!This readme is written by ChatGPT!
YassQueenDB is a graph database library that allows you to store, analyze, and search through your data in a graph format. By using the Universal Sentence Encoder, it provides an efficient and semantic approach to handle text data. ππ§ π
- Semantic understanding of text data π
- Efficient handling of relationships between data πΌ
- Easy-to-use graph manipulation functions π οΈ
- Text summarization capabilities π
- Keyword extraction for easy indexing and searching π
- Flexible graph creation and management π
- Requires downloading and loading the Universal Sentence Encoder model π₯
- Limited to text data only π«
- Might be slow for very large datasets based on your system resources π
- Create, select, and delete graphs π
- Add and delete nodes π
- Add and delete edges
βοΈ
- Semantic search for nodes π§
- Summarize sections and paragraphs π
- Split paragraphs into sentences and create nodes from them π
- Generate embeddings for text data π
- Extract keywords from input data π·οΈ
- Laplacian eigenmaps for dimensionality reduction π
- Save and load graphs to/from files πΎ
from yassqueendb import GraphDatabase
#Create a YassQueenDB instance
db = GraphDatabase()
# Load the sentence encoder
db.load_sentence_encoder()
# Create a graph
db.create_graph('example_graph')
# Add a node
db.add_node('This is a sample sentence.')
# Add an edge between nodes
db.add_edge('node1', 'node2', 'relationship_name')
# Search for a node
db.search_node('node1')
# Show the graph
db.show_graph()
# Save the graph to a file
db.save_graph_to_file('example_graph.pickle')
# Load the graph from a file
db.load_graph_from_file('example_graph.pickle')
# Summarize a section of text
section = "This is a section of text. It has multiple paragraphs."
section_summary = db.summarize_section(section)`
Get started with YassQueenDB and unleash the power of semantic graph databases! πππΊ