# SmartChunkLLM
Türkçe hukuki belgeler için gelişmiş semantik metin parçalama ve analiz sistemi.
## 🚀 Kurulum
### Gereksinimler
- Python 3.8+
- pip veya conda
### Temel Kurulum
```bash
# Projeyi klonlayın
git clone <repository-url>
cd smartchunkllm
# Sanal ortam oluşturun (önerilen)
python -m venv venv
source venv/bin/activate # Linux/Mac
# veya
venv\Scripts\activate # Windows
# Bağımlılıkları yükleyin
pip install -r requirements.txt
# Paketi geliştirme modunda yükleyin
pip install -e .
```
### İsteğe Bağlı Bağımlılıklar
```bash
# OCR desteği için
pip install "smartchunkllm[ocr]"
# Web arayüzü için
pip install "smartchunkllm[web]"
# Türkçe NLP desteği için
pip install "smartchunkllm[turkish]"
# Tüm özellikler için
pip install "smartchunkllm[all]"
```
## 📖 Kullanım
### Komut Satırı Arayüzü (CLI)
#### PDF Belgelerini İşleme
```bash
# Temel PDF işleme
smartchunk process document.pdf
# OCR ile taranmış PDF işleme
smartchunk process document.pdf --ocr
# Düzen algılama ile
smartchunk process document.pdf --layout-detection
# Çıktıyı JSON formatında kaydetme
smartchunk process document.pdf --output results.json --format json
# Özel parça boyutu ile
smartchunk process document.pdf --chunk-size 1000 --overlap 200
```
#### Ham Metin İşleme
```bash
# Metin dosyasını parçalama
smartchunk chunk-text input.txt --output chunks.json
# Farklı strateji ile
smartchunk chunk-text input.txt --strategy semantic --quality high
```
#### Sistem Bilgileri
```bash
# Sistem durumunu kontrol etme
smartchunk info
# Kullanım örneklerini görme
smartchunk examples
```
### Python API
#### Temel Kullanım
```python
from smartchunkllm import SmartChunkLLM, ChunkingStrategy, QualityLevel
# SmartChunkLLM örneği oluşturma
chunker = SmartChunkLLM(
strategy=ChunkingStrategy.SEMANTIC,
quality_level=QualityLevel.HIGH,
chunk_size=800,
overlap=150
)
# PDF belgesi işleme
result = chunker.process_pdf("document.pdf")
# Sonuçları görüntüleme
for chunk in result.chunks:
print(f"Chunk {chunk.id}: {chunk.text[:100]}...")
print(f"Kalite Skoru: {chunk.quality_score}")
print(f"Güven Düzeyi: {chunk.confidence}")
print("---")
```
#### Gelişmiş Kullanım
```python
from smartchunkllm import (
SmartChunkLLM,
LLMProvider,
EmbeddingModel,
ClusteringAlgorithm
)
# Gelişmiş yapılandırma
chunker = SmartChunkLLM(
strategy=ChunkingStrategy.HYBRID,
quality_level=QualityLevel.PREMIUM,
llm_provider=LLMProvider.OPENAI,
embedding_model=EmbeddingModel.OPENAI_ADA_002,
clustering_algorithm=ClusteringAlgorithm.HIERARCHICAL,
enable_ocr=True,
enable_layout_detection=True,
language="tr"
)
# Metin işleme
text = "Uzun hukuki metin..."
