Files
lancedb/docs/src/examples/python_examples/multimodal.md
2024-10-29 22:55:27 +05:30

28 lines
4.4 KiB
Markdown

# **Multimodal Search with LanceDB 🤹‍♂️🔍**
Using LanceDB's multimodal capabilities, combine text and image queries to find the most relevant results in your corpus ! 🔓💡
**Explore the Future of Search 🚀**
LanceDB supports multimodal search by indexing and querying vector representations of text and image data 🤖. This enables efficient retrieval of relevant documents and images using vector-based similarity search 📊. The platform facilitates cross-modal search, allowing for text-image and image-text retrieval, and supports scalable indexing of high-dimensional vector spaces 💻.
| **Multimodal** | **Description** | **Links** |
|:----------------|:-----------------|:-----------|
| **Multimodal CLIP: DiffusionDB 🌐💥** | Multi-Modal Search with **CLIP** and **LanceDB** Using **DiffusionDB** Data for Combined Text and Image Understanding ! 🔓 | [![GitHub](../../assets/github.svg)][Clip_diffusionDB_github] <br>[![Open In Collab](../../assets/colab.svg)][Clip_diffusionDB_colab] <br>[![Python](../../assets/python.svg)][Clip_diffusionDB_python] <br>[![Ghost](../../assets/ghost.svg)][Clip_diffusionDB_ghost] |
| **Multimodal CLIP: Youtube Videos 📹👀** | Search **Youtube videos** using Multimodal CLIP, finding relevant content with ease and accuracy! 🎯 | [![Github](../../assets/github.svg)][Clip_youtube_github] <br>[![Open In Collab](../../assets/colab.svg)][Clip_youtube_colab] <br> [![Python](../../assets/python.svg)][Clip_youtube_python] <br>[![Ghost](../../assets/ghost.svg)][Clip_youtube_python] |
| **Multimodal Image + Text Search 📸🔍** | Find **relevant documents** and **images** with a single query using **LanceDB's** multimodal search capabilities, to seamlessly integrate text and visuals ! 🌉 | [![GitHub](../../assets/github.svg)](https://github.com/lancedb/vectordb-recipes/tree/main/examples/archived_examples/multimodal_search) <br>[![Open In Collab](../../assets/colab.svg)](https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/archived_examples/multimodal_search/main.ipynb) <br> [![Python](../../assets/python.svg)](https://github.com/lancedb/vectordb-recipes/blob/main/examples/multimodal_search/main.py)<br> [![Ghost](../../assets/ghost.svg)](https://blog.lancedb.com/multi-modal-ai-made-easy-with-lancedb-clip-5aaf8801c939/) |
| **Cambrian-1: Vision-Centric Image Exploration 🔍👀** | Learn how **Cambrian-1** works, using an example of **Vision-Centric** exploration on images found through vector search ! Work on **Flickr-8k** dataset 🔎 | [![Kaggle](https://img.shields.io/badge/Kaggle-035a7d?style=for-the-badge&logo=kaggle&logoColor=white)](https://www.kaggle.com/code/prasantdixit/cambrian-1-vision-centric-exploration-of-images/)<br> [![Ghost](../../assets/ghost.svg)](https://blog.lancedb.com/cambrian-1-vision-centric-exploration/) |
[Clip_diffusionDB_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/multimodal_clip_diffusiondb
[Clip_diffusionDB_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/multimodal_clip_diffusiondb/main.ipynb
[Clip_diffusionDB_python]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/multimodal_clip_diffusiondb/main.py
[Clip_diffusionDB_ghost]: https://blog.lancedb.com/multi-modal-ai-made-easy-with-lancedb-clip-5aaf8801c939/
[Clip_youtube_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/multimodal_video_search
[Clip_youtube_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/multimodal_video_search/main.ipynb
[Clip_youtube_python]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/multimodal_video_search/main.py
[Clip_youtube_ghost]: https://blog.lancedb.com/multi-modal-ai-made-easy-with-lancedb-clip-5aaf8801c939/