created new index '{self.index_name}' with dimension {VECTOR_DIMENSION}")
|
||||
|
||||
self.index = self.pinecone.Index(self.index_name)
|
||||
|
||||
def upsert_articles(self, articles: List[Dict[str, Any]]) -> bool:
|
||||
|
||||
Reference in New Issue
Block a user