https://github.com/nicholasgriffintn/llm-rss-vectorise-agent
An LLM agent that uses vectorise to make RSS feeds searchable
https://github.com/nicholasgriffintn/llm-rss-vectorise-agent
cloudflare cloudflare-ai cloudflare-queues cloudflare-vectorize llm remix rss
Last synced: 21 days ago
JSON representation
An LLM agent that uses vectorise to make RSS feeds searchable
- Host: GitHub
- URL: https://github.com/nicholasgriffintn/llm-rss-vectorise-agent
- Owner: nicholasgriffintn
- License: apache-2.0
- Created: 2024-08-23T20:42:00.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2025-01-20T22:53:50.000Z (over 1 year ago)
- Last Synced: 2025-03-24T04:39:11.746Z (about 1 year ago)
- Topics: cloudflare, cloudflare-ai, cloudflare-queues, cloudflare-vectorize, llm, remix, rss
- Language: TypeScript
- Homepage:
- Size: 11.4 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# LLM RSS Vectorise Agent
This is a project that uses Cloudflare AI with Vectorize to make RSS feeds searchable, alongside various other models through Cloudflare's API to summarise, analyse and chat with articles.
https://github.com/user-attachments/assets/a77b4a33-20f9-4601-ba46-39ba798d7c6c
## Apps
### Vectorise
The [Vectorise](/apps/vectorize/README.md) app is a CloudFlare Workers app that has the following triggers and endpoints:
1. `insert` - Triggered by calling `/insert`; retrieves active RSS feeds and queues them for processing.
2. `query` - Triggered by calling `/query?query=`; embeds the query and returns matching results.
3. `queue` - Triggered by Cloudflare Queues to process RSS feed messages and article entry messages.
4. `feeds` - Manage feed sources in D1:
- `GET /feeds` returns active RSS feeds.
- `POST /feeds` with `{ "url": "https://example.com/rss.xml" }` adds/enables a feed.
- `DELETE /feeds` with `{ "url": "https://example.com/rss.xml" }` disables a feed.
### Web
This is the web interface for the Vectorise app. It allows users to search, summarise, analyse, chat about articles, and save article notes.