| Name | metorial-mistral JSON |
| Version |
1.0.4
JSON |
| download |
| home_page | None |
| Summary | Mistral AI provider for Metorial |
| upload_time | 2025-10-30 05:03:13 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.10 |
| license | MIT |
| keywords |
ai
llm
metorial
mistral
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# metorial-mistral
Mistral AI provider integration for Metorial.
## Installation
```bash
pip install metorial-mistral
# or
uv add metorial-mistral
# or
poetry add metorial-mistral
```
## Features
- š¤ **Mistral Integration**: Full support for Mistral Large, Codestral, and other Mistral models
- š” **Session Management**: Automatic tool lifecycle handling
- š **Format Conversion**: Converts Metorial tools to Mistral function format
- ā” **Async Support**: Full async/await support
## Supported Models
All Mistral AI models that support function calling:
- `mistral-large-latest`: Latest Mistral Large model with enhanced reasoning
- `mistral-large-2411`: Mistral Large November 2024
- `mistral-large-2407`: Mistral Large July 2024
- `mistral-small-latest`: Smaller, faster Mistral model
- `codestral-latest`: Specialized for code generation and analysis
## Usage
### Quick Start (Recommended)
```python
import asyncio
from mistralai.async_client import MistralAsyncClient
from metorial import Metorial
async def main():
# Initialize clients
metorial = Metorial(api_key="...your-metorial-api-key...") # async by default
mistral_client = MistralAsyncClient(
api_key="...your-mistral-api-key..."
)
# 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
mistral_client,
model="mistral-large-latest",
max_iterations=25
)
print("Response:", response)
asyncio.run(main())
```
### Streaming Chat
```python
import asyncio
from mistralai.async_client import MistralAsyncClient
from metorial import Metorial
from metorial.types import StreamEventType
async def streaming_example():
# Initialize clients
metorial = Metorial(api_key="...your-metorial-api-key...")
mistral_client = MistralAsyncClient(
api_key="...your-mistral-api-key..."
)
# Streaming chat with real-time responses
async def stream_action(session):
messages = [
{"role": "user", "content": "Explain quantum computing"}
]
async for event in metorial.stream(
mistral_client, session, messages,
model="mistral-large-latest",
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
from mistralai.client import MistralClient
from mistralai.models.chat_completion import ChatMessage
from metorial import Metorial
from metorial_mistral import MetorialMistralSession
async def main():
# Initialize clients
metorial = Metorial(api_key="...your-metorial-api-key...")
mistral = MistralClient(api_key="...your-mistral-api-key...")
# Create session with your server deployments
async with metorial.session(["...your-server-deployment-id..."]) as session:
# Create Mistral-specific wrapper
mistral_session = MetorialMistralSession(session.tool_manager)
messages = [
ChatMessage(role="user", content="What are the latest commits?")
]
response = mistral.chat(
model="mistral-large-latest",
messages=messages,
tools=mistral_session.tools
)
# Handle tool calls
if response.choices[0].message.tool_calls:
tool_responses = await mistral_session.call_tools(response.choices[0].message.tool_calls)
# Add assistant message and tool responses
messages.append(response.choices[0].message)
messages.extend(tool_responses)
# Continue conversation...
asyncio.run(main())
```
### Using Convenience Functions
```python
from metorial_mistral import build_mistral_tools, call_mistral_tools
async def example_with_functions():
# Get tools in Mistral format
tools = build_mistral_tools(tool_manager)
# Call tools from Mistral response
tool_messages = await call_mistral_tools(tool_manager, tool_calls)
```
## API Reference
### `MetorialMistralSession`
Main session class for Mistral integration.
```python
session = MetorialMistralSession(tool_manager)
```
**Properties:**
- `tools`: List of tools in Mistral format
**Methods:**
- `async call_tools(tool_calls)`: Execute tool calls and return tool messages
### `build_mistral_tools(tool_mgr)`
Build Mistral-compatible tool definitions.
