# Dhenara
Dhenara is a genuinely open source Python package for interacting with various AI models in a unified way. It is a lightweight, straightforward framework for integrating multiple AI models into Python applications. It's similar in spirit to LangChain but with a focus on simplicity and minimal dependencies along with type safety using Pydantic Models.
For full documentation, visit [docs.dhenara.com](https://docs.dhenara.com/).
## Why Dhenara?
- **Genuinely Open Source**: Built from the ground up as a community resource, not an afterthought or internal tool
- **Unified API**: Interact with different AI providers through a consistent interface
- **Type Safety**: Built with Pydantic for robust type checking and validation
- **Easy Regeneration across Providers**: With a unified Pydantic output and built-in prompt formatting, send output from a model to any other model easily
- **Streaming**: First-class support for streaming responses along with accumulated responses similar to non-streaming responses
- **Async Support**: Both synchronous and asynchronous interfaces for maximum flexibility
- **Resource Management**: Automatic handling of connections, retries, and timeouts
- **Foundation Models**: Pre-configured models with sensible defaults
- **Test Mode**: Bring up your app with dummy responses for streaming and non-streaming generation
- **Cost/Usage Data**: Derived cost and usage data along with responses, with optional charge for each model endpoint for commercial deployment
- **Community-Oriented Design**: An architecture separating API credentials, models, and configurations for flexible deployment and scaling
## Example Usage
Here's a simple example of using Dhenara to interact with an AI model. You can find more examples in [docs.dhenara.com](https://docs.dhenara.com/).
```python
from dhenara.ai import AIModelClient
from dhenara.ai.types import AIModelCallConfig, AIModelEndpoint
from dhenara.ai.types.external_api import AIModelAPIProviderEnum
from dhenara.ai.types.genai import AIModelAPI
from dhenara.ai.types.genai.foundation_models.anthropic.chat import Claude37Sonnet
# Create an API
api = AIModelAPI(
provider=AIModelAPIProviderEnum.ANTHROPIC,
api_key="your_api_key",
)
# Create an endpoint using a pre-configured model
model_endpoint = AIModelEndpoint(
api=api,
ai_model=Claude37Sonnet,
)
# Configure the api call
config = AIModelCallConfig(
max_output_tokens=16000,
reasoning=True, # Thinking/reasoning mode
max_reasoning_tokens=8000,
streaming=False,
)
# Create the client
client = AIModelClient(
model_endpoint=model_endpoint,
config=config,
is_async=False,
)
# Create a prompt
prompt = {
"role": "user",
"content": "Explain quantum computing in simple terms",
}
# Generate a response
response = client.generate(prompt=prompt)
# If not streaming
if response.chat_response:
print(response.chat_response.choices[0].contents[0].get_text())
# If streaming
elif response.stream_generator:
for chunk, _ in response.stream_generator:
if chunk:
print(
chunk.data.choice_deltas[0].content_deltas[0].get_text_delta(),
end="",
flush=True,
)
```
## Documentation
For full documentation, visit [docs.dhenara.com](https://docs.dhenara.com/).
Raw data
{
"_id": null,
"home_page": "https://github.com/dhenara/dhenara-ai",
"name": "dhenara-ai",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "ai, llm, machine learning, language models",
"author": "Dhenara",
"author_email": "support@dhenara.com",
"download_url": "https://files.pythonhosted.org/packages/d4/92/7378ff50811212dcb8efeed4bd9073743154abc5f4dd34184e373a7cee63/dhenara_ai-1.0.2.tar.gz",
"platform": null,
"description": "# Dhenara\n\nDhenara is a genuinely open source Python package for interacting with various AI models in a unified way. It is a lightweight, straightforward framework for integrating multiple AI models into Python applications. It's similar in spirit to LangChain but with a focus on simplicity and minimal dependencies along with type safety using Pydantic Models.\n\nFor full documentation, visit [docs.dhenara.com](https://docs.dhenara.com/).\n\n## Why Dhenara?