xberg 1.0.0

High-performance document intelligence library for Rust. Extract text, metadata, and structured data from PDFs, Office documents, images, and 98 formats and 306 programming languages via tree-sitter code intelligence with async/sync APIs.
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29

{
  "id": "generic_document",
  "version": "v1",
  "schema_name": "generic_document",
  "description": "Extract a title and one-sentence summary from any document. Synthetic toy preset shipped with the OSS library.",
  "category": "other",
  "tags": [],
  "schema": {
    "type": "object",
    "properties": {
      "title": {
        "type": "string",
        "description": "The document title or a short descriptive heading."
      },
      "summary": {
        "type": "string",
        "description": "A single sentence capturing the main point of the document."
      }
    },
    "required": [
      "title",
      "summary"
    ]
  },
  "system_prompt": "Extract a title and one-sentence summary from the document.",
  "merge_mode": "object_merge",
  "preferred_call_mode": "text_only",
  "emit_citations": false
}