**Returns:** List of tool definitions in Mistral format
### `call_mistral_tools(tool_mgr, tool_calls)`
Execute tool calls from Mistral response.
**Returns:** List of tool messages
## Tool Format
Tools are converted to Mistral's function calling format:
```python
{
"type": "function",
"function": {
"name": "tool_name",
"description": "Tool description",
"parameters": {
"type": "object",
"properties": {...},
"required": [...]
},
"strict": True
}
}
```
## Error Handling
```python
try:
tool_messages = await mistral_session.call_tools(tool_calls)
except Exception as e:
print(f"Tool execution failed: {e}")
```
Tool errors are returned as tool messages with error content.
## License
MIT License - see [LICENSE](../../LICENSE) file for details.
Raw data
{
"_id": null,
"home_page": null,
"name": "metorial-mistral",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "ai, llm, metorial, mistral",
"author": null,
"author_email": "Metorial Team <support@metorial.com>",
"download_url": "https://files.pythonhosted.org/packages/ce/4f/1cd9c810364ab5c49e38502d0043b89a67736e9eee6ce599825a8efc0311/metorial_mistral-1.0.4.tar.gz",
"platform": null,
"description": "# metorial-mistral\n\nMistral AI provider integration for Metorial.\n\n## Installation\n\n```bash\npip install metorial-mistral\n# or\nuv add metorial-mistral\n# or\npoetry add metorial-mistral\n```\n\n## Features\n\n- \ud83e\udd16 **Mistral Integration**: Full support for Mistral Large, Codestral, and other Mistral models\n- \ud83d\udce1 **Session Management**: Automatic tool lifecycle handling\n- \ud83d\udd04 **Format Conversion**: Converts Metorial tools to Mistral function format\n- \u26a1 **Async Support**: Full async/await support\n\n## Supported Models\n\nAll Mistral AI models that support function calling:\n\n- `mistral-large-latest`: Latest Mistral Large model with enhanced reasoning\n- `mistral-large-2411`: Mistral Large November 2024\n- `mistral-large-2407`: Mistral Large July 2024\n- `mistral-small-latest`: Smaller, faster Mistral model\n- `codestral-latest`: Specialized for code generation and analysis\n\n## Usage\n\n### Quick Start (Recommended)\n\n```python\nimport asyncio\nfrom mistralai.async_client import MistralAsyncClient\nfrom metorial import Metorial\n\nasync def main():\n # Initialize clients\n metorial = Metorial(api_key=\"...your-metorial-api-key...\") # async by default\n mistral_client = MistralAsyncClient(\n api_key=\"...your-mistral-api-key...\"\n )\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 mistral_client,\n model=\"mistral-large-latest\",\n max_iterations=25\n )\n \n print(\"Response:\", response)\n\nasyncio.run(main())\n```\n\n### Streaming Chat\n\n```python\nimport asyncio\nfrom mistralai.async_client import MistralAsyncClient\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 mistral_client = MistralAsyncClient(\n api_key=\"...your-mistral-api-key...\"\n )\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 mistral_client, session, messages, \n model=\"mistral-large-latest\",\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\nfrom mistralai.client import MistralClient\nfrom mistralai.models.chat_completion import ChatMessage\nfrom metorial import Metorial\nfrom metorial_mistral import MetorialMistralSession\n\nasync def main():\n # Initialize clients\n metorial = Metorial(api_key=\"...your-metorial-api-key...\")\n mistral = MistralClient(api_key=\"...your-mistral-api-key...\")\n \n # Create session with your server deployments\n async with metorial.session([\"...your-server-deployment-id...\"]) as session:\n # Create Mistral-specific wrapper\n mistral_session = MetorialMistralSession(session.tool_manager)\n \n messages = [\n ChatMessage(role=\"user\", content=\"What are the latest commits?