# Hashub Vector SDK
[](https://badge.fury.io/py/hashub-vector)
[](https://www.python.org/downloads/)
[](https://opensource.org/licenses/MIT)
[](https://pepy.tech/project/hashub-vector)
**High-quality multilingual text embeddings with Turkish excellence** 🇹🇷
The official Python SDK for Hashub Vector API - providing state-of-the-art text embeddings with exceptional Turkish language support and 80+ other languages.
## 🚀 Features
- **6 Premium Models** - From ultra-fast to premium quality
- **Turkish Excellence** - Optimized for Turkish market with exceptional Turkish language performance
- **80+ Languages** - Comprehensive multilingual support
- **Async/Sync Support** - Both synchronous and asynchronous operations
- **OpenAI Compatible** - Drop-in replacement for OpenAI embeddings
- **Smart Retry Logic** - Automatic retries with exponential backoff
- **Type Safety** - Full type hints and validation
- **Production Ready** - Built for scale with rate limiting and error handling
## 📦 Installation
```bash
pip install hashub-vector
```
For development with all extras:
```bash
pip install hashub-vector[dev,examples]
```
## 🏃♂️ Quick Start
```python
from hashub_vector import HashubVector
# Initialize client
client = HashubVector(api_key="your-api-key")
# Single text embedding
response = client.vectorize("Merhaba dünya! Hashub ile güçlü vektör embedding'ler.")
print(f"Vector dimension: {response.dimension}")
print(f"First 5 dimensions: {response.vector[:5]}")
# Batch processing
texts = [
"Artificial intelligence is transforming the world",
"Yapay zeka dünyayı dönüştürüyor",
"L'intelligence artificielle transforme le monde"
]
batch_response = client.vectorize_batch(texts, model="gte_base")
print(f"Processed {batch_response.count} texts")
print(f"Total tokens: {batch_response.total_tokens}")
# Calculate similarity
similarity = client.similarity(
"Machine learning",
"Makine öğrenmesi"
)
print(f"Similarity: {similarity:.3f}")
```
## 🤖 Async Support
```python
import asyncio
from hashub_vector import HashubVector
async def main():
async with HashubVector(api_key="your-api-key") as client:
# Async single embedding
response = await client.avectorize("Async ile hızlı embedding!")
# Async batch processing
texts = ["Hello", "Merhaba", "Bonjour"]
batch_response = await client.avectorize_batch(texts)
print(f"Processed {batch_response.count} texts asynchronously")
asyncio.run(main())
```
## 🎯 Model Selection Guide
| Model | Best For | Dimension | Max Tokens | Price/1M | Turkish Support |
|-------|----------|-----------|------------|----------|-----------------|
| `gte_base` | Long documents, RAG | 768 | 8,192 | $0.01 | ⭐⭐⭐⭐⭐ |
| `nomic_base` | General purpose | 768 | 2,048 | $0.005 | ⭐⭐⭐⭐ |
| `e5_base` | Search, retrieval | 768 | 512 | $0.003 | ⭐⭐⭐⭐⭐ |
| `mpnet_base` | Q&A, similarity | 768 | 512 | $0.0035 | ⭐⭐⭐⭐⭐ |
| `e5_small` | High volume, speed | 384 | 512 | $0.002 | ⭐⭐⭐⭐ |
| `minilm_base` | Ultra-fast | 384 | 512 | $0.0025 | ⭐⭐⭐⭐ |
### Turkish Market Optimization
All models provide excellent Turkish language support, with `gte_base`, `e5_base`, and `mpnet_base` offering the highest quality for Turkish text processing.
