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: add AutoDocument to list-template type legend

Frankie-Xuaebb5811d791
diff --git a/docs/en/cli/commands/list.md b/docs/en/cli/commands/list.md
index 128188a..b35a6c8 100644
--- a/docs/en/cli/commands/list.md
+++ b/docs/en/cli/commands/list.md
@@ -49,6 +49,7 @@ Templates are organized by output type:
| Type | Templates |
|------|-----------|
+| `document` | Chunked raw text without LLM extraction |
| `model` | Structured data extraction |
| `list` | Ordered collections |
| `set` | Deduplicated collections |
diff --git a/docs/zh/cli/commands/list.md b/docs/zh/cli/commands/list.md
index 999db49..2f3f3de 100644
--- a/docs/zh/cli/commands/list.md
+++ b/docs/zh/cli/commands/list.md
@@ -49,6 +49,7 @@ medicine/drug_interaction graph Drug interaction network
| 类型 | 模板 |
|------|-----------|
+| `document` | 分块原文,不跑 LLM 抽取 |
| `model` | 结构化数据提取 |
| `list` | 有序集合 |
| `set` | 去重集合 |
diff --git a/hyperextract/cli/commands/list.py b/hyperextract/cli/commands/list.py
index 8f9fc12..2b8907f 100644
--- a/hyperextract/cli/commands/list.py
+++ b/hyperextract/cli/commands/list.py
@@ -99,8 +99,12 @@ def template(
console.print(f"\n[dim]Total: {len(templates)} templates[/dim]")
console.print()
console.print("[dim]Type explanations:[/dim]")
+ console.print(" [cyan]document[/cyan] - Chunked raw text (no LLM extraction)")
console.print(" [cyan]graph[/cyan] - Entity-relationship graph (binary relations)")
console.print(" [cyan]hypergraph[/cyan] - Hypergraph (n-ary relations)")
+ console.print(" [cyan]temporal_graph[/cyan] - Graph with time context")
+ console.print(" [cyan]spatial_graph[/cyan] - Graph with location context")
+ console.print(" [cyan]spatio_temporal_graph[/cyan] - Graph with time and location")
console.print(" [cyan]list[/cyan] - Key-value list")
console.print(" [cyan]model[/cyan] - Structured data model")
console.print(" [cyan]set[/cyan] - Entity collection")
diff --git a/hyperextract/types/__init__.py b/hyperextract/types/__init__.py
index 51bd87d..49e6cca 100644
--- a/hyperextract/types/__init__.py
+++ b/hyperextract/types/__init__.py
@@ -8,6 +8,7 @@ handling the complexities of LLM interaction, text chunking, and result merging
| Class | Structure | Core Use Case | Key Feature |
| :--- | :--- | :--- | :--- |
+| **`AutoDocument`** | Text Chunks | Raw corpus retrieval | No LLM extraction; stores and searches chunks |
| **`AutoModel`** | Single Object | Document Summaries, Metadata | Merges all chunks into ONE consistent object |
| **`AutoList`** | List[Item] | Event Logs, Todo Lists | Appends items from all chunks commonly |
| **`AutoSet`** | Set[Item] | Entity Registries, Glossaries | Deduplicates items by key & merges details |
@@ -20,6 +21,9 @@ handling the complexities of LLM interaction, text chunking, and result merging
# 📚 Detailed Scope Description
## 1. Scalar & Document Types (标量与文档型)
+* **`AutoDocument`**: Designed for **"One Document -> Retrievable Chunks"**.
+ * *Scope*: Keep the source text as chunks when you do not want LLM extraction (baseline retrieval, or a fallback when extraction quality/cost is a concern).
+ * *Logic*: `feed_text` splits text, stores chunks, and `search` returns the raw chunks. YAML `type: document`.
* **`AutoModel`**: Designed for **"One Document -> One Object"**.
* *Scope*: When you need to summarize a whole file into a single structure (e.g., "Research Report" with fields for summary, author, conclusion).
* *Logic*: It treats every text chunk as a partial view of the *same* object and uses LLM to merge them.
diff --git a/tests/cli/test_verbose.py b/tests/cli/test_verbose.py
index dffaa27..dbb96ca 100644
--- a/tests/cli/test_verbose.py
+++ b/tests/cli/test_verbose.py
@@ -114,6 +114,15 @@ class TestCLINoVerboseFlag:
result = runner.invoke(app, ["list", "template", "--help"])
assert result.exit_code == 0
+ def test_list_template_legend_includes_document(self):
+ """Type explanations mention AutoDocument's YAML type."""
+ result = runner.invoke(app, ["list", "template"])
+ assert result.exit_code == 0, result.output
+ assert "document" in result.output
+ assert "temporal_graph" in result.output
+ assert "spatial_graph" in result.output
+ assert "spatio_temporal_graph" in result.output
+
def test_config_help_works(self):
"""he config --help exits cleanly."""
result = runner.invoke(app, ["config", "--help"])