result = chunker.process_text(text)
# Kalite metrikleri
print(f"Ortalama Kalite: {result.metrics.average_quality}")
print(f"İşlem Süresi: {result.metrics.processing_time}s")
print(f"Bellek Kullanımı: {result.metrics.memory_usage}MB")
```
#### Hukuki Belge Analizi
```python
from smartchunkllm.legal import LegalAnalyzer
# Hukuki analiz
analyzer = LegalAnalyzer()
analysis = analyzer.analyze_document("contract.pdf")
# Sonuçları görüntüleme
print(f"Belge Türü: {analysis.document_type}")
print(f"Tespit Edilen Maddeler: {len(analysis.articles)}")
print(f"Anahtar Terimler: {analysis.key_terms}")
```
### Yapılandırma
#### Ortam Değişkenleri
```bash
# API anahtarları
export OPENAI_API_KEY="your-openai-key"
export ANTHROPIC_API_KEY="your-anthropic-key"
export COHERE_API_KEY="your-cohere-key"
# Ollama yapılandırması
export OLLAMA_HOST="http://localhost:11434"
# Loglama seviyesi
export SMARTCHUNK_LOG_LEVEL="INFO"
# Bellek limiti (MB)
export SMARTCHUNK_MEMORY_LIMIT="2048"
```
#### Yapılandırma Dosyası
```yaml
# config.yaml
chunking:
strategy: "semantic"
chunk_size: 800
overlap: 150
quality_level: "high"
llm:
provider: "openai"
model: "gpt-4"
temperature: 0.1
max_tokens: 2000
embedding:
model: "openai-ada-002"
batch_size: 100
processing:
enable_ocr: true
enable_layout_detection: true
language: "tr"
max_workers: 4
logging:
level: "INFO"
format: "structured"
file: "smartchunk.log"
```
## 🔧 Özellikler
### ✨ Temel Özellikler
- **Semantik Parçalama**: İçerik anlamına göre akıllı metin bölme
- **Çoklu Strateji**: Sabit boyut, semantik, hibrit parçalama
- **Kalite Değerlendirme**: Otomatik parça kalitesi analizi
- **Türkçe Desteği**: Özelleşmiş Türkçe NLP işlemleri
### 📄 PDF İşleme
- **OCR Desteği**: Taranmış belgeleri metin çıkarma
- **Düzen Algılama**: Sayfa düzenini koruyarak işleme
- **Font Analizi**: Metin biçimlendirme bilgilerini koruma
- **Tablo Çıkarma**: Yapılandırılmış veri tespiti
### 🤖 AI/ML Entegrasyonu
- **Çoklu LLM Desteği**: OpenAI, Anthropic, Cohere, Ollama
- **Embedding Modelleri**: Çeşitli gömme modeli seçenekleri
- **Kümeleme**: Benzer içerikleri gruplandırma
- **Kalite Analizi**: AI destekli kalite değerlendirme
### ⚖️ Hukuki Belge Desteği
- **Belge Türü Tespiti**: Sözleşme, kanun, yönetmelik analizi
- **Madde Çıkarma**: Hukuki maddeleri otomatik tespit
- **Anahtar Terim Analizi**: Hukuki terim vurgulama
- **Referans Takibi**: Çapraz referans analizi
### 🔍 Monitoring ve Profiling
- **Performans İzleme**: Gerçek zamanlı performans metrikleri
- **Bellek Yönetimi**: Otomatik bellek optimizasyonu
- **Loglama**: Yapılandırılmış günlük kayıtları
- **Hata Yönetimi**: Kapsamlı hata yakalama ve raporlama
## 📊 Çıktı Formatları
### JSON Çıktısı
```json
{
"chunks": [
{
"id": "chunk_001",
"text": "Metin içeriği...",
"metadata": {
"page_number": 1,
"position": {"x": 100, "y": 200},
"font_info": {"family": "Arial", "size": 12},
"quality_score": 0.95,
"confidence": 0.88
}
}
],
"metrics": {
"total_chunks": 25,
"average_quality": 0.92,
"processing_time": 15.3,
"memory_usage": 256
}
}
```
### Markdown Çıktısı
```markdown
# Belge Analiz Sonuçları
## Chunk 1
**Kalite Skoru**: 0.95
**Sayfa**: 1
**Pozisyon**: (100, 200)
Metin içeriği...
---
## Chunk 2
...
```
## 🛠️ Geliştirme
### Test Çalıştırma
```bash
# Tüm testleri çalıştırma
python -m pytest tests/
# Belirli bir test dosyası
python -m pytest tests/test_chunking.py
# Kapsam raporu ile
python -m pytest --cov=smartchunkllm tests/
```
### Kod Kalitesi
```bash
# Kod formatı kontrolü
black smartchunkllm/
flake8 smartchunkllm/
# Tip kontrolü
mypy smartchunkllm/
```
## 📝 Lisans
MIT License - Detaylar için `LICENSE` dosyasına bakınız.