```python
# Optimized for Turkish content
response = client.vectorize(
"Hashub Vector API ile Türkçe metinlerinizi güçlü vektörlere dönüştürün!",
model="gte_base" # Best for Turkish
)
```
## 🔄 OpenAI Compatibility
Drop-in replacement for OpenAI's embedding API:
```python
# OpenAI style (compatible)
response = client.create_embedding(
input="Your text here",
model="e5_base"
)
embedding = response["data"][0]["embedding"]
# Multiple texts
response = client.create_embedding(
input=["Text 1", "Text 2", "Text 3"],
model="gte_base"
)
```
## 🧠 Advanced Features
### Chunking for Long Documents
```python
# Automatic chunking for long texts
response = client.vectorize(
long_document,
model="gte_base",
chunk_size=1024,
chunk_overlap=0.1 # 10% overlap
)
print(f"Document split into {response.chunk_count} chunks")
```
### Model Information
```python
# Get available models
models = client.get_models()
for model in models:
print(f"{model.alias}: {model.description}")
print(f" Dimension: {model.dimension}")
print(f" Max tokens: {model.max_tokens}")
print(f" Price: ${model.price_per_1m_tokens}/1M tokens")
```
### Usage Monitoring
```python
# Check your usage
usage = client.get_usage()
print(f"Tokens used: {usage.tokens_used:,}")
print(f"Usage percentage: {usage.tokens_percentage_used:.1f}%")
```
## 🛠️ Integration Examples
### With LangChain
```python
from hashub_vector import HashubVector
from langchain.embeddings.base import Embeddings
class HashubEmbeddings(Embeddings):
def __init__(self, api_key: str, model: str = "e5_base"):
self.client = HashubVector(api_key=api_key)
self.model = model
def embed_documents(self, texts):
response = self.client.vectorize_batch(texts, model=self.model)
return response.vectors
def embed_query(self, text):
response = self.client.vectorize(text, model=self.model)
return response.vector
# Usage
embeddings = HashubEmbeddings(api_key="your-key", model="gte_base")
```
### With Pinecone
```python
import pinecone
from hashub_vector import HashubVector
# Initialize clients
client = HashubVector(api_key="your-Hashub-key")
pinecone.init(api_key="your-pinecone-key", environment="your-env")
# Create embeddings and store
texts = ["Your documents here..."]
response = client.vectorize_batch(texts, model="gte_base")
# Upsert to Pinecone
index = pinecone.Index("your-index")
vectors = [
(f"doc_{i}", embedding, {"text": text})
for i, (embedding, text) in enumerate(zip(response.vectors, texts))
]
index.upsert(vectors)
```
## 🔧 Error Handling
```python
from hashub_vector import (
HashubVector,
AuthenticationError,
RateLimitError,
QuotaExceededError
)
client = HashubVector(api_key="your-key")
try:
response = client.vectorize("Your text")
except AuthenticationError:
print("Invalid API key")
except RateLimitError as e:
print(f"Rate limited. Retry after {e.retry_after} seconds")
except QuotaExceededError:
print("Quota exceeded. Please upgrade your plan")
```
## 🌍 Language Support
Hashub Vector SDK supports 80+ languages with excellent Turkish performance:
### Tier 1 (Excellent Performance)
🇹🇷 **Turkish**, English, German, French, Spanish, Italian, Portuguese, Dutch, Russian, Polish, Czech, Swedish, Danish, Norwegian, Finnish, Ukrainian
### Tier 2 (Very Good Performance)
Arabic, Persian, Chinese, Japanese, Korean, Hindi, Bengali, Indonesian, Malay, Thai, Vietnamese, Bulgarian, Romanian, Hungarian, Croatian
### Tier 3 (Good Performance)
And 50+ additional languages including African, South Asian, and other European languages.
## 📊 Performance & Pricing
### Speed Benchmarks (texts/second)
- `minilm_base`: ~950 texts/second (Ultra-fast)
- `e5_small`: ~780 texts/second (Fast)
- `e5_base`: ~520 texts/second (Balanced)
- `mpnet_base`: ~465 texts/second (Quality)
- `nomic_base`: ~350 texts/second (Premium)
- `gte_base`: ~280 texts/second (Maximum quality)
### Cost Examples
- **1M tokens with `e5_small`**: $2.00 (Most economical)
- **1M tokens with `e5_base`**: $3.00 (Best value)
- **1M tokens with `gte_base`**: $10.00 (Premium quality)
## 🔐 Authentication
Get your API key from [Hashub Console](https://console.Hashub.dev):
1. Sign up at Hashub Console
2. Create a new API key
3. Choose your pricing tier
4. Start building!
```python
# Environment variable (recommended)
import os
client = HashubVector(api_key=os.getenv("Hashub_API_KEY"))
# Direct initialization
client = HashubVector(api_key="hv-1234567890abcdef...")
