LingXi AI Writing Platform
AI-powered intelligent article creation platform built on Spring Boot 3 + Spring AI Alibaba
•
1 min read
The RAG Basics: From Documents to Cited Answers
Understand ingestion, chunking, retrieval, and grounded generation, with citations that constrain answers.
RAG Embeddings and Vector Databases: The Engineering Behind Similarity
Understand embeddings, distance metrics, metadata, indexing, and incremental updates for reliable vector retrieval.
Production RAG Architecture: Permissions, Versions, and Observability
Design deployable RAG systems with ingestion, permission filters, index versions, caching, evaluation, and graceful degradation.
Optimizing RAG Retrievers: Top-K, Hybrid Search, and Reranking
Tune RAG retrievers with BM25, vector search, hybrid recall, reranking, and context compression trade-offs.
OpenAI Tool Calling: Schemas, Execution Loops, and Safety Boundaries
Build auditable function-calling loops with explicit schemas, model decisions, application execution, and result handoff.
OpenAI Structured Outputs: Make Model Results Verifiable
Constrain model output with JSON Schema and Pydantic while handling refusals, parse failures, and schema evolution.
OpenAI Multimodal AI: Working with Text, Images, and Documents
Design multimodal input pipelines with preprocessing, cost, privacy, and structured output for images and documents.
OpenAI API Fundamentals: Requests, Messages, Parameters, and Reliability
Build a reliable model API foundation with client setup, message structure, timeouts, retries, and cost controls.
LangChain Tool-Calling Agents: Separate Decisions from Execution
Design controllable agents with explicit tool schemas, decision loops, execution boundaries, and error recovery.