itrummer/thalamusdb
ThalamusDB: semantic query processing on multimodal data
This helps data analysts and researchers query complex datasets that combine text, images, and audio, even if the information isn't perfectly structured. You input a database containing descriptions, image paths, and audio file paths, and get answers to questions like "How many cars in pictures are red?" or "Show me all audio clips with someone speaking." It's for anyone who needs to extract insights from diverse, unstructured media using natural language.
114 stars. No commits in the last 6 months.
Use this if you need to ask complex, semantic questions about a database that includes unstructured data like images, audio, and text, and want to use natural language in your queries.
Not ideal if your data is entirely structured in traditional tables and doesn't require semantic understanding of images, audio, or free-form text.
Stars
114
Forks
6
Language
Python
License
MIT
Category
Last pushed
Aug 27, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/itrummer/thalamusdb"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ewok-core/ewok-paper
Elements of World Knowledge! This repository houses data and code needed to replicate our first...
texttron/hyde
HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels
ArslanKAS/Large-Language-Models-with-Semantic-Search
Explore from keyword search to dense retrieval and reranking, which injects the intelligence of...
Ahren09/SciEvo
A longitudinal dataset for academic literature, including papers, metadata, and citation graphs,...
jzhoubu/vsearch
An Extensible Framework for Retrieval-Augmented LLM Applications: Learning Relevance Beyond...