Best Products
Launches
Launch archive
Most-loved launches by the community
Launch Guide
Checklists and pro tips for launching
Community
Discuss
Forums
Ask questions, find support, and connect
Events
Meet others online and in-person
Kitty Points Leaderboard
The highest scoring community members
Streaks
The most active community members
Read
Newsletter
The best of Product Hunt, every day
Stories
Tech news, interviews, and tips from makers
Changelog
New Product Hunt features and releases
MCP
New
Advertise
Subscribe
Sign in
Clear text
recent
p/yggy
by
Carlos Gienow
•
22d ago
Your retriever found the topic. Did it satisfy the question?
... paper first on 62.4% and 66.0% of questions. Lexical text search scored 36.4% and 40.4%. A basic graph approach scored 51.2% and 52.4%. The useful takeaway for builders is that matching a topic and satisfying a question are different
retrieval
tasks. A paper can sound perfect and still come from the wrong institution. Some boundaries matter here. This is our methodology benchmark using STaRK s existing graph, with roughly 26,000 candidate papers per split. It does not test yggy ... ... document extraction or hosted product, and it is not a comparison against modern vector or hybrid
retrieval
1
4
p/general
by
Andres Vlaeminck
•
1yr ago
RAG Frustration: Is Vector Search Giving Your LLM Junk Context?
... Makers & Builders using LLMs! Anyone else building cool stuff like PDF Q&A or custom bots with RAG, but finding the context
retrieval
step... frustrating? Most AI app data stacks these days use vector search (Pinecone, Weaviate, etc.) to grab text chunks for the LLM. But sometimes it feels like it finds stuff that's keyword-similar while totally missing the actual point the user asked for. Leads to those slightly weak or "confidently wrong" LLM answers ... ... vector similarity? Getting re-ranking right? What part is giving you the most trouble? (Context: We hit this wall hard internally. Similarity search wasn't cutting it for the precision we needed, so we ended up building our own
retrieval
0
10
Subscribe
Sign in