Reading
An enterprise-level semantic analysis prototype that converts natural language business questions into governed SQL queries using semantic layer, LangGraph orchestration, PostgreSQL, and LLM.
Section 01
An enterprise-level semantic analysis prototype that converts natural language business questions into governed SQL queries using semantic layer, LangGraph orchestration, PostgreSQL, and LLM.
Section 02
Section 03
In the field of enterprise data analysis, a long-standing contradiction exists: business personnel need data insights, but the technical threshold of SQL queries deters most people. Traditional solutions are BI tools or predefined reports, but these often fail to meet flexible and changing business needs.
hmandadi's Semantic Insights Agent attempts to bridge this gap using AI technology. It is not a simple "text-to-SQL" tool, but an enterprise-level semantic analysis system that emphasizes governance, interpretability, and architectural rigor.
Section 04
The Semantic Layer is the core innovation of this project. It sits between the original database and business users, defining:
The value of this design is that when a business person asks "What was the sales volume in the East China region last quarter?", the system not only knows which table to query but also understands how "sales volume" should be calculated and which provinces are included in "East China region".
Section 05
The project's architectural design reflects a clear layered approach:
Section 06
A lightweight web interface that allows users to input questions in natural language and view results. This choice reflects the MVP (Minimum Viable Product) design philosophy—avoiding excessive resource investment in UI development before verifying core concepts.
Section 07
This is the "brain" of the system. LangGraph is responsible for orchestrating LLM-driven reasoning steps, breaking down the complex natural language to SQL conversion process into manageable nodes:
Section 08
Uses OpenAI's models for natural language to SQL translation. The project uses carefully designed prompt templates (prompts.py) to guide the model to generate high-quality SQL that meets enterprise governance requirements.
Keep going with more reads from the same topic.
Nornir MCP Server is an enterprise-level server based on the Model Context Protocol (MCP). It seamlessly integrates large language models (such as Claude) with the Nornir network automation framework, supporting natural language orchestration for multi-vendor network devices (Cisco, Arista, Juniper, etc.), and providing production-grade features like a dual-engine architecture (NAPALM + Netmiko), intelligent filtering, and a secure sandbox.
Bibliothèque Française LLM is a structured indexing and annotation project for French public domain literature designed specifically for large language models (LLMs). It integrates multiple authoritative sources such as DraCor, Common Corpus, and Wikisource, providing metadata indexing categorized by genre, author, and era, as well as in-depth annotations for dramatic texts (including characters, lines, stage directions, etc.). Its aim is to enable LLMs to efficiently read and understand classic French literary works.
Splinter is a minimalist, high-performance key-value (KV) and vector storage system enabling zero-latency inter-process communication via shared memory and atomic operations. With only 766 lines of core code, it supports millions of operations per second and 768-dimensional vector storage, offering a new architectural approach for local LLM inference and data-intensive applications.
A complete cloud-native AI application development guide for beginners, building a simple generative AI chatbot using Amazon EC2, Apache, Python CGI, and Amazon Bedrock, covering architecture design, IAM permission configuration, security best practices, and cost optimization suggestions.