Alternatives
Products that do what PAVL does
Psychological Movie recommendation System
- 1
- 2
- 3
Perplexity for videos, #1 research tool for video marketing
Sep 2025
- 4RA
Hello HN! I've built a web app that helps you discover new shows and movies you'll actually enjoy by: - Connecting to your Sonarr/Radarr/Plex instances to understand your media library - Leveraging your Plex watch history for personalized recommendations - Using the LLM of your choice to generate intelligent suggestions - Simple setup: Easy integration with your existing media stack - Flexible AI options: Works with OpenAI-compatible APIs like OpenRouter, or run locally via LM Studio, Ollama, etc. - Personalized recommendations: Based on what you actually watch. While it's still a…
2025 · github.com
- 5IM
2021 · mood2movie.com
- 6
- 7
- 8
- 9
- 10
- 11OS
Hi all! This morning, we released a new Apache 2.0 licensed model on HuggingFace for detecting hallucinations in retrieval augmented generation (RAG) systems. What we've found is that even when given a "simple" instruction like "summarize the following news article," every LLM that's available hallucinates to some extent, making up details that never existed in the source article -- and some of them quite a bit. As a RAG provider and proponents of ethical AI, we want to see LLMs get better at this. We've published an open source model, a blog more thoroughly describing our methodology (and…
2023 · vectara.com
- 12MA
Last week I released Moodflix (https://moodflix.streamlit.app), a movie recommendation engine based to find movies based on your mood. Moodflix was created on top of a movie dataset of 10k movies from The Movie Database. I vectorised the films using Hugging Face's T5 model (https://huggingface.co/docs/transformers/model_doc/t5) using the film's plot synopsis, genres and languages. Then I indexed the vectors using hnswlib (https://github.com/nmslib/hnswlib). LLMs can understand a movie's plot pretty well and distill the similarities…
2023 · share.streamlit.io
- 13PR
Personalized Recommendations: Tailored Just for You! Ever felt lost in the sea of TV shows, anime, and movies ? We’ve all been there. But guess what? Those days are over. Say hello to Personalized Recommendations. This isn’t just any update; it’s your ticket to a curated watchlist that feels like it was handpicked by your best friend who knows your taste inside out. Uses two separate recommendation engines — each serving up not just tens but hundreds, and sometimes even thousands, of personalized picks to which you can apply your preferred sorting and filters to narrow down exactly what you…
2024 · simkl.org
- 14MR
We've been working on a custom engineered collaborative filtering algorithm not only to recommend movies for one person but for several to watch together, at the same time. We're still in closed beta but would love to get feedback before launching.
2012 · foundd.com
- 15MI
Most Friday nights and weekends, my wife and I would spend 30+ minutes scrolling Netflix, vetoing each other's movie suggestions. The intersection of our tastes is pretty small. She's into rom coms and the occasional thriller, and couldn't care less about ratings. I gravitate toward critically acclaimed stuff and 3h+ sagas. Eventually, we would settle on something neither of us really wanted, or a comfort TV show. So, I built movieagent.io to help us. It's an agent that finds what you're in the mood for tonight. The agent plays the role of an arbiter, and does its best to try and bridge the…
Jan 2026 · movieagent.io
- 16
- 17
- 18IM
I built MoodieMovie, a web app that recommends films based on how you're feeling right now. Select emotions like "cheerful," "reflective," or even "weird," and get curated movie suggestions that match your current state of mind. Features: Mood-based algorithm that actually works (no more scrolling endlessly through streaming services) Magazine-style TOP100 section showcasing essential cinema Simple, intuitive UI with smooth animations Detailed movie pages with shareable links Tech stack: Next.js, Framer Motion, and a custom algorithm that maps emotional states to film characteristics. All…
2025 · moodiemovie.top
- 19
- 20SA
Hi HN, I’m Tullie, founder of Shaped. Previously, I was a researcher at Meta AI, worked on ranking for Instagram Reels, and was a contributor to PyTorch Lightning. We built ShapedQL because we noticed that while retrieval (finding 1,000 items) has been commoditized by vector DBs, ranking (finding the best 10 items) is still an infrastructure problem. To build a decent for you feed or a RAG system with long-term memory, you usually have to put together a vector DB (Pinecone/Milvus), a feature store (Redis), an inference service, and thousands of lines of Python to handle business logic…
Jan 2026 · playground.shaped.ai
- 21WB
Me and my friend built an unique content based Recommendation System, where user can just select Anime or write synopsis and our system will find the most similar anime available. We used Qdrant Vector Database for the Recommendations. Other Features includes, Streaming, Custom watchlist creation and sharing of watchlists. We update our Database regularly and plan to introduce new features in future.
2025 · aniversehd.com
- 22MR
2017 · cinetrii.com
- 23
- 24SS
2024 · mixpeek.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →