From source code 2 LLM constraints:a semantic extractor for Python, SwiftUI, Lua
The Semantic Extractor is a tool designed to enhance the capabilities of language models by providing structured information about framework usage rules. It compiles source code into an intermediate representation that captures various constraints and relationships within the framework. This allows language models to retrieve accurate information about how to use decorators and other elements correctly, reducing the likelihood of generating incorrect code.
- ▪The Semantic Extractor serves as a compiler that translates framework source code into a structured IR bundle.
- ▪It provides detailed information on decorator placement, signature transformations, and type constraints.
- ▪Supported frameworks include Python's Click, Flask, and SQLModel, as well as SwiftUI and Lua.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/whitecell-dev/Semantic-Extractor/tree/main |
| Publication time | Sun, 24 May 2026 08:31:38 +0000 |
| Retrieval time | 2026-05-24T08:37:31.504Z |
| Last seen | 2026-05-24T08:37:31.504Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | b1tPZFKa_OS0 |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Semantic Extractor Griffe + constraints, served over MCP. Ground truth about framework usage rules, not just API signatures. The Problem Griffe tells you what a framework has. It doesn't tell you how the framework forces you to use it. Which decorators can nest? What signature transformations happen? What are the type constraints? Where can a decorator legally be placed? LLMs need these rules to generate correct code. The Solution Semantic Extractor compiles framework source code into a structured IR bundle that captures: Layer What It Captures Example API signatures Functions, classes, methods (Griffe-compatible) def command(...) Decorator placement Where decorators can legally appear `COMMAND_BUILDER = FUNCTION Signature invariants How decorators transform function signatures…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.