```
## 🚦 Rate Limits
| Tier | Requests/Minute | Tokens/Month | Batch Size |
|------|----------------|--------------|------------|
| **Free** | 60 | 100K | 100 texts |
| **Starter** | 300 | 1M | 500 texts |
| **Pro** | 1,000 | 10M | 1,000 texts |
| **Enterprise** | Custom | Custom | Custom |
The SDK automatically handles rate limiting with intelligent retry logic.
## 🧪 Testing
```bash
# Install dev dependencies
pip install hashub-vector[dev]
# Run tests
pytest
# Run with coverage
pytest --cov=hashub_vector
# Run specific test
pytest tests/test_client.py::test_vectorize
```
## 📚 Documentation
- **[Official Documentation](https://docs.vector.Hashub.dev)** - Complete API reference
- **[Model Comparison](https://vector.Hashub.dev/models)** - Detailed model specifications
- **[Pricing](https://vector.Hashub.dev/pricing)** - Transparent pricing information
- **[Examples](./examples/)** - Integration examples and tutorials
## 🤝 Contributing
We welcome contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details.
```bash
# Development setup
git clone https://github.com/hasanbahadir/hashub-vector-sdk.git
cd hashub-vector-sdk
pip install -e ".[dev]"
pre-commit install
```
## 📄 License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
## 🆘 Support
- **Documentation**: [docs.vector.hashub.dev](https://docs.vector.hashub.dev)
- **Email**: [support@hashub.dev](mailto:support@hashub.dev)
- **Issues**: [GitHub Issues](https://github.com/hasanbahadir/hashub-vector-sdk/issues)
- **Discord**: [Hashub Community](https://discord.gg/hashub)
## 🚀 What's Next?
Check out our roadmap for upcoming features:
- [ ] Vector database integrations (Weaviate, Qdrant, Chroma)
- [ ] Embedding visualization tools
- [ ] Fine-tuning capabilities
- [ ] On-premise deployment options
- [ ] More language-specific optimizations
---
**Made with ❤️ in Turkey** 🇹🇷
**Hashub Vector SDK** - Powering the next generation of AI applications with Turkish excellence.
Raw data
{
"_id": null,
"home_page": null,
"name": "hashub-vector",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "embeddings, vector, nlp, ai, machine-learning, text-processing, multilingual, turkish, semantic-search, rag, retrieval",
"author": null,
"author_email": "Hashub Team <support@hashub.dev>",
"download_url": "https://files.pythonhosted.org/packages/55/15/a86e4013dfb3b727533016ad36e9d699060397499d897ea81f46b3eeb33c/hashub_vector-1.0.0.tar.gz",
"platform": null,
"description": "# Hashub Vector SDK\r\n\r\n[](https://badge.fury.io/py/hashub-vector)\r\n[](https://www.python.org/downloads/)\r\n[](https://opensource.org/licenses/MIT)\r\n[](https://pepy.tech/project/hashub-vector)\r\n\r\n**High-quality multilingual text embeddings with Turkish excellence** \ud83c\uddf9\ud83c\uddf7\r\n\r\nThe official Python SDK for Hashub Vector API - providing state-of-the-art text embeddings with exceptional Turkish language support and 80+ other languages.