# metorial
The main Python client for Metorial - The open source integration platform for agentic AI. This is the primary package that provides the core client and session management functionality.
## Installation
```bash
pip install metorial
# or
uv add metorial
# or
poetry add metorial
```
## Features
- 🔧 **Multi-Provider Support**: Use the same tools across different AI providers
- 🚀 **Easy Integration**: Simple async/await interface
- 📡 **Session Management**: Automatic session lifecycle handling
- 🛠️ **Tool Discovery**: Automatic tool detection and formatting
- 🔄 **Format Conversion**: Provider-specific tool format conversion
## Supported Providers
- ✅ OpenAI (GPT-4, GPT-3.5)
- ✅ Anthropic (Claude)
- ✅ Google (Gemini)
- ✅ Mistral AI
- ✅ DeepSeek
- ✅ Together AI
- ✅ XAI (Grok)
## Usage
### Basic Usage
```python
import asyncio
from metorial import Metorial
async def main():
# Initialize Metorial client
metorial = Metorial(api_key="your-metorial-api-key")
# Create session with your server deployments
async with metorial.session(["your-server-deployment-id"]) as session:
# Access tool manager
tool_manager = session.tool_manager
# Use with provider-specific packages
# See provider packages for specific integrations
asyncio.run(main())
```
### With Provider Packages
Use metorial with provider-specific packages:
```python
import asyncio
from metorial import Metorial
from metorial_openai import MetorialOpenAISession
from openai import OpenAI
async def main():
# Initialize clients
metorial = Metorial(api_key="your-metorial-api-key")
openai_client = OpenAI(api_key="your-openai-api-key")
# Create session
async with metorial.session(["deployment-id"]) as session:
# Use with OpenAI
openai_session = MetorialOpenAISession(session.tool_manager)
response = openai_client.chat.completions.create(
model="gpt-4",
messages=[{"role": "user", "content": "Help me"}],
tools=openai_session.tools
)
# Handle tool calls
if response.choices[0].message.tool_calls:
tool_responses = await openai_session.call_tools(
response.choices[0].message.tool_calls
)
asyncio.run(main())
```
## API Reference
### `Metorial`
Main client class for Metorial.
```python
client = Metorial(api_key="your-api-key")
```
**Parameters:**
- `api_key`: Your Metorial API key
**Methods:**
- `async session(deployment_ids)`: Create a session with specified deployments
### Session Context Manager
```python
async with metorial.session(["deployment-id"]) as session:
# session.tool_manager provides access to tools
```
**Properties:**
- `tool_manager`: Manager for executing tools
## Provider Integration
This package works with provider-specific packages:
- `metorial-openai`: OpenAI integration
- `metorial-anthropic`: Anthropic (Claude) integration
- `metorial-google`: Google (Gemini) integration
- `metorial-mistral`: Mistral AI integration
- `metorial-xai`: XAI (Grok) integration
- `metorial-deepseek`: DeepSeek integration
- `metorial-togetherai`: Together AI integration
## Error Handling
```python
from metorial import MetorialAPIError
try:
async with metorial.session(["deployment-id"]) as session:
# Your code here
pass
except MetorialAPIError as e:
print(f"API Error: {e.message} (Status: {e.status})")
except Exception as e:
print(f"Unexpected error: {e}")
```
## Configuration
### Environment Variables
You can also configure the client using environment variables:
```bash
export METORIAL_API_KEY="your-api-key"
```
```python
# Will use METORIAL_API_KEY if no api_key provided
metorial = Metorial()
```
## Dependencies
- `metorial-core>=1.0.0`
- `metorial-mcp-session>=1.0.0`
- `typing-extensions>=4.0.0`
## License
MIT License - see [LICENSE](../../LICENSE) file for details.
Raw data
{
"_id": null,
"home_page": null,
"name": "metorial",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": null,
"keywords": "ai, anthropic, chat, completions, llm, mcp, metorial, model-context-protocol, openai, sessions, tools",
"author": null,
"author_email": "Metorial Team <support@metorial.com>",
"download_url": "https://files.pythonhosted.org/packages/74/39/0b5ab59150fe357ee93eb7efe8453112485a81633db124fc0a3644f44c19/metorial-1.0.0rc3.tar.gz",
"platform": null,
"description": "# metorial\n\nThe main Python client for Metorial - The open source integration platform for agentic AI. This is the primary package that provides the core client and session management functionality.\n\n## Installation\n\n```bash\npip install metorial\n# or\nuv add metorial\n# or\npoetry add metorial\n```\n\n## Features\n\n- \ud83d\udd27 **Multi-Provider Support**: Use the same tools across different AI providers\n- \ud83d\ude80 **Easy Integration**: Simple async/await interface\n- \ud83d\udce1 **Session Management**: Automatic session lifecycle handling\n- \ud83d\udee0\ufe0f **Tool Discovery**: Automatic tool detection and formatting\n- \ud83d\udd04 **Format Conversion**: Provider-specific tool format conversion\n\n## Supported Providers\n\n- \u2705 OpenAI (GPT-4, GPT-3.5)\n- \u2705 Anthropic (Claude)\n- \u2705 Google (Gemini)\n- \u2705 Mistral AI\n- \u2705 DeepSeek\n- \u2705 Together AI\n- \u2705 XAI (Grok)\n\n## Usage\n\n### Basic Usage\n\n```python\nimport asyncio\nfrom metorial