Vector-Database with Qdrant Library and Embedding with Sentence Tansformers

Simulating a Vector Database on CoNaLa dataset.

Dataset

• CoNaLa: The Code/Natural Language Challenge dataset to retrieve program snippets relevant to user queries.

Frameworks

• Vector Database: in-memory vector database using Qdrant library.
• Embeddings: Sentence Transformer (all-MiniLM-L6-v2).

Files

• prepare_data.ipynb: Notebook to view the data and perfrom simple Analysis of the Dataset.
• embeddings.ipynb: Contain the full code to create embedding using sentence-transformers, vector-database using qdrant and then retrieval based on cosine similarity.

If you find the repo helpful, please drop a ⭐