\r\n\r\n## \ud83d\ude80 Features\r\n\r\n- **6 Premium Models** - From ultra-fast to premium quality\r\n- **Turkish Excellence** - Optimized for Turkish market with exceptional Turkish language performance\r\n- **80+ Languages** - Comprehensive multilingual support\r\n- **Async/Sync Support** - Both synchronous and asynchronous operations\r\n- **OpenAI Compatible** - Drop-in replacement for OpenAI embeddings\r\n- **Smart Retry Logic** - Automatic retries with exponential backoff\r\n- **Type Safety** - Full type hints and validation\r\n- **Production Ready** - Built for scale with rate limiting and error handling\r\n\r\n## \ud83d\udce6 Installation\r\n\r\n```bash\r\npip install hashub-vector\r\n```\r\n\r\nFor development with all extras:\r\n```bash\r\npip install hashub-vector[dev,examples]\r\n```\r\n\r\n## \ud83c\udfc3\u200d\u2642\ufe0f Quick Start\r\n\r\n```python\r\nfrom hashub_vector import HashubVector\r\n\r\n# Initialize client\r\nclient = HashubVector(api_key=\"your-api-key\")\r\n\r\n# Single text embedding\r\nresponse = client.vectorize(\"Merhaba d\u00fcnya! Hashub ile g\u00fc\u00e7l\u00fc vekt\u00f6r embedding'ler.\")\r\nprint(f\"Vector dimension: {response.dimension}\")\r\nprint(f\"First 5 dimensions: {response.vector[:5]}\")\r\n\r\n# Batch processing\r\ntexts = [\r\n \"Artificial intelligence is transforming the world\",\r\n \"Yapay zeka d\u00fcnyay\u0131 d\u00f6n\u00fc\u015ft\u00fcr\u00fcyor\",\r\n \"L'intelligence artificielle transforme le monde\"\r\n]\r\n\r\nbatch_response = client.vectorize_batch(texts, model=\"gte_base\")\r\nprint(f\"Processed {batch_response.count} texts\")\r\nprint(f\"Total tokens: {batch_response.total_tokens}\")\r\n\r\n# Calculate similarity\r\nsimilarity = client.similarity(\r\n \"Machine learning\", \r\n \"Makine \u00f6\u011frenmesi\"\r\n)\r\nprint(f\"Similarity: {similarity:.3f}\")\r\n```\r\n\r\n## \ud83e\udd16 Async Support\r\n\r\n```python\r\nimport asyncio\r\nfrom hashub_vector import HashubVector\r\n\r\nasync def main():\r\n async with HashubVector(api_key=\"your-api-key\") as client:\r\n # Async single embedding\r\n response = await client.avectorize(\"Async ile h\u0131zl\u0131 embedding!\")\r\n \r\n # Async batch processing\r\n texts = [\"Hello\", \"Merhaba\", \"Bonjour\"]\r\n batch_response = await client.avectorize_batch(texts)\r\n \r\n print(f\"Processed {batch_response.count} texts asynchronously\")\r\n\r\nasyncio.run(main())\r\n```\r\n\r\n## \ud83c\udfaf Model Selection Guide\r\n\r\n| Model | Best For | Dimension | Max Tokens | Price/1M | Turkish Support |\r\n|-------|----------|-----------|------------|----------|-----------------|\r\n| `gte_base` | Long documents, RAG | 768 | 8,192 | $0.01 | \u2b50\u2b50\u2b50\u2b50\u2b50 |\r\n| `nomic_base` | General purpose | 768 | 2,048 | $0.005 | \u2b50\u2b50\u2b50\u2b50 |\r\n| `e5_base` | Search, retrieval | 768 | 512 | $0.003 | \u2b50\u2b50\u2b50\u2b50\u2b50 |\r\n| `mpnet_base` | Q&A, similarity | 768 | 512 | $0.0035 | \u2b50\u2b50\u2b50\u2b50\u2b50 |\r\n| `e5_small` | High volume, speed | 384 | 512 | $0.002 | \u2b50\u2b50\u2b50\u2b50 |\r\n| `minilm_base` | Ultra-fast | 384 | 512 | $0.0025 | \u2b50\u2b50\u2b50\u2b50 |\r\n\r\n### Turkish Market Optimization\r\n\r\nAll models provide excellent Turkish language support, with `gte_base`, `e5_base`, and `mpnet_base` offering the highest quality for Turkish text processing.\r\n\r\n```python\r\n# Optimized for Turkish content\r\nresponse = client.vectorize(\r\n \"Hashub Vector API ile T\u00fcrk\u00e7e metinlerinizi g\u00fc\u00e7l\u00fc vekt\u00f6rlere d\u00f6n\u00fc\u015ft\u00fcr\u00fcn!