beyond_vector_search

Di luar pencarian vektor
Mesin Permintaan Grafik Vektor/Pengetahuan Hibrida untuk Peningkatan Pengambilan Data

Instalasi

Kami menggunakan Python == 3.9.18, dan kami sarankan menggunakan lingkungan virtual untuk menginstal paket yang diperlukan.

 pip install -r requirements.txt

Membuat data yang difilter

• notebooks/parsing_json.ipynb : filter data untuk arxiv
• notebooks/parsing_cnn_news.ipynb : Filter data untuk CNN News
• notebooks/parsing_wiki_movies.ipynb : filter data untuk film wiki

Dataset

Kami menggunakan subset dari dataset ARXIV dari Kaggle yang berisi 12.926 sampel, dan file acar disediakan di "Beyond_vector_search/data/filtered_data.pickle".

Kode Sumber

 make_vectordb.py: a script to build a vector database from a "data/filtered_data.pickle"

utils/
    - build_graph.py: a script containing helper functions for building the knowledge graph
    - parse_arxiv.py: a script containing helper functions for parsing the arxiv dataset
vector_graph/
    - bipartite_graph_dict.py: A custom implementation of the bipartite graph
    - bipartite_graph_networkx.py: An experimental implementation of the bipartite graph using networkx
    - embedding_models.py: A custom implementation of the embedding models for generating the text embeddings
workloads
    - keyword_extractor.py
    - query_gen.py: A script for generating the text queries given paper data points
    - workload_gen.sh: This is the script for generating the workloads we described in the report
testing
    - inference.py: A script for executing our various search query engines on the generated workloads
zy_testing
    - compute_metrics_cos.py: A script for computing the accuracy of our results utilizing various performance compute_metrics_cos