AI Bot: Intelligent Financial Query Assistant Powered by PostgreSQL and Ollama

This is a submission for the Open Source AI Challenge with pgai and Ollama

What I Built

Presenting An AI bot is a clever assistant designed to comprehend and react to actual questions about banking, insurance, and credit cards. By matching the semantics of user inquiries with the most appropriate answers, the AI Bot provides contextually relevant answers. It is designed to not only recognize but also fully understand the user's query purpose. The AI Bot provides a smooth and easy-to-use user experience by accurately interpreting and responding to user inquiries about specific policies, financial advice, or credit details.

Demo

https://www.youtube.com/watch?v=MTUj1jAPEdk&feature=youtu.be

Tools Used

To accomplish its responsive, high-performance AI capabilities, this project makes use of a number of potent tools and technologies:

- Database: PostgreSQL server, provided by Timescale, serves as the foundational database for vector storage and querying.
- Programming Language: Built using .NET 8 for seamless and robust server-side execution.
- Model: Utilized Ollama’s nomic-embed-text model to generate precise embeddings and support AI Bot’s semantic understanding.
- Embedding API: Ollama’s embedding API enabled enhanced text matching and contextual understanding.
- Algorithm: Cosine Similarity was implemented to measure and match query relevance.
- Cache: Optimized with Memory Cache for faster responses and reduced computation time.
- AI Extension: pgvector was instrumental in managing and querying vector data.

Final Thoughts

The process of creating AI Bot was fascinating and demonstrated how open-source, AI-powered tools can be used to create practical applications. This project exemplifies how PostgreSQL and Ollama's open-source models may be used to create solutions that are intelligent, responsive, and easily accessible.

Prize Categories:

• Open-source Models from Ollama: AI Bot leverages Ollama’s open-source models for embedding and understanding text-based queries.
• Embeeding API: Ollama’s embedding API enabled enhanced text matching and contextual understanding
• Vectorizer Vibe: With pgvector, we harnessed vector embeddings to achieve high-accuracy query matching
• PR: ngtduc693