\",\r\n model=\"gte_base\" # Best for Turkish\r\n)\r\n```\r\n\r\n## \ud83d\udd04 OpenAI Compatibility\r\n\r\nDrop-in replacement for OpenAI's embedding API:\r\n\r\n```python\r\n# OpenAI style (compatible)\r\nresponse = client.create_embedding(\r\n input=\"Your text here\",\r\n model=\"e5_base\"\r\n)\r\nembedding = response[\"data\"][0][\"embedding\"]\r\n\r\n# Multiple texts\r\nresponse = client.create_embedding(\r\n input=[\"Text 1\", \"Text 2\", \"Text 3\"],\r\n model=\"gte_base\"\r\n)\r\n```\r\n\r\n## \ud83e\udde0 Advanced Features\r\n\r\n### Chunking for Long Documents\r\n\r\n```python\r\n# Automatic chunking for long texts\r\nresponse = client.vectorize(\r\n long_document,\r\n model=\"gte_base\",\r\n chunk_size=1024,\r\n chunk_overlap=0.1 # 10% overlap\r\n)\r\nprint(f\"Document split into {response.chunk_count} chunks\")\r\n```\r\n\r\n### Model Information\r\n\r\n```python\r\n# Get available models\r\nmodels = client.get_models()\r\nfor model in models:\r\n print(f\"{model.alias}: {model.description}\")\r\n print(f\" Dimension: {model.dimension}\")\r\n print(f\" Max tokens: {model.max_tokens}\")\r\n print(f\" Price: ${model.price_per_1m_tokens}/1M tokens\")\r\n```\r\n\r\n### Usage Monitoring\r\n\r\n```python\r\n# Check your usage\r\nusage = client.get_usage()\r\nprint(f\"Tokens used: {usage.tokens_used:,}\")\r\nprint(f\"Usage percentage: {usage.tokens_percentage_used:.1f}%\")\r\n```\r\n\r\n## \ud83d\udee0\ufe0f Integration Examples\r\n\r\n### With LangChain\r\n\r\n```python\r\nfrom hashub_vector import HashubVector\r\nfrom langchain.embeddings.base import Embeddings\r\n\r\nclass HashubEmbeddings(Embeddings):\r\n def __init__(self, api_key: str, model: str = \"e5_base\"):\r\n self.client = HashubVector(api_key=api_key)\r\n self.model = model\r\n \r\n def embed_documents(self, texts):\r\n response = self.client.vectorize_batch(texts, model=self.model)\r\n return response.vectors\r\n \r\n def embed_query(self, text):\r\n response = self.client.vectorize(text, model=self.model)\r\n return response.vector\r\n\r\n# Usage\r\nembeddings = HashubEmbeddings(api_key=\"your-key\", model=\"gte_base\")\r\n```\r\n\r\n### With Pinecone\r\n\r\n```python\r\nimport pinecone\r\nfrom hashub_vector import HashubVector\r\n\r\n# Initialize clients\r\nclient = HashubVector(api_key=\"your-Hashub-key\")\r\npinecone.init(api_key=\"your-pinecone-key\", environment=\"your-env\")\r\n\r\n# Create embeddings and store\r\ntexts = [\"Your documents here...\"]\r\nresponse = client.vectorize_batch(texts, model=\"gte_base\")\r\n\r\n# Upsert to Pinecone\r\nindex = pinecone.Index(\"your-index\")\r\nvectors = [\r\n (f\"doc_{i}\", embedding, {\"text\": text})\r\n for i, (embedding, text) in enumerate(zip(response.vectors, texts))\r\n]\r\nindex.upsert(vectors)\r\n```\r\n\r\n## \ud83d\udd27 Error Handling\r\n\r\n```python\r\nfrom hashub_vector import (\r\n HashubVector,\r\n AuthenticationError,\r\n RateLimitError,\r\n QuotaExceededError\r\n)\r\n\r\nclient = HashubVector(api_key=\"your-key\")\r\n\r\ntry:\r\n response = client.vectorize(\"Your text\")\r\nexcept AuthenticationError:\r\n print(\"Invalid API key\")\r\nexcept RateLimitError as