# Notebook Examples
Hybrid Search with Hyperspace
Use semantic search and metadata filtering to match academic papers.

Dataset:
arXiv dataset

Embedding Model:

all-MiniLM-L6-v2
Vector Dimension: 384
No. Metadata Fields: 7
Query Operations:
Vector search, key-value matching

Classic Search with Hyperspace
Use classic search to match files of Crimes in Chicago.


Dataset:
Crimes in Chicago
No. Metadata Fields: 23
Query Operations:
Key-value matching, geo-distance matching, date matching
Hybrid Search and Hamming Distance with Hyperspace
Use metadata filtering and vector search in binary format.

Dataset:
Internal by Hyperspace
Embedding Model:

Randomly generated data
Vector Dimension: 200
No. Metadata Fields: 6
Query Operations:
Vector search, key-value matching

Movie Recommendation with Hyperspace
Use metadata filtering and semantic search to create a Movie recommendation engine.

Dataset:
The Movie Dataset
Embedding Model:

all-MiniLM-L6-v2
Vector Dimension: 384
No. Metadata Fields: 15
Query Operations:
Vector search, key-value matching, aggregations

Matching Applications with Hyperspace
Use metadata filtering and semantic search to match applications.

Dataset:
ADVEC-ML App Data
Embedding Model:

bge-small-en
Vector Dimension: 384
No. Metadata Fields: 6
Query Operations:
Vector search, key-value matching

E-Commerce Recommendation System with Hyperspace
Use keyword filtering and multi vector search to build a recommendation system for Amazon products
Dataset:
Amazon Products Dataset
Embedding Model:

Clip
Vector Dimension: 384
No. Metadata Fields: 6
Query Operations:
Vector search, text matching

--- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.hyper-space.io/hyperspace-docs/getting-started/notebook-examples.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.