@xberg-io/opencode-xberg 1.0.5 → 1.0.9
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.opencode/plugins/xberg.js +1 -1
- package/README.md +3 -3
- package/package.json +2 -2
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
// AI-RULEZ :: GENERATED FILE — DO NOT EDIT
|
|
2
2
|
// Content-Hash: blake3:a176d5615df7d9fc0f850b5d83d3355f87d3045645f185d67c0d1e5edfb4a6c6
|
|
3
|
-
// Source-Hash: blake3:
|
|
3
|
+
// Source-Hash: blake3:71849ab3b4d251b20078a2489fa8f529b5304927bf6d5631590df6ed42f3b160
|
|
4
4
|
// Schema-Version: v1
|
|
5
5
|
|
|
6
6
|
import {tool} from "@opencode-ai/plugin";
|
package/README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# xberg
|
|
2
2
|
|
|
3
|
-
Extract text, tables, metadata, and images from
|
|
3
|
+
Extract text, tables, metadata, and images from 101 document formats — PDF, Office, images with OCR, HTML, email, archives, academic — using the local `xberg` CLI in your agent.
|
|
4
4
|
|
|
5
5
|
<!-- ~keep TODO: add screenshot -->
|
|
6
6
|
|
|
@@ -51,7 +51,7 @@ sudo apt install tesseract-ocr-* # Debian/Ubuntu
|
|
|
51
51
|
|
|
52
52
|
| Skill | Trigger |
|
|
53
53
|
|-------|---------|
|
|
54
|
-
| **xberg** | Extract text, tables, metadata, and images from
|
|
54
|
+
| **xberg** | Extract text, tables, metadata, and images from 101 document formats (PDF, Office, images, HTML, email, archives, academic) using Xberg. Use when writing code that calls Xberg APIs in Python, Node.js/TypeScript, Rust, or CLI. Covers installation, extraction (sync/async), configuration (OCR, chunking, output format), batch processing, error handling, and plugins. |
|
|
55
55
|
| **extracting-with-ocr** | Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer. Covers OCR backends, language packs, force-OCR, and performance tuning. |
|
|
56
56
|
| **extracting-tables** | Use when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown / JSON cells), and known limits. |
|
|
57
57
|
| **chunking** | Use when splitting extracted text into chunks for LLM context windows or RAG ingestion. Covers chunk size, overlap, markdown/yaml/semantic chunkers, tokenizer-based sizing, and the standalone `chunk` command. |
|
|
@@ -65,7 +65,7 @@ sudo apt install tesseract-ocr-* # Debian/Ubuntu
|
|
|
65
65
|
|-----------|---------|
|
|
66
66
|
| **CLI Reference** | All commands, flags, config precedence, exit codes |
|
|
67
67
|
| **Configuration Reference** | TOML/YAML/JSON formats, auto-discovery, env vars, full schema |
|
|
68
|
-
| **Supported Formats** | All
|
|
68
|
+
| **Supported Formats** | All 101 formats (115 file extensions) with file extensions and MIME types |
|
|
69
69
|
| **Python API Reference** | All functions, config classes, plugin protocols, exact signatures |
|
|
70
70
|
| **Node.js API Reference** | All functions, TypeScript interfaces, worker pool APIs |
|
|
71
71
|
| **Rust API Reference** | All functions with feature gates, structs, Cargo.toml examples |
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@xberg-io/opencode-xberg",
|
|
3
|
-
"version": "1.0.
|
|
4
|
-
"description": "Local document extraction: text, tables, metadata, images from
|
|
3
|
+
"version": "1.0.9",
|
|
4
|
+
"description": "Local document extraction: text, tables, metadata, images from 101 formats with optional OCR.",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"document-intelligence",
|
|
7
7
|
"extraction",
|