rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2026-01-06 03:42:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: add recommender system example (#1561)

Browse Source 
before:
![Screenshot 2024-08-24
230216](https://github.com/user-attachments/assets/cc8a810a-b032-45d7-b086-b2ef0720dc16)

After:
![Screenshot 2024-08-24
230228](https://github.com/user-attachments/assets/eaa1dc31-ac7f-4b81-aa79-b4cf94f0cbd5)

---------

Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com>
This commit is contained in:
Rithik Kumar
2024-08-25 12:30:30 +05:30
committed by GitHub
parent 02d85a4ea4
commit 632007d0e2
5 changed files with 52 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/src/examples/python_examples/rag.md
View File

@@ -2,11 +2,11 @@
**RAG: Revolutionize Information Retrieval with LanceDB 🔓🧐**
====================================================================
Unlock the full potential of Retrieval-Augmented Generation (RAG) with LanceDB, a solution for efficient vector-based information retrieval 📊.
Build RAG (Retrieval-Augmented Generation) with LanceDB, a powerful solution for efficient vector-based information retrieval 📊.
**Experience the Future of Search 🔄**
RAG integrates large language models (LLMs) with scalable knowledge bases, enabling efficient information retrieval and answer generation 🤖. By applying RAG to industry-specific use cases, developers can optimize query processing 📊, reduce response latency ⏱️, and improve resource utilization 💻. LanceDB provides a robust framework for integrating LLMs with external knowledge sources, facilitating accurate and informative responses 📝.
🤖 RAG enables AI to **retrieve** relevant information from external sources and use it to **generate** more accurate and context-specific responses. 💻 LanceDB provides a robust framework for integrating LLMs with external knowledge sources 📝.
| **RAG** | **Description** | **Links** |
|----------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------|

37
docs/src/examples/python_examples/recommendersystem.md Normal file
View File

@@ -0,0 +1,37 @@
**Recommender Systems: Personalized Discovery🍿📺**
==============================================================
Deliver personalized experiences with Recommender Systems. 🎁
**Technical Overview📜**
🔍️ LanceDB's powerful vector database capabilities can efficiently store and query item embeddings. Recommender Systems can utilize it and provide personalized recommendations based on user preferences 🤝 and item features 📊 and therefore enhance the user experience.🗂️
| **Recommender System** | **Description** | **Links** |
| ---------------------- | --------------- | --------- |
| **Movie Recommender System🎬** | 🤝 Use **collaborative filtering** to predict user preferences, assuming similar users will like similar movies, and leverage **Singular Value Decomposition** (SVD) from Numpy for precise matrix factorization and accurate recommendations📊 | [![Github](../../assets/github.svg)][movie_github] <br>[![Open In Collab](../../assets/colab.svg)][movie_colab] <br>[![Python](../../assets/python.svg)][movie_python] |
| **🎥 Movie Recommendation with Genres** | 🔍 Creates movie embeddings using Doc2Vec, capturing genre and characteristic nuances, and leverages VectorDB for efficient storage and querying, enabling accurate genre classification and personalized movie recommendations through similarity searches🎥 | [![Github](../../assets/github.svg)][genre_github] <br>[![Open In Collab](../../assets/colab.svg)][genre_colab] <br>[![Ghost](../../assets/ghost.svg)][genre_ghost] |
| **🛍️ Product Recommender using Collaborative Filtering and LanceDB** | 📈 Using **Collaborative Filtering** and **LanceDB** to analyze your past purchases, recommends products based on user's past purchases. Demonstrated with the Instacart dataset in our example🛒 | [![Github](../../assets/github.svg)][product_github] <br>[![Open In Collab](../../assets/colab.svg)][product_colab] <br>[![Python](../../assets/python.svg)][product_python] |
| **🔍 Arxiv Search with OpenCLIP and LanceDB** | 💡 Build a semantic search engine for Arxiv papers using LanceDB, and benchmarks its performance against traditional keyword-based search on Nomic's Atlas, to demonstrate the power of semantic search in finding relevant research papers📚 | [![Github](../../assets/github.svg)][arxiv_github] <br>[![Open In Collab](../../assets/colab.svg)][arxiv_colab] <br>[![Python](../../assets/python.svg)][arxiv_python] |
| **Food Recommendation System🍴** | 🍔 Build a food recommendation system with LanceDB, featuring vector-based recommendations, full-text search, hybrid search, and reranking model integration for personalized and accurate food suggestions👌 | [![Github](../../assets/github.svg)][food_github] <br>[![Open In Collab](../../assets/colab.svg)][food_colab] |
[movie_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/movie-recommender
[movie_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/movie-recommender/main.ipynb
[movie_python]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/movie-recommender/main.py
[genre_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/movie-recommendation-with-genres
[genre_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/movie-recommendation-with-genres/movie_recommendation_with_doc2vec_and_lancedb.ipynb
[genre_ghost]: https://blog.lancedb.com/movie-recommendation-system-using-lancedb-and-doc2vec/
[product_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/product-recommender
[product_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/product-recommender/main.ipynb
[product_python]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/product-recommender/main.py
[arxiv_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/arxiv-recommender
[arxiv_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/arxiv-recommender/main.ipynb
[arxiv_python]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/arxiv-recommender/main.py
[food_github]: https://github.com/lancedb/vectordb-recipes/blob/main/examples/Food_recommendation
[food_colab]: https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/Food_recommendation/main.ipynb

2
docs/src/examples/python_examples/vector_search.md
View File

@@ -1,7 +1,7 @@
**Vector Search: Unlock Efficient Document Retrieval 🔓👀**
====================================================================
Unlock the power of vector search with LanceDB, a cutting-edge solution for efficient vector-based document retrieval 📊.
Vector search with LanceDB, is a solution for efficient and accurate similarity searches in large datasets 📊.
**Vector Search Capabilities in LanceDB🔝**