Blog
All articles. All pillars. All authors.
#119 -- FastEmbed Integration for Embeddings
How FLIN integrates FastEmbed for local embedding generation -- no API calls, no network latency, no data leaving the server. Privacy-first semantic search at 10ms per embedding.
#120 -- RAG: Retrieval, Reranking, and Source Attribution
How FLIN implements Retrieval-Augmented Generation -- semantic retrieval from your data, cross-encoder reranking for precision, and source attribution so users know where answers come from.
#121 -- Document Parsing: PDF, DOCX, CSV, JSON, YAML
How FLIN extracts text from PDF, DOCX, CSV, JSON, and YAML files for indexing and RAG -- built-in parsers that turn any document format into searchable, embeddable text.
#053 -- Time Arithmetic: Adding Days, Comparing Dates
How we implemented duration literals and time arithmetic in FLIN -- from the elegant N.days syntax to constant folding at compile time, delivering zero-cost abstractions for date operations.
#124 -- AI-First Language Design
How FLIN was designed from the ground up for AI-assisted development -- minimal syntax for fewer tokens, self-contained files for complete context, and MCP integration for AI agent tooling.
#020 -- The Complete Compilation Pipeline, End to End
FLIN's complete compilation pipeline: six phases from source code to running application, explained end to end.
#037 -- Destructuring Everywhere
How we implemented destructuring in FLIN -- array, entity, and nested destructuring with rest patterns, default values, and the stub-first approach that kept the compiler healthy.
#122 -- Code-Aware Chunking for RAG
How FLIN's chunk_text() function splits documents into embedding-appropriate segments while respecting paragraph boundaries, code blocks, headings, and semantic coherence.
#123 -- Hybrid Document Search: BM25 + Semantic
How FLIN combines BM25 keyword search with semantic vector search for hybrid document ranking -- getting the precision of exact keyword matching and the recall of meaning-based search.
#129 -- Download Grants and Access Keys
How FLIN secures file access with time-limited download grants and scoped access keys.
#132 -- Extracting Text From CSV, XLSX, RTF, and XML
How FLIN extracts searchable text from CSV, XLSX, RTF, and XML files with built-in parsers.
#085 -- Design Tokens and Theming System
How FlinUI's design token system provides 50+ tokens for colors, spacing, typography, and shadows -- enabling consistent theming and dark mode across 365+ components.