\")\n ]\n \n response = mistral.chat(\n model=\"mistral-large-latest\",\n messages=messages,\n tools=mistral_session.tools\n )\n \n # Handle tool calls\n if response.choices[0].message.tool_calls:\n tool_responses = await mistral_session.call_tools(response.choices[0].message.tool_calls)\n \n # Add assistant message and tool responses\n messages.append(response.choices[0].message)\n messages.extend(tool_responses)\n \n # Continue conversation...\n\nasyncio.run(main())\n```\n\n### Using Convenience Functions\n\n```python\nfrom metorial_mistral import build_mistral_tools, call_mistral_tools\n\nasync def example_with_functions():\n # Get tools in Mistral format\n tools = build_mistral_tools(tool_manager)\n \n # Call tools from Mistral response\n tool_messages = await call_mistral_tools(tool_manager, tool_calls)\n```\n\n## API Reference\n\n### `MetorialMistralSession`\n\nMain session class for Mistral integration.\n\n```python\nsession = MetorialMistralSession(tool_manager)\n```\n\n**Properties:**\n- `tools`: List of tools in Mistral format\n\n**Methods:**\n- `async call_tools(tool_calls)`: Execute tool calls and return tool messages\n\n### `build_mistral_tools(tool_mgr)`\n\nBuild Mistral-compatible tool definitions.\n\n**Returns:** List of tool definitions in Mistral format\n\n### `call_mistral_tools(tool_mgr, tool_calls)`\n\nExecute tool calls from Mistral response.\n\n**Returns:** List of tool messages\n\n## Tool Format\n\nTools are converted to Mistral's function calling format:\n\n```python\n{\n \"type\": \"function\",\n \"function\": {\n \"name\": \"tool_name\",\n \"description\": \"Tool description\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {...},\n \"required\": [...]\n },\n \"strict\": True\n }\n}\n```\n\n## Error Handling\n\n```python\ntry:\n tool_messages = await mistral_session.call_tools(tool_calls)\nexcept Exception as e:\n print(f\"Tool execution failed: {e}\")\n```\n\nTool errors are returned as tool messages with error content.\n\n## License\n\nMIT License - see [LICENSE](../../LICENSE) file for details.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Mistral AI 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",
" llm",
" metorial",
" mistral"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "07ea3defbfe1c75af089bf75dd6c8b9dd4dfd268e4d846a8ce3baa05b4560ac3",
"md5": "74cb579fc84dce36b7aec20a314ee2c8",
"sha256": "91a3688a6bd5858ea5297843698028536777d67bc7f17cc4794b3ac2362d8270"
},
"downloads": -1,
"filename": "metorial_mistral-1.0.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "74cb579fc84dce36b7aec20a314ee2c8",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 5541,
"upload_time": "2025-10-30T05:03:11",
"upload_time_iso_8601": "2025-10-30T05:03:11.838820Z",
"url": "https://files.pythonhosted.org/packages/07/ea/3defbfe1c75af089bf75dd6c8b9dd4dfd268e4d846a8ce3baa05b4560ac3/metorial_mistral-1.0.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "ce4f1cd9c810364ab5c49e38502d0043b89a67736e9eee6ce599825a8efc0311",
"md5": "1b28560da021f872ed1e93b168c9563b",
"sha256": "02c9a3ee8f57d39e7e0966232e910b4ab362a5f2c60269cd788a7f2f11d49dab"
},
"downloads": -1,
"filename": "metorial_mistral-1.0.4.tar.gz",
"has_sig": false,
"md5_digest": "1b28560da021f872ed1e93b168c9563b",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 6553,
"upload_time": "2025-10-30T05:03:13",
"upload_time_iso_8601": "2025-10-30T05:03:13.409171Z",
"url": "https://files.pythonhosted.org/packages/ce/4f/1cd9c810364ab5c49e38502d0043b89a67736e9eee6ce599825a8efc0311/metorial_mistral-1.0.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-30 05:03:13",
"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-mistral"
}
