streamlit-CLIP-Unsplash-explorer
CLIPSemanticImageSearch
streamlit-CLIP-Unsplash-explorer | CLIPSemanticImageSearch | |
---|---|---|
1 | 1 | |
50 | 1 | |
- | - | |
4.4 | 4.1 | |
over 3 years ago | about 3 years ago | |
CSS | Python | |
- | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
streamlit-CLIP-Unsplash-explorer
-
Show HN: Building search engines with open source tech for $99
We are building machine learning products for a fixed weekly fee. We saw that search engines are the most requested type of product.
Nowadays, with https://streamlit.io/, https://typesense.org/, or http://jina.ai/ (which are open source) and some coding skills you can build state-of-the-art quality search engines. 10 years ago a team of engineers was required for this.
Some examples,
You can search documents: https://pinksearchengine.link/example_search.html (code here https://github.com/kstathou/vector_engine)
You can search webpages: https://pinksearchengine.link/example_search_web.html (code here https://github.com/typesense/showcase-recipe-search)
You can search images, using textual queries: https://pinksearchengine.link/example_search_images_with_tex... (code here https://github.com/vatsalsaglani/CLIPSemanticImageSearch)
You can search images, using images as queries: https://pinksearchengine.link/example_search_images_with_ima... (code here https://github.com/thoppe/streamlit-CLIP-Unsplash-explorer)
CLIPSemanticImageSearch
-
Show HN: Building search engines with open source tech for $99
We are building machine learning products for a fixed weekly fee. We saw that search engines are the most requested type of product.
Nowadays, with https://streamlit.io/, https://typesense.org/, or http://jina.ai/ (which are open source) and some coding skills you can build state-of-the-art quality search engines. 10 years ago a team of engineers was required for this.
Some examples,
You can search documents: https://pinksearchengine.link/example_search.html (code here https://github.com/kstathou/vector_engine)
You can search webpages: https://pinksearchengine.link/example_search_web.html (code here https://github.com/typesense/showcase-recipe-search)
You can search images, using textual queries: https://pinksearchengine.link/example_search_images_with_tex... (code here https://github.com/vatsalsaglani/CLIPSemanticImageSearch)
You can search images, using images as queries: https://pinksearchengine.link/example_search_images_with_ima... (code here https://github.com/thoppe/streamlit-CLIP-Unsplash-explorer)
What are some alternatives?
Typesense - Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences
streamlit - Streamlit — A faster way to build and share data apps.
showcase-recipe-search - Instantly search 2M cooking recipes using Typesense Search (an open source alternative to Algolia / ElasticSearch) ⚡ 🥘 🔍
Super-mario-bros-PPO-pytorch - Proximal Policy Optimization (PPO) algorithm for Super Mario Bros
vector_engine - Build a semantic search engine with Transformers and Faiss
dalle-starter - Node-based starter application for interacting with Dall-E 3 / Dall-E 2 (OpenAI) API in the browser.