Skip to main content

Mistral AI provider for Metorial

Project description

metorial-mistral

Mistral AI provider integration for Metorial.

Installation

pip install metorial mistralai

Quick Start

import asyncio
from metorial import Metorial, MetorialMistral
from mistralai import AsyncMistral

metorial = Metorial(api_key="your-metorial-api-key")
mistral = AsyncMistral(api_key="your-mistral-api-key")

async def main():
    async def session_handler(session):
        messages = [{"role": "user", "content": "What's the latest news?"}]

        for _ in range(10):
            response = await mistral.chat.complete_async(
                model="mistral-large-latest",
                messages=messages,
                tools=session["tools"]
            )

            choice = response.choices[0]
            tool_calls = choice.message.tool_calls

            if not tool_calls:
                print(choice.message.content)
                break

            tool_responses = await session["callTools"](tool_calls)
            messages.append({"role": "assistant", "tool_calls": tool_calls})
            messages.extend(tool_responses)

        await session["closeSession"]()

    await metorial.with_provider_session(
        MetorialMistral,
        {"serverDeployments": [{"serverDeploymentId": "your-server-deployment-id"}]},
        session_handler
    )

asyncio.run(main())

Streaming

import asyncio
from metorial import Metorial, MetorialMistral
from mistralai import AsyncMistral

metorial = Metorial(api_key="your-metorial-api-key")
mistral = AsyncMistral(api_key="your-mistral-api-key")

async def main():
    async def session_handler(session):
        messages = [{"role": "user", "content": "What's the latest news?"}]

        stream = await mistral.chat.stream_async(
            model="mistral-large-latest",
            messages=messages,
            tools=session["tools"]
        )

        async for chunk in stream:
            if chunk.data.choices[0].delta.content:
                print(chunk.data.choices[0].delta.content, end="", flush=True)

        await session["closeSession"]()

    await metorial.with_provider_session(
        MetorialMistral,
        {
            "serverDeployments": [{"serverDeploymentId": "your-server-deployment-id"}],
            "streaming": True,  # Required for streaming with tool calls
        },
        session_handler
    )

asyncio.run(main())

Supported Models

  • mistral-large-latest: Most capable Mistral model
  • codestral-latest: Code-focused Mistral model

Session Object

async def session_handler(session):
    tools = session["tools"]           # Tool definitions in Mistral format
    call_tools = session["callTools"]  # Execute tools and get responses
    close_session = session["closeSession"]  # Close the session when done

Error Handling

from metorial import MetorialAPIError

try:
    await metorial.with_provider_session(...)
except MetorialAPIError as e:
    print(f"API Error: {e.message} (Status: {e.status})")
except Exception as e:
    print(f"Unexpected error: {e}")

License

MIT License - see LICENSE file for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

metorial_mistral-1.0.5.tar.gz (6.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

metorial_mistral-1.0.5-py3-none-any.whl (4.9 kB view details)

Uploaded Python 3

File details

Details for the file metorial_mistral-1.0.5.tar.gz.

File metadata

  • Download URL: metorial_mistral-1.0.5.tar.gz
  • Upload date:
  • Size: 6.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for metorial_mistral-1.0.5.tar.gz
Algorithm Hash digest
SHA256 8f5559eb24060b07cf7b273a4d264b5f58a85d0142edf0b3ae8449595249d4de
MD5 e2da43dd2fd58d03916f2a36bd7efb09
BLAKE2b-256 58d099012c6edc4ca424e789b48fba0afbbc0e5f896192a7e453c376bfd0394d

See more details on using hashes here.

Provenance

The following attestation bundles were made for metorial_mistral-1.0.5.tar.gz:

Publisher: release.yml on metorial/metorial-python

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file metorial_mistral-1.0.5-py3-none-any.whl.

File metadata

File hashes

Hashes for metorial_mistral-1.0.5-py3-none-any.whl
Algorithm Hash digest
SHA256 15b50c114f20900e64063ae60dd96cb785cd2eb065d1475c805a31598d48a2f3
MD5 ea76b39fe2fd09460003e7e9606d8c2b
BLAKE2b-256 a2d378c4314de82e1888990b4ab77d0b55a2b39dc0c51753adba9d9741dbc180

See more details on using hashes here.

Provenance

The following attestation bundles were made for metorial_mistral-1.0.5-py3-none-any.whl:

Publisher: release.yml on metorial/metorial-python

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page