Viewing profile — MrezaPourreza

Rather than converting the entirety of structured data into unstructured text, we opt to provide the language model with sample rows and the database schema. Utilizing this approac…

Yes, based on what I've experimented with OpenAI's assistants, it still requires engineering and developing tools to get the best performance on large databases.

Hello, thank you very much for your meticulous comment. The 85.3% accuracy reported in our paper (I'm one of the authors of the DIN-SQL paper) pertains to the test set. However, in…

Yes, we have already submitted the model for evaluation on the Spider holdout test set. While your suggestion is certainly intriguing, implementing a universal solution could be qu…

I believe this article underscores the significance and efficacy of fine-tuning for specific tasks. Looking ahead, I envision the integration of fine-tuned models with RAG agents a…

A tutorial on how to fine-tune a GPT3.5 model for Natural Language to SQL tasks and a comparison of its performance vs Retrieval Augmented Generation. Based on the results, fine-tu…

Hello, and thank you for your positive feedback on our work with Dataherald. I'm currently in the process of tidying up the DIN-SQL repository, and I apologize for any inconvenienc…

Thank you for your interest in our work. The schema linking approach employed in our agent significantly differs from the one described in my paper. In the paper, we utilized a met…

For schema matching, we leverage embeddings. We create embeddings for the tables within the database and generate one for the natural language question provided. We then calculate …

I'd be delighted to assist you with your inquiries. Indeed, the context store interacts with vector databases to retrieve samples based on vector embeddings and cosine similarity.

This link contains some methods to get a confidence score for SQL queries.