e:\r\n print(f\"Rate limited. Retry after {e.retry_after} seconds\")\r\nexcept QuotaExceededError:\r\n print(\"Quota exceeded. Please upgrade your plan\")\r\n```\r\n\r\n## \ud83c\udf0d Language Support\r\n\r\nHashub Vector SDK supports 80+ languages with excellent Turkish performance:\r\n\r\n### Tier 1 (Excellent Performance)\r\n\ud83c\uddf9\ud83c\uddf7 **Turkish**, English, German, French, Spanish, Italian, Portuguese, Dutch, Russian, Polish, Czech, Swedish, Danish, Norwegian, Finnish, Ukrainian\r\n\r\n### Tier 2 (Very Good Performance) \r\nArabic, Persian, Chinese, Japanese, Korean, Hindi, Bengali, Indonesian, Malay, Thai, Vietnamese, Bulgarian, Romanian, Hungarian, Croatian\r\n\r\n### Tier 3 (Good Performance)\r\nAnd 50+ additional languages including African, South Asian, and other European languages.\r\n\r\n## \ud83d\udcca Performance & Pricing\r\n\r\n### Speed Benchmarks (texts/second)\r\n- `minilm_base`: ~950 texts/second (Ultra-fast)\r\n- `e5_small`: ~780 texts/second (Fast)\r\n- `e5_base`: ~520 texts/second (Balanced)\r\n- `mpnet_base`: ~465 texts/second (Quality)\r\n- `nomic_base`: ~350 texts/second (Premium)\r\n- `gte_base`: ~280 texts/second (Maximum quality)\r\n\r\n### Cost Examples\r\n- **1M tokens with `e5_small`**: $2.00 (Most economical)\r\n- **1M tokens with `e5_base`**: $3.00 (Best value)\r\n- **1M tokens with `gte_base`**: $10.00 (Premium quality)\r\n\r\n## \ud83d\udd10 Authentication\r\n\r\nGet your API key from [Hashub Console](https://console.Hashub.dev):\r\n\r\n1. Sign up at Hashub Console\r\n2. Create a new API key\r\n3. Choose your pricing tier\r\n4. Start building!\r\n\r\n```python\r\n# Environment variable (recommended)\r\nimport os\r\nclient = HashubVector(api_key=os.getenv(\"Hashub_API_KEY\"))\r\n\r\n# Direct initialization\r\nclient = HashubVector(api_key=\"hv-1234567890abcdef...\")\r\n```\r\n\r\n## \ud83d\udea6 Rate Limits\r\n\r\n| Tier | Requests/Minute | Tokens/Month | Batch Size |\r\n|------|----------------|--------------|------------|\r\n| **Free** | 60 | 100K | 100 texts |\r\n| **Starter** | 300 | 1M | 500 texts |\r\n| **Pro** | 1,000 | 10M | 1,000 texts |\r\n| **Enterprise** | Custom | Custom | Custom |\r\n\r\nThe SDK automatically handles rate limiting with intelligent retry logic.\r\n\r\n## \ud83e\uddea Testing\r\n\r\n```bash\r\n# Install dev dependencies\r\npip install hashub-vector[dev]\r\n\r\n# Run tests\r\npytest\r\n\r\n# Run with coverage\r\npytest --cov=hashub_vector\r\n\r\n# Run specific test\r\npytest tests/test_client.py::test_vectorize\r\n```\r\n\r\n## \ud83d\udcda Documentation\r\n\r\n- **[Official Documentation](https://docs.vector.Hashub.dev)** - Complete API reference\r\n- **[Model Comparison](https://vector.Hashub.dev/models)** - Detailed model specifications\r\n- **[Pricing](https://vector.Hashub.dev/pricing)** - Transparent pricing information\r\n- **[Examples](./examples/)** - Integration examples and tutorials\r\n\r\n## \ud83e\udd1d Contributing\r\n\r\nWe welcome contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details.\r\n\r\n```bash\r\n# Development setup\r\ngit clone https://github.com/hasanbahadir/hashub-vector-sdk.git\r\ncd hashub-vector-sdk\r\npip install -e \".