Skip to content

Commit 9bd6300

Browse files
committed
docs: update README.md
1 parent c4ea508 commit 9bd6300

File tree

4 files changed

+31
-4
lines changed

4 files changed

+31
-4
lines changed

.github/workflows/pylint.yml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@ jobs:
77
runs-on: ubuntu-latest
88
strategy:
99
matrix:
10-
python-version: ["3.9", "3.10"]
10+
python-version: ["3.10"]
1111
steps:
1212
- uses: actions/checkout@v4
1313
- name: Set up Python ${{ matrix.python-version }}

README.md

Lines changed: 27 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -12,6 +12,33 @@ Available on PyPI: https://pypi.org/project/rag-chunk/
1212
- ✅ CLI with table/JSON/CSV output formats
1313
- ✅ Realistic example corpus included
1414

15+
### Demo
16+
[View the demo](assets/demo.gif)
17+
18+
## 🚀 Roadmap
19+
20+
`rag-chunk` is actively developed! Here's the plan to move from a basic tool to a full-featured chunking workbench.
21+
22+
### ✅ Version 0.1 – Launched
23+
* [x] Core CLI engine (`click`)
24+
* [x] Markdown (`.md`) file parsing (`mistune`)
25+
* [x] Basic chunking strategies: `fixed-size` and `paragraph` (word-based)
26+
* [x] Evaluation harness: calculate **Recall score** from a `test-file.json`
27+
* [x] **PyPI Publication:** Installable via `pip install rag-chunk`
28+
29+
### 🎯 Version 0.2 – In Progress
30+
* [x] CLI output formatting (`rich` tables)
31+
* [x] **Demo GIF:** Showcase the tool in action in the README
32+
* [ ] **`tiktoken` Support:** Add `--use-tiktoken` flag for precise, token-based chunking
33+
* [ ] CLI/UX improvements and bug fixes
34+
35+
### 📈 Version 1.0 – Planned
36+
* [ ] **More Strategies:** Add advanced strategies like `RecursiveCharacterTextSplitter`, `HierarchicalChunker`
37+
* [ ] **More File Types:** Support `.txt`, `.rst`, and other plain text formats
38+
* [ ] **Export & Logging:** Save results as JSON/CSV, optional MLFlow integration
39+
* [ ] **Benchmarking Mode:** Compare chunking strategies automatically
40+
41+
1542
### Installation
1643
```bash
1744
pip install rag-chunk

demo.gif

64.1 KB
Loading

src/cli.py

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -15,10 +15,10 @@
1515
from rich.table import Table
1616

1717
RICH_AVAILABLE = True
18-
console = Console()
18+
CONSOLE = Console()
1919
except ImportError: # pragma: no cover - optional dependency
2020
RICH_AVAILABLE = False
21-
console = None
21+
CONSOLE = None
2222

2323

2424
def write_chunks(chunks, strategy: str):
@@ -151,7 +151,7 @@ def _write_results(results, detail, output):
151151
pct_cell,
152152
str(r.get("saved", "")),
153153
)
154-
console.print(table)
154+
CONSOLE.print(table)
155155
return
156156
print(format_table(results))
157157
return

0 commit comments

Comments
 (0)