\n\n- **Genuinely Open Source**: Built from the ground up as a community resource, not an afterthought or internal tool\n- **Unified API**: Interact with different AI providers through a consistent interface\n- **Type Safety**: Built with Pydantic for robust type checking and validation\n- **Easy Regeneration across Providers**: With a unified Pydantic output and built-in prompt formatting, send output from a model to any other model easily\n- **Streaming**: First-class support for streaming responses along with accumulated responses similar to non-streaming responses\n- **Async Support**: Both synchronous and asynchronous interfaces for maximum flexibility\n- **Resource Management**: Automatic handling of connections, retries, and timeouts\n- **Foundation Models**: Pre-configured models with sensible defaults\n- **Test Mode**: Bring up your app with dummy responses for streaming and non-streaming generation\n- **Cost/Usage Data**: Derived cost and usage data along with responses, with optional charge for each model endpoint for commercial deployment\n- **Community-Oriented Design**: An architecture separating API credentials, models, and configurations for flexible deployment and scaling\n\n## Example Usage\n\nHere's a simple example of using Dhenara to interact with an AI model. You can find more examples in [docs.dhenara.com](https://docs.dhenara.com/).\n\n```python\nfrom dhenara.ai import AIModelClient\nfrom dhenara.ai.types import AIModelCallConfig, AIModelEndpoint\nfrom dhenara.ai.types.external_api import AIModelAPIProviderEnum\nfrom dhenara.ai.types.genai import AIModelAPI\nfrom dhenara.ai.types.genai.foundation_models.anthropic.chat import Claude37Sonnet\n\n# Create an API\napi = AIModelAPI(\n provider=AIModelAPIProviderEnum.ANTHROPIC,\n api_key=\"your_api_key\",\n)\n\n# Create an endpoint using a pre-configured model\nmodel_endpoint = AIModelEndpoint(\n api=api,\n ai_model=Claude37Sonnet,\n)\n\n# Configure the api call\nconfig = AIModelCallConfig(\n max_output_tokens=16000,\n reasoning=True, # Thinking/reasoning mode\n max_reasoning_tokens=8000,\n streaming=False,\n)\n\n# Create the client\nclient = AIModelClient(\n model_endpoint=model_endpoint,\n config=config,\n is_async=False,\n)\n\n# Create a prompt\nprompt = {\n \"role\": \"user\",\n \"content\": \"Explain quantum computing in simple terms\",\n}\n\n# Generate a response\nresponse = client.generate(prompt=prompt)\n\n# If not streaming\nif response.chat_response:\n print(response.chat_response.choices[0].contents[0].get_text())\n\n# If streaming\nelif response.stream_generator:\n for chunk, _ in response.stream_generator:\n if chunk:\n print(\n chunk.data.choice_deltas[0].content_deltas[0].get_text_delta(),\n end=\"\",\n flush=True,\n )\n```\n\n## Documentation\n\nFor full documentation, visit [docs.dhenara.com](https://docs.dhenara.com/).\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Dhenara Package for Multi Provider AI-Model API calls",
"version": "1.0.2",
"project_urls": {
"Bug Reports": "https://github.com/dhenara/dhenara-ai/issues",
"Documentation": "https://docs.dhenara.com/",
"Homepage": "https://dhenara.com",
"Source Code": "https://github.com/dhenara/dhenara-ai"
},
"split_keywords": [
"ai",
" llm",
" machine learning",
" language models"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "1cb972ac132189ddd4cf40272c2b33f5712f2d5e1bf24641984ff7ef7f0a424c",
"md5": "8fbba4484df6bb61ff8ecfa2fd409171",
"sha256": "ec929812f3fd0822ce9ed0e3bb3e986b8a001bf93c841ceaeeb0155b0e6c2d70"
},
"downloads": -1,
"filename": "dhenara_ai-1.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "8fbba4484df6bb61ff8ecfa2fd409171",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 109023,
"upload_time": "2025-07-23T08:11:49",
"upload_time_iso_8601": "2025-07-23T08:11:49.377314Z",
"url": "https://files.pythonhosted.org/packages/1c/b9/72ac132189ddd4cf40272c2b33f5712f2d5e1bf24641984ff7ef7f0a424c/dhenara_ai-1.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "d4927378ff50811212dcb8efeed4bd9073743154abc5f4dd34184e373a7cee63",
"md5": "b4c591e8b901e7ec19f0f1550a0a8c04",
"sha256": "fefef1dfba7b6d40eb51abcce0f9346b5bbf2916b45b33052852e1d28900d0a3"
},
"downloads": -1,
"filename": "dhenara_ai-1.0.2.tar.gz",
"has_sig": false,
"md5_digest": "b4c591e8b901e7ec19f0f1550a0a8c04",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 80325,
"upload_time": "2025-07-23T08:11:50",
"upload_time_iso_8601": "2025-07-23T08:11:50.573782Z",
"url": "https://files.pythonhosted.org/packages/d4/92/7378ff50811212dcb8efeed4bd9073743154abc5f4dd34184e373a7cee63/dhenara_ai-1.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-23 08:11:50",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "dhenara",
"github_project": "dhenara-ai",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "dhenara-ai"
}
JSON