[dev]\"\r\npre-commit install\r\n```\r\n\r\n## \ud83d\udcc4 License\r\n\r\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\r\n\r\n## \ud83c\udd98 Support\r\n\r\n- **Documentation**: [docs.vector.hashub.dev](https://docs.vector.hashub.dev)\r\n- **Email**: [support@hashub.dev](mailto:support@hashub.dev)\r\n- **Issues**: [GitHub Issues](https://github.com/hasanbahadir/hashub-vector-sdk/issues)\r\n- **Discord**: [Hashub Community](https://discord.gg/hashub)\r\n\r\n## \ud83d\ude80 What's Next?\r\n\r\nCheck out our roadmap for upcoming features:\r\n- [ ] Vector database integrations (Weaviate, Qdrant, Chroma)\r\n- [ ] Embedding visualization tools\r\n- [ ] Fine-tuning capabilities\r\n- [ ] On-premise deployment options\r\n- [ ] More language-specific optimizations\r\n\r\n---\r\n\r\n**Made with \u2764\ufe0f in Turkey** \ud83c\uddf9\ud83c\uddf7\r\n\r\n**Hashub Vector SDK** - Powering the next generation of AI applications with Turkish excellence.\r\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Python SDK for Hashub Vector API - High-quality multilingual text embeddings",
"version": "1.0.0",
"project_urls": {
"Changelog": "https://github.com/hasanbahadir/hashub-vector-sdk/blob/master/CHANGELOG.md",
"Documentation": "https://github.com/hasanbahadir/hashub-vector-sdk#readme",
"Homepage": "https://github.com/hasanbahadir/hashub-vector-sdk",
"Issues": "https://github.com/hasanbahadir/hashub-vector-sdk/issues",
"Repository": "https://github.com/hasanbahadir/hashub-vector-sdk"
},
"split_keywords": [
"embeddings",
" vector",
" nlp",
" ai",
" machine-learning",
" text-processing",
" multilingual",
" turkish",
" semantic-search",
" rag",
" retrieval"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "176727734c85fc82138bb3810fb295af82803c77c8d4cc5bdfcf6948408397a3",
"md5": "ed9c17502c112e816064097943cc2dbc",
"sha256": "429db5755d7b7e369feea9e90409912fe100c234982a54f3ae2ee96bb850a476"
},
"downloads": -1,
"filename": "hashub_vector-1.0.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "ed9c17502c112e816064097943cc2dbc",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 16287,
"upload_time": "2025-08-03T22:00:03",
"upload_time_iso_8601": "2025-08-03T22:00:03.995677Z",
"url": "https://files.pythonhosted.org/packages/17/67/27734c85fc82138bb3810fb295af82803c77c8d4cc5bdfcf6948408397a3/hashub_vector-1.0.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "5515a86e4013dfb3b727533016ad36e9d699060397499d897ea81f46b3eeb33c",
"md5": "f44c6381de6e3f03b6b4c83a17c09182",
"sha256": "68182e8e95ff9c54c4585909e00e9ca543a07fdcd6dd037365542806dc8ae384"
},
"downloads": -1,
"filename": "hashub_vector-1.0.0.tar.gz",
"has_sig": false,
"md5_digest": "f44c6381de6e3f03b6b4c83a17c09182",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 31121,
"upload_time": "2025-08-03T22:00:05",
"upload_time_iso_8601": "2025-08-03T22:00:05.653911Z",
"url": "https://files.pythonhosted.org/packages/55/15/a86e4013dfb3b727533016ad36e9d699060397499d897ea81f46b3eeb33c/hashub_vector-1.0.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-03 22:00:05",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "hasanbahadir",
"github_project": "hashub-vector-sdk",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "hashub-vector"
}
JSON