## 🤝 Katkıda Bulunma
1. Projeyi fork edin
2. Feature branch oluşturun (`git checkout -b feature/amazing-feature`)
3. Değişikliklerinizi commit edin (`git commit -m 'Add amazing feature'`)
4. Branch'inizi push edin (`git push origin feature/amazing-feature`)
5. Pull Request oluşturun
## 📞 Destek
Sorularınız için:
- GitHub Issues
- Dokümantasyon: [Link]
- E-posta: [E-posta adresi]
---
**SmartChunkLLM** - Türkçe hukuki belgeler için akıllı metin analizi 🚀
Raw data
{
"_id": null,
"home_page": "https://github.com/smartchunkllm/smartchunkllm",
"name": "smartchunkllm",
"maintainer": "SmartChunkLLM Team",
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": "SmartChunkLLM Team <info@smartchunkllm.com>",
"keywords": "legal, documents, semantic, chunking, nlp, ai, llm, pdf, turkish, law, embedding, clustering, transformers, ollama, openai, anthropic",
"author": "SmartChunkLLM Team",
"author_email": "SmartChunkLLM Team <info@smartchunkllm.com>",
"download_url": "https://files.pythonhosted.org/packages/6a/4e/40e8404d102e46c0265686c56a380601f73794df83236e058fdb05c9aa4d/smartchunkllm-0.1.7.tar.gz",
"platform": "any",
"description": "# SmartChunkLLM\n\nT\u00fcrk\u00e7e hukuki belgeler i\u00e7in geli\u015fmi\u015f semantik metin par\u00e7alama ve analiz sistemi.\n\n## \ud83d\ude80 Kurulum\n\n### Gereksinimler\n- Python 3.8+\n- pip veya conda\n\n### Temel Kurulum\n\n```bash\n# Projeyi klonlay\u0131n\ngit clone <repository-url>\ncd smartchunkllm\n\n# Sanal ortam olu\u015fturun (\u00f6nerilen)\npython -m venv venv\nsource venv/bin/activate # Linux/Mac\n# veya\nvenv\\Scripts\\activate # Windows\n\n# Ba\u011f\u0131ml\u0131l\u0131klar\u0131 y\u00fckleyin\npip install -r requirements.txt\n\n# Paketi geli\u015ftirme modunda y\u00fckleyin\npip install -e .\n```\n\n### \u0130ste\u011fe Ba\u011fl\u0131 Ba\u011f\u0131ml\u0131l\u0131klar\n\n```bash\n# OCR deste\u011fi i\u00e7in\npip install \"smartchunkllm[ocr]\"\n\n# Web aray\u00fcz\u00fc i\u00e7in\npip install \"smartchunkllm[web]\"\n\n# T\u00fcrk\u00e7e NLP deste\u011fi i\u00e7in\npip install \"smartchunkllm[turkish]\"\n\n# T\u00fcm \u00f6zellikler i\u00e7in\npip install \"smartchunkllm[all]\"\n```\n\n## \ud83d\udcd6 Kullan\u0131m\n\n### Komut Sat\u0131r\u0131 Aray\u00fcz\u00fc (CLI)\n\n#### PDF Belgelerini \u0130\u015fleme\n\n```bash\n# Temel PDF i\u015fleme\nsmartchunk process document.pdf\n\n# OCR ile taranm\u0131\u015f PDF i\u015fleme\nsmartchunk process document.pdf --ocr\n\n# D\u00fczen alg\u0131lama ile\nsmartchunk process document.pdf --layout-detection\n\n# \u00c7\u0131kt\u0131y\u0131 JSON format\u0131nda kaydetme\nsmartchunk process document.pdf --output results.json --format json\n\n# \u00d6zel par\u00e7a boyutu ile\nsmartchunk process document.pdf --chunk-size 1000 --overlap 200\n```\n\n#### Ham Metin \u0130\u015fleme\n\n```bash\n# Metin dosyas\u0131n\u0131 par\u00e7alama\nsmartchunk chunk-text input.txt --output chunks.json\n\n# Farkl\u0131 strateji ile\nsmartchunk chunk-text input.txt --strategy semantic --quality