Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Skip to main content
graphify extract
[Local] Run local structural extraction and optional semantic processing.
graphify extract <path> [options]
Common options
| Option | Purpose |
|---|---|
--code-only | Skip semantic document and media extraction; no model key needed. |
--backend <name> | Select a headless semantic backend. |
--model <name> | Override the model for that backend. |
--mode deep | Request richer semantic extraction. |
--out <dir> / --output <dir> | Choose an output root. |
--no-cluster | Skip clustering. |
--no-gitignore | Ignore Git’s exclusions while still honoring .graphifyignore. |
--max-workers <n> | Structural extraction parallelism. |
--token-budget <n> | Semantic chunk budget. |
--max-concurrency <n> | Concurrent model requests. |
--api-timeout <seconds> | Request timeout. |
--force | Permit replacement with a smaller graph after intentional changes. |
--timing | Print stage timings. |
--google-workspace | Explicitly enable Google Workspace shortcut export. |
--cargo | Include Cargo workspace dependency information. |
--postgres <DSN> | Read a PostgreSQL schema with the relevant extra and credentials. |
Examples
graphify extract . --code-only
graphify extract ./docs --backend ollama --max-concurrency 2
graphify extract ./src --code-only --timing
Outputs and failures
Inspect the console summary and generated report before using the graph. Missing grammars, unsupported files, model errors, partial results, and the smaller-graph guard can affect what was written.--force is an explicit override, not a routine remedy for an unexplained failure.
See headless extraction for provider setup and outputs for the saved files.
Assistant
Responses are generated using AI and may contain mistakes.