import Metorial\n\nasync def main():\n # Initialize Metorial client\n metorial = Metorial(api_key=\"your-metorial-api-key\")\n \n # Create session with your server deployments\n async with metorial.session([\"your-server-deployment-id\"]) as session:\n # Access tool manager\n tool_manager = session.tool_manager\n \n # Use with provider-specific packages\n # See provider packages for specific integrations\n\nasyncio.run(main())\n```\n\n### With Provider Packages\n\nUse metorial with provider-specific packages:\n\n```python\nimport asyncio\nfrom metorial import Metorial\nfrom metorial_openai import MetorialOpenAISession\nfrom openai import OpenAI\n\nasync def main():\n # Initialize clients\n metorial = Metorial(api_key=\"your-metorial-api-key\")\n openai_client = OpenAI(api_key=\"your-openai-api-key\")\n \n # Create session\n async with metorial.session([\"deployment-id\"]) as session:\n # Use with OpenAI\n openai_session = MetorialOpenAISession(session.tool_manager)\n \n response = openai_client.chat.completions.create(\n model=\"gpt-4\",\n messages=[{\"role\": \"user\", \"content\": \"Help me\"}],\n tools=openai_session.tools\n )\n \n # Handle tool calls\n if response.choices[0].message.tool_calls:\n tool_responses = await openai_session.call_tools(\n response.choices[0].message.tool_calls\n )\n\nasyncio.run(main())\n```\n\n## API Reference\n\n### `Metorial`\n\nMain client class for Metorial.\n\n```python\nclient = Metorial(api_key=\"your-api-key\")\n```\n\n**Parameters:**\n- `api_key`: Your Metorial API key\n\n**Methods:**\n- `async session(deployment_ids)`: Create a session with specified deployments\n\n### Session Context Manager\n\n```python\nasync with metorial.session([\"deployment-id\"]) as session:\n # session.tool_manager provides access to tools\n```\n\n**Properties:**\n- `tool_manager`: Manager for executing tools\n\n## Provider Integration\n\nThis package works with provider-specific packages:\n\n- `metorial-openai`: OpenAI integration\n- `metorial-anthropic`: Anthropic (Claude) integration \n- `metorial-google`: Google (Gemini) integration\n- `metorial-mistral`: Mistral AI integration\n- `metorial-xai`: XAI (Grok) integration\n- `metorial-deepseek`: DeepSeek integration\n- `metorial-togetherai`: Together AI integration\n\n## Error Handling\n\n```python\nfrom metorial import MetorialAPIError\n\ntry:\n async with metorial.session([\"deployment-id\"]) as session:\n # Your code here\n pass\nexcept MetorialAPIError as e:\n print(f\"API Error: {e.message} (Status: {e.status})\")\nexcept Exception as e:\n print(f\"Unexpected error: {e}\")\n```\n\n## Configuration\n\n### Environment Variables\n\nYou can also configure the client using environment variables:\n\n```bash\nexport METORIAL_API_KEY=\"your-api-key\"\n```\n\n```python\n# Will use METORIAL_API_KEY if no api_key provided\nmetorial = Metorial()\n```\n\n## Dependencies\n\n- `metorial-core>=1.0.0`\n- `metorial-mcp-session>=1.0.0`\n- `typing-extensions>=4.0.0`\n\n## License\n\nMIT License - see [LICENSE](../../LICENSE) file for details.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Python SDK for Metorial - AI-powered tool calling and session management",
"version": "1.0.0rc3",
"project_urls": {
"Changelog": "https://github.com/metorial/metorial-enterprise/blob/main/CHANGELOG.md",
"Documentation": "https://metorial.com/docs",
"Homepage": "https://metorial.com",
"Repository": "https://github.com/metorial/metorial-enterprise"
},
"split_keywords": [
"ai",
" anthropic",
" chat",
" completions",
" llm",
" mcp",
" metorial",
" model-context-protocol",
" openai",
" sessions",
" tools"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "2eb464c9e4479485bbb30af6ba0cd6c813a3c7758dc75378f7fef6d26d894a83",
"md5": "40c2b8ca79e4628bcddb6052e82a985d",
"sha256": "95413548cec23e27075e2ad05ce059e4a1e1c1075da7165e4df7771925276a0c"
},
"downloads": -1,
"filename": "metorial-1.0.0rc3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "40c2b8ca79e4628bcddb6052e82a985d",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9",
"size": 4125,
"upload_time": "2025-07-26T12:37:22",
"upload_time_iso_8601": "2025-07-26T12:37:22.343690Z",
"url": "https://files.pythonhosted.org/packages/2e/b4/64c9e4479485bbb30af6ba0cd6c813a3c7758dc75378f7fef6d26d894a83/metorial-1.0.0rc3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "74390b5ab59150fe357ee93eb7efe8453112485a81633db124fc0a3644f44c19",
"md5": "c31f712d12995cf026dd00821f01105b",
"sha256": "727c77e7b2b7072aa85959c8a3110624e988c0d15ec43d401242c69590b83403"
},
"downloads": -1,
"filename": "metorial-1.0.0rc3.tar.gz",
"has_sig": false,
"md5_digest": "c31f712d12995cf026dd00821f01105b",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 5605,
"upload_time": "2025-07-26T12:37:24",
"upload_time_iso_8601": "2025-07-26T12:37:24.089250Z",
"url": "https://files.pythonhosted.org/packages/74/39/0b5ab59150fe357ee93eb7efe8453112485a81633db124fc0a3644f44c19/metorial-1.0.0rc3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-26 12:37:24",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "metorial",
"github_project": "metorial-enterprise",
"github_not_found": true,
"lcname": "metorial"
}
JSON
