| Name | metorial-google JSON |
| Version |
1.0.4
JSON |
| download |
| home_page | None |
| Summary | Google (Gemini) provider for Metorial |
| upload_time | 2025-10-30 05:03:23 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.10 |
| license | MIT |
| keywords |
ai
gemini
google
llm
metorial
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# metorial-google
Google (Gemini) provider integration for Metorial.
## Installation
```bash
pip install metorial-google
# or
uv add metorial-google
# or
poetry add metorial-google
```
## Features
- š¤ **Gemini Integration**: Full support for Gemini Pro, Gemini Flash, and other Google AI models
- š” **Session Management**: Automatic tool lifecycle handling
- š **Format Conversion**: Converts Metorial tools to Google function declaration format
- ā” **Async Support**: Full async/await support
## Supported Models
All Google Gemini models that support function calling:
- `gemini-1.5-pro`: Most capable Gemini model with 2M context window
- `gemini-1.5-flash`: Fast and efficient Gemini model
- `gemini-pro`: Standard Gemini Pro model
- `gemini-pro-vision`: Gemini Pro with vision capabilities
## Usage
### Quick Start (Recommended)
```python
import asyncio
import google.generativeai as genai
from metorial import Metorial
async def main():
# Initialize clients
metorial = Metorial(api_key="...your-metorial-api-key...") # async by default
genai.configure(api_key="...your-google-api-key...")
google_client = genai.GenerativeModel('gemini-pro')
# One-liner chat with automatic session management
response = await metorial.run(
"What are the latest commits in the metorial/websocket-explorer repository?",
"...your-mcp-server-deployment-id...", # can also be list
google_client,
model="gemini-pro",
max_iterations=25
)
print("Response:", response)
asyncio.run(main())
```
### Streaming Chat
```python
import asyncio
import google.generativeai as genai
from metorial import Metorial
from metorial.types import StreamEventType
async def streaming_example():
# Initialize clients
metorial = Metorial(api_key="...your-metorial-api-key...")
genai.configure(api_key="...your-google-api-key...")
google_client = genai.GenerativeModel('gemini-pro')
# Streaming chat with real-time responses
async def stream_action(session):
messages = [
{"role": "user", "content": "Explain quantum computing"}
]
async for event in metorial.stream(
google_client, session, messages,
model="gemini-pro",
max_iterations=25
):
if event.type == StreamEventType.CONTENT:
print(f"š¤ {event.content}", end="", flush=True)
elif event.type == StreamEventType.TOOL_CALL:
print(f"\nš§ Executing {len(event.tool_calls)} tool(s)...")
elif event.type == StreamEventType.COMPLETE:
print(f"\nā
Complete!")
await metorial.with_session("...your-server-deployment-id...", stream_action)
asyncio.run(streaming_example())
```
### Advanced Usage with Session Management
```python
import asyncio
import google.generativeai as genai
from metorial import Metorial
from metorial_google import MetorialGoogleSession
async def main():
# Initialize clients
metorial = Metorial(api_key="...your-metorial-api-key...")
genai.configure(api_key="...your-google-api-key...")
# Create session with your server deployments
async with metorial.session(["...your-server-deployment-id..."]) as session:
# Create Google-specific wrapper
google_session = MetorialGoogleSession(session.tool_manager)
model = genai.GenerativeModel(
model_name="gemini-pro",
tools=google_session.tools
)
response = model.generate_content("What are the latest commits?")
# Handle function calls if present
if response.candidates[0].content.parts:
function_calls = [
part.function_call for part in response.candidates[0].content.parts
if hasattr(part, 'function_call') and part.function_call
]
if function_calls:
tool_response = await google_session.call_tools(function_calls)
# Continue conversation with tool_response
asyncio.run(main())
```
### Using Convenience Functions
```python
from metorial_google import build_google_tools, call_google_tools
async def example_with_functions():
# Get tools in Google format
tools = build_google_tools(tool_manager)
# Call tools from Google response
response = await call_google_tools(tool_manager, function_calls)
```
## API Reference
### `MetorialGoogleSession`
Main session class for Google integration.
```python
session = MetorialGoogleSession(tool_manager)
```
**Properties:**
- `tools`: List of tools in Google function declaration format
**Methods:**
- `async call_tools(function_calls)`: Execute function calls and return user content
### `build_google_tools(tool_mgr)`
Build Google-compatible tool definitions.
**Returns:** List of tool definitions in Google format
### `call_google_tools(tool_mgr, function_calls)`
Execute function calls from Google response.
