Skip to content

Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.

docs: directory parse reads ingest-supported files, not only txt/md

Frankie-Xucd7a7fa3ecdc
diff --git a/docs/en/cli/commands/parse.md b/docs/en/cli/commands/parse.md
index 9f2a079..e0edf9c 100644
--- a/docs/en/cli/commands/parse.md
+++ b/docs/en/cli/commands/parse.md
@@ -86,7 +86,7 @@ he parse document.md -o ./output/ -l en
### Process a Directory
-Extract from all `.md` and `.txt` files in a directory:
+Directory mode is non-recursive and reads supported files in that folder (`.txt`/`.md` always; PDF/DOCX/… when `hyperextract[ingest]` is installed); other regular files at the same level are skipped with a warning.
```bash
he parse ./documents/ -t general/concept_graph -o ./output/ -l en
diff --git a/docs/zh/cli/commands/parse.md b/docs/zh/cli/commands/parse.md
index 014f105..fa1d852 100644
--- a/docs/zh/cli/commands/parse.md
+++ b/docs/zh/cli/commands/parse.md
@@ -82,7 +82,7 @@ he parse document.md -o ./output/ -l zh
### 处理目录
-从目录中的所有 `.md` 和 `.txt` 文件提取:
+目录模式非递归:读取该目录下受支持的文件(`.txt`/`.md` 始终支持;安装 `hyperextract[ingest]` 后还包括 PDF/DOCX 等);同层其它常规文件会 warning 并跳过:
```bash
he parse ./documents/ -t general/concept_graph -o ./output/ -l zh