high\n```\n\n#### Sistem Bilgileri\n\n```bash\n# Sistem durumunu kontrol etme\nsmartchunk info\n\n# Kullan\u0131m \u00f6rneklerini g\u00f6rme\nsmartchunk examples\n```\n\n### Python API\n\n#### Temel Kullan\u0131m\n\n```python\nfrom smartchunkllm import SmartChunkLLM, ChunkingStrategy, QualityLevel\n\n# SmartChunkLLM \u00f6rne\u011fi olu\u015fturma\nchunker = SmartChunkLLM(\n strategy=ChunkingStrategy.SEMANTIC,\n quality_level=QualityLevel.HIGH,\n chunk_size=800,\n overlap=150\n)\n\n# PDF belgesi i\u015fleme\nresult = chunker.process_pdf(\"document.pdf\")\n\n# Sonu\u00e7lar\u0131 g\u00f6r\u00fcnt\u00fcleme\nfor chunk in result.chunks:\n print(f\"Chunk {chunk.id}: {chunk.text[:100]}...\")\n print(f\"Kalite Skoru: {chunk.quality_score}\")\n print(f\"G\u00fcven D\u00fczeyi: {chunk.confidence}\")\n print(\"---\")\n```\n\n#### Geli\u015fmi\u015f Kullan\u0131m\n\n```python\nfrom smartchunkllm import (\n SmartChunkLLM, \n LLMProvider, \n EmbeddingModel,\n ClusteringAlgorithm\n)\n\n# Geli\u015fmi\u015f yap\u0131land\u0131rma\nchunker = SmartChunkLLM(\n strategy=ChunkingStrategy.HYBRID,\n quality_level=QualityLevel.PREMIUM,\n llm_provider=LLMProvider.OPENAI,\n embedding_model=EmbeddingModel.OPENAI_ADA_002,\n clustering_algorithm=ClusteringAlgorithm.HIERARCHICAL,\n enable_ocr=True,\n enable_layout_detection=True,\n language=\"tr\"\n)\n\n# Metin i\u015fleme\ntext = \"Uzun hukuki metin...\"\nresult = chunker.process_text(text)\n\n# Kalite metrikleri\nprint(f\"Ortalama Kalite: {result.metrics.average_quality}\")\nprint(f\"\u0130\u015flem S\u00fcresi: {result.metrics.processing_time}s\")\nprint(f\"Bellek Kullan\u0131m\u0131: {result.metrics.memory_usage}MB\")\n```\n\n#### Hukuki Belge Analizi\n\n```python\nfrom smartchunkllm.legal import LegalAnalyzer\n\n# Hukuki analiz\nanalyzer = LegalAnalyzer()\nanalysis = analyzer.analyze_document(\"contract.pdf\")\n\n# Sonu\u00e7lar\u0131 g\u00f6r\u00fcnt\u00fcleme\nprint(f\"Belge T\u00fcr\u00fc: {analysis.document_type}\")\nprint(f\"Tespit Edilen Maddeler: {len(analysis.articles)}\")\nprint(f\"Anahtar Terimler: {analysis.key_terms}\")\n```\n\n### Yap\u0131land\u0131rma\n\n#### Ortam De\u011fi\u015fkenleri\n\n```bash\n# API anahtarlar\u0131\nexport OPENAI_API_KEY=\"your-openai-key\"\nexport ANTHROPIC_API_KEY=\"your-anthropic-key\"\nexport COHERE_API_KEY=\"your-cohere-key\"\n\n# Ollama yap\u0131land\u0131rmas\u0131\nexport OLLAMA_HOST=\"http://localhost:11434\"\n\n# Loglama seviyesi\nexport SMARTCHUNK_LOG_LEVEL=\"INFO\"\n\n# Bellek limiti (MB)\nexport SMARTCHUNK_MEMORY_LIMIT=\"2048\"\n```\n\n#### Yap\u0131land\u0131rma Dosyas\u0131\n\n```yaml\n# config.yaml\nchunking:\n strategy: \"semantic\"\n chunk_size: 800\n overlap: 150\n quality_level: \"high\"\n\nllm:\n provider: \"openai\"\n model: \"gpt-4\"\n temperature: 0.1\n max_tokens: 2000\n\nembedding:\n model: \"openai-ada-002\"\n batch_size: 100\n\nprocessing:\n enable_ocr: true\n enable_layout_detection: true\n language: \"tr\"\n max_workers: 4\n\nlogging:\n level: \"INFO\"\n format: \"structured\"\n