**Returns:** User content with function responses
## Tool Format
Tools are converted to Google's function declaration format:
```python
[{
"function_declarations": [
{
"name": "tool_name",
"description": "Tool description",
"parameters": {
"type": "object",
"properties": {...},
"required": [...]
}
}
]
}]
```
## Error Handling
```python
try:
response = await google_session.call_tools(function_calls)
except Exception as e:
print(f"Tool execution failed: {e}")
```
Tool errors are returned as error objects in the response format.
## License
MIT License - see [LICENSE](../../LICENSE) file for details.
Raw data
{
"_id": null,
"home_page": null,
"name": "metorial-google",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "ai, gemini, google, llm, metorial",
"author": null,
"author_email": "Metorial Team <support@metorial.com>",
"download_url": "https://files.pythonhosted.org/packages/ff/66/e0b71774ea78cb4b937b508bbc0f0d90a3618b54de4f924c8f95d0f3291f/metorial_google-1.0.4.tar.gz",
"platform": null,
"description": "# metorial-google\n\nGoogle (Gemini) provider integration for Metorial.\n\n## Installation\n\n```bash\npip install metorial-google\n# or\nuv add metorial-google\n# or\npoetry add metorial-google\n```\n\n## Features\n\n- \ud83e\udd16 **Gemini Integration**: Full support for Gemini Pro, Gemini Flash, and other Google AI models\n- \ud83d\udce1 **Session Management**: Automatic tool lifecycle handling\n- \ud83d\udd04 **Format Conversion**: Converts Metorial tools to Google function declaration format\n- \u26a1 **Async Support**: Full async/await support\n\n## Supported Models\n\nAll Google Gemini models that support function calling:\n\n- `gemini-1.5-pro`: Most capable Gemini model with 2M context window\n- `gemini-1.5-flash`: Fast and efficient Gemini model \n- `gemini-pro`: Standard Gemini Pro model\n- `gemini-pro-vision`: Gemini Pro with vision capabilities\n\n## Usage\n\n### Quick Start (Recommended)\n\n```python\nimport asyncio\nimport google.generativeai as genai\nfrom metorial import Metorial\n\nasync def main():\n # Initialize clients\n metorial = Metorial(api_key=\"...your-metorial-api-key...\") # async by default\n genai.configure(api_key=\"...your-google-api-key...\")\n google_client = genai.GenerativeModel('gemini-pro')\n \n # One-liner chat with automatic session management\n response = await metorial.run(\n \"What are the latest commits in the metorial/websocket-explorer repository?\",\n \"...your-mcp-server-deployment-id...\", # can also be list\n google_client,\n model=\"gemini-pro\",\n max_iterations=25\n )\n \n print(\"Response:\", response)\n\nasyncio.run(main())\n```\n\n### Streaming Chat\n\n```python\nimport asyncio\nimport google.generativeai as genai\nfrom metorial import Metorial\nfrom metorial.types import StreamEventType\n\nasync def streaming_example():\n # Initialize clients\n metorial = Metorial(api_key=\"...your-metorial-api-key...\")\n genai.configure(api_key=\"...your-google-api-key...\")\n google_client = genai.GenerativeModel('gemini-pro')\n \n # Streaming chat with real-time responses\n async def stream_action(session):\n messages = [\n {\"role\": \"user\", \"content\": \"Explain quantum computing\"}\n ]\n \n async for event in metorial.stream(\n google_client, session, messages, \n model=\"gemini-pro\",\n max_iterations=25\n ):\n if event.type == StreamEventType.CONTENT:\n print(f\"\ud83e\udd16 {event.content}\", end=\"\", flush=True)\n elif event.type == StreamEventType.TOOL_CALL:\n print(f\"\\n\ud83d\udd27 Executing {len(event.tool_calls)} tool(s)...\")\n elif event.type == StreamEventType.COMPLETE:\n print(f\"\\n\u2705 Complete!\")\n \n await metorial.with_session(\"...your-server-deployment-id...\", stream_action)\n\nasyncio.run(streaming_example())\n```\n\n### Advanced Usage with Session Management\n\n```python\nimport asyncio\nimport google.generativeai as genai\nfrom metorial import Metorial\nfrom metorial_google import MetorialGoogleSession\n\nasync def main():\n # Initialize clients\n metorial = Metorial(api_key=\"...your-metorial-api-key...\")\n genai.configure(api_key=\"...your-google-api-key...\")\n \n # Create session with your server deployments\n async with metorial.session([\"...your-server-deployment-id...