This is a test project to mimic the performance of the knowledge graph
Install requirements.txt
pip install requirements.txt
- Pretrained pretrained_model.py
Find relavant words by using pretrained model (Fast & Outdated)
- Selftrained word2vec_trainer.py
Find relavant words by using latest Wiki corpus trained model (Slow & Latest)
Return Google search links related to query and relavant words
Implement keyword extraction algorithm based on Text Rank on the content of links obtained through Google Search Engine