file: \"smartchunk.log\"\n```\n\n## \ud83d\udd27 \u00d6zellikler\n\n### \u2728 Temel \u00d6zellikler\n- **Semantik Par\u00e7alama**: \u0130\u00e7erik anlam\u0131na g\u00f6re ak\u0131ll\u0131 metin b\u00f6lme\n- **\u00c7oklu Strateji**: Sabit boyut, semantik, hibrit par\u00e7alama\n- **Kalite De\u011ferlendirme**: Otomatik par\u00e7a kalitesi analizi\n- **T\u00fcrk\u00e7e Deste\u011fi**: \u00d6zelle\u015fmi\u015f T\u00fcrk\u00e7e NLP i\u015flemleri\n\n### \ud83d\udcc4 PDF \u0130\u015fleme\n- **OCR Deste\u011fi**: Taranm\u0131\u015f belgeleri metin \u00e7\u0131karma\n- **D\u00fczen Alg\u0131lama**: Sayfa d\u00fczenini koruyarak i\u015fleme\n- **Font Analizi**: Metin bi\u00e7imlendirme bilgilerini koruma\n- **Tablo \u00c7\u0131karma**: Yap\u0131land\u0131r\u0131lm\u0131\u015f veri tespiti\n\n### \ud83e\udd16 AI/ML Entegrasyonu\n- **\u00c7oklu LLM Deste\u011fi**: OpenAI, Anthropic, Cohere, Ollama\n- **Embedding Modelleri**: \u00c7e\u015fitli g\u00f6mme modeli se\u00e7enekleri\n- **K\u00fcmeleme**: Benzer i\u00e7erikleri grupland\u0131rma\n- **Kalite Analizi**: AI destekli kalite de\u011ferlendirme\n\n### \u2696\ufe0f Hukuki Belge Deste\u011fi\n- **Belge T\u00fcr\u00fc Tespiti**: S\u00f6zle\u015fme, kanun, y\u00f6netmelik analizi\n- **Madde \u00c7\u0131karma**: Hukuki maddeleri otomatik tespit\n- **Anahtar Terim Analizi**: Hukuki terim vurgulama\n- **Referans Takibi**: \u00c7apraz referans analizi\n\n### \ud83d\udd0d Monitoring ve Profiling\n- **Performans \u0130zleme**: Ger\u00e7ek zamanl\u0131 performans metrikleri\n- **Bellek Y\u00f6netimi**: Otomatik bellek optimizasyonu\n- **Loglama**: Yap\u0131land\u0131r\u0131lm\u0131\u015f g\u00fcnl\u00fck kay\u0131tlar\u0131\n- **Hata Y\u00f6netimi**: Kapsaml\u0131 hata yakalama ve raporlama\n\n## \ud83d\udcca \u00c7\u0131kt\u0131 Formatlar\u0131\n\n### JSON \u00c7\u0131kt\u0131s\u0131\n```json\n{\n \"chunks\": [\n {\n \"id\": \"chunk_001\",\n \"text\": \"Metin i\u00e7eri\u011fi...\",\n \"metadata\": {\n \"page_number\": 1,\n \"position\": {\"x\": 100, \"y\": 200},\n \"font_info\": {\"family\": \"Arial\", \"size\": 12},\n \"quality_score\": 0.95,\n \"confidence\": 0.88\n }\n }\n ],\n \"metrics\": {\n \"total_chunks\": 25,\n \"average_quality\": 0.92,\n \"processing_time\": 15.3,\n \"memory_usage\": 256\n }\n}\n```\n\n### Markdown \u00c7\u0131kt\u0131s\u0131\n```markdown\n# Belge Analiz Sonu\u00e7lar\u0131\n\n## Chunk 1\n**Kalite Skoru**: 0.95 \n**Sayfa**: 1 \n**Pozisyon**: (100, 200)\n\nMetin i\u00e7eri\u011fi...\n\n---\n\n## Chunk 2\n...\n```\n\n## \ud83d\udee0\ufe0f Geli\u015ftirme\n\n### Test \u00c7al\u0131\u015ft\u0131rma\n```bash\n# T\u00fcm testleri \u00e7al\u0131\u015ft\u0131rma\npython -m pytest tests/\n\n# Belirli bir test dosyas\u0131\npython -m pytest tests/test_chunking.py\n\n# Kapsam raporu ile\npython -m pytest --cov=smartchunkllm tests/\n```\n\n### Kod Kalitesi\n```bash\n# Kod format\u0131 kontrol\u00fc\nblack smartchunkllm/\nflake8 smartchunkllm/\n\n# Tip kontrol\u00fc\nmypy smartchunkllm/\n```\n\n## \ud83d\udcdd Lisans\n\nMIT License - Detaylar i\u00e7in `LICENSE` dosyas\u0131na bak\u0131n\u0131z.