\"]) as session:\n # Create Google-specific wrapper\n google_session = MetorialGoogleSession(session.tool_manager)\n \n model = genai.GenerativeModel(\n model_name=\"gemini-pro\",\n tools=google_session.tools\n )\n \n response = model.generate_content(\"What are the latest commits?\")\n \n # Handle function calls if present\n if response.candidates[0].content.parts:\n function_calls = [\n part.function_call for part in response.candidates[0].content.parts\n if hasattr(part, 'function_call') and part.function_call\n ]\n \n if function_calls:\n tool_response = await google_session.call_tools(function_calls)\n # Continue conversation with tool_response\n\nasyncio.run(main())\n```\n\n### Using Convenience Functions\n\n```python\nfrom metorial_google import build_google_tools, call_google_tools\n\nasync def example_with_functions():\n # Get tools in Google format\n tools = build_google_tools(tool_manager)\n \n # Call tools from Google response\n response = await call_google_tools(tool_manager, function_calls)\n```\n\n## API Reference\n\n### `MetorialGoogleSession`\n\nMain session class for Google integration.\n\n```python\nsession = MetorialGoogleSession(tool_manager)\n```\n\n**Properties:**\n- `tools`: List of tools in Google function declaration format\n\n**Methods:**\n- `async call_tools(function_calls)`: Execute function calls and return user content\n\n### `build_google_tools(tool_mgr)`\n\nBuild Google-compatible tool definitions.\n\n**Returns:** List of tool definitions in Google format\n\n### `call_google_tools(tool_mgr, function_calls)`\n\nExecute function calls from Google response.\n\n**Returns:** User content with function responses\n\n## Tool Format\n\nTools are converted to Google's function declaration format:\n\n```python\n[{\n \"function_declarations\": [\n {\n \"name\": \"tool_name\",\n \"description\": \"Tool description\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {...},\n \"required\": [...]\n }\n }\n ]\n}]\n```\n\n## Error Handling\n\n```python\ntry:\n response = await google_session.call_tools(function_calls)\nexcept Exception as e:\n print(f\"Tool execution failed: {e}\")\n```\n\nTool errors are returned as error objects in the response format.\n\n## License\n\nMIT License - see [LICENSE](../../LICENSE) file for details.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Google (Gemini) provider for Metorial",
"version": "1.0.4",
"project_urls": {
"Documentation": "https://metorial.com/docs",
"Homepage": "https://metorial.com",
"Repository": "https://github.com/metorial/metorial-python"
},
"split_keywords": [
"ai",
" gemini",
" google",
" llm",
" metorial"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "e5a35d584697e2773af61bdbecb6fd83866ae3ebf8cc50a034c088bee33f4dd8",
"md5": "691cad01eaa6296e41a9b8411671a1fc",
"sha256": "13061ceebbe78bd514a0e55504648b1e84f9aa3402c9f7f69aade48bdd1148b1"
},
"downloads": -1,
"filename": "metorial_google-1.0.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "691cad01eaa6296e41a9b8411671a1fc",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 5574,
"upload_time": "2025-10-30T05:03:14",
"upload_time_iso_8601": "2025-10-30T05:03:14.629806Z",
"url": "https://files.pythonhosted.org/packages/e5/a3/5d584697e2773af61bdbecb6fd83866ae3ebf8cc50a034c088bee33f4dd8/metorial_google-1.0.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "ff66e0b71774ea78cb4b937b508bbc0f0d90a3618b54de4f924c8f95d0f3291f",
"md5": "4f587c2ce2fab2b89f3f5d7c7621b33e",
"sha256": "d5319bb9dc32ba2777482262b61e6a546b4312e6c5b955f8b8bc9cead5ee5648"
},
"downloads": -1,
"filename": "metorial_google-1.0.4.tar.gz",
"has_sig": false,
"md5_digest": "4f587c2ce2fab2b89f3f5d7c7621b33e",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 6586,
"upload_time": "2025-10-30T05:03:23",
"upload_time_iso_8601": "2025-10-30T05:03:23.710251Z",
"url": "https://files.pythonhosted.org/packages/ff/66/e0b71774ea78cb4b937b508bbc0f0d90a3618b54de4f924c8f95d0f3291f/metorial_google-1.0.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-30 05:03:23",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "metorial",
"github_project": "metorial-python",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "metorial-google"
}