\n\n## \ud83e\udd1d Katk\u0131da Bulunma\n\n1. Projeyi fork edin\n2. Feature branch olu\u015fturun (`git checkout -b feature/amazing-feature`)\n3. De\u011fi\u015fikliklerinizi commit edin (`git commit -m 'Add amazing feature'`)\n4. Branch'inizi push edin (`git push origin feature/amazing-feature`)\n5. Pull Request olu\u015fturun\n\n## \ud83d\udcde Destek\n\nSorular\u0131n\u0131z i\u00e7in:\n- GitHub Issues\n- Dok\u00fcmantasyon: [Link]\n- E-posta: [E-posta adresi]\n\n---\n\n**SmartChunkLLM** - T\u00fcrk\u00e7e hukuki belgeler i\u00e7in ak\u0131ll\u0131 metin analizi \ud83d\ude80\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Advanced Legal Document Semantic Chunking System",
"version": "0.1.7",
"project_urls": {
"Bug Reports": "https://github.com/smartchunkllm/smartchunkllm/issues",
"Changelog": "https://github.com/smartchunkllm/smartchunkllm/blob/main/CHANGELOG.md",
"Documentation": "https://smartchunkllm.readthedocs.io/",
"Download": "https://github.com/smartchunkllm/smartchunkllm/archive/v1.0.0.tar.gz",
"Homepage": "https://github.com/smartchunkllm/smartchunkllm",
"Repository": "https://github.com/smartchunkllm/smartchunkllm"
},
"split_keywords": [
"legal",
" documents",
" semantic",
" chunking",
" nlp",
" ai",
" llm",
" pdf",
" turkish",
" law",
" embedding",
" clustering",
" transformers",
" ollama",
" openai",
" anthropic"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "c7692bf070e4a6901283edeb98619b7c7e501bc961b433d35f5c574bc0858265",
"md5": "b871b757c2257c5b791cb93de758e667",
"sha256": "cda4ccb875c987888750a7e45eaf00e7a76296c91d1df130f0741793f21f8757"
},
"downloads": -1,
"filename": "smartchunkllm-0.1.7-py3-none-any.whl",
"has_sig": false,
"md5_digest": "b871b757c2257c5b791cb93de758e667",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 160014,
"upload_time": "2025-08-10T21:52:22",
"upload_time_iso_8601": "2025-08-10T21:52:22.258100Z",
"url": "https://files.pythonhosted.org/packages/c7/69/2bf070e4a6901283edeb98619b7c7e501bc961b433d35f5c574bc0858265/smartchunkllm-0.1.7-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "6a4e40e8404d102e46c0265686c56a380601f73794df83236e058fdb05c9aa4d",
"md5": "783a7d2c171dac9e0f66abd01c3ad847",
"sha256": "cf917a524c26a029f507bb85ef87bde651981f17000dca4f7af6f43cbaba37b3"
},
"downloads": -1,
"filename": "smartchunkllm-0.1.7.tar.gz",
"has_sig": false,
"md5_digest": "783a7d2c171dac9e0f66abd01c3ad847",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 149397,
"upload_time": "2025-08-10T21:52:24",
"upload_time_iso_8601": "2025-08-10T21:52:24.011256Z",
"url": "https://files.pythonhosted.org/packages/6a/4e/40e8404d102e46c0265686c56a380601f73794df83236e058fdb05c9aa4d/smartchunkllm-0.1.7.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-10 21:52:24",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "smartchunkllm",
"github_project": "smartchunkllm",
"github_not_found": true,
"lcname": "smartchunkllm"
}
JSON
