Skip to content

gcp

Directory actions

More options

Directory actions

More options

Latest commit

 

History

History
 
 

gcp

README.md

Mistral on GCP Python Client

Prerequisites

Before you begin, you will need to create a Google Cloud project and enable the Mistral API. To do this, follow the instructions here.

To run this locally you will also need to ensure you are authenticated with Google Cloud. You can do this by running

gcloud auth application-default login

SDK Installation

Install the extras dependencies specific to Google Cloud:

pip install mistralai[gcp]

SDK Example Usage

Create Chat Completions

This example shows how to create chat completions.

The SDK automatically:

  • Detects credentials via google.auth.default()
  • Auto-refreshes tokens when they expire
  • Builds the Vertex AI URL from project_id and region
# Synchronous Example
import os
from mistralai.gcp.client import MistralGCP

# The SDK auto-detects credentials and builds the Vertex AI URL
s = MistralGCP(
    project_id=os.environ.get("GCP_PROJECT_ID"),  # Optional: auto-detected from credentials
    region=os.environ.get("GCP_REGION", "us-central1"),
)

res = s.chat.complete(messages=[
    {
        "role": "user",
        "content": "Who is the best French painter? Answer in one short sentence.",
    },
], model="mistral-small-2503")

if res is not None:
    # handle response
    print(res.choices[0].message.content)

The same SDK client can also be used to make asynchronous requests by importing asyncio.

# Asynchronous Example
import asyncio
import os
from mistralai.gcp.client import MistralGCP

async def main():
    # The SDK auto-detects credentials and builds the Vertex AI URL
    s = MistralGCP(
        project_id=os.environ.get("GCP_PROJECT_ID"),  # Optional: auto-detected
        region=os.environ.get("GCP_REGION", "us-central1"),
    )
    res = await s.chat.complete_async(messages=[
        {
            "role": "user",
            "content": "Who is the best French painter? Answer in one short sentence.",
        },
    ], model="mistral-small-2503")
    if res is not None:
        # handle response
        print(res.choices[0].message.content)

asyncio.run(main())

Available Resources and Operations

chat

fim

Server-sent event streaming

Server-sent events are used to stream content from certain operations. These operations will expose the stream as Generator that can be consumed using a simple for loop. The loop will terminate when the server no longer has any events to send and closes the underlying connection.

import os
from mistralai.gcp.client import MistralGCP

# The SDK auto-detects credentials and builds the Vertex AI URL
s = MistralGCP(
    project_id=os.environ.get("GCP_PROJECT_ID"),  # Optional: auto-detected
    region=os.environ.get("GCP_REGION", "us-central1"),
)

res = s.chat.stream(messages=[
    {
        "role": "user",
        "content": "Who is the best French painter? Answer in one short sentence.",
    },
], model="mistral-small-2503")

if res is not None:
    for event in res:
        # handle event
        print(event)

Retries

Some of the endpoints in this SDK support retries. If you use the SDK without any configuration, it will fall back to the default retry strategy provided by the API. However, the default retry strategy can be overridden on a per-operation basis, or across the entire SDK.

To change the default retry strategy for a single API call, simply provide a RetryConfig object to the call:

import os
from mistralai.gcp.client import MistralGCP
from mistralai.gcp.client.utils import BackoffStrategy, RetryConfig

# The SDK auto-detects credentials and builds the Vertex AI URL
s = MistralGCP(
    project_id=os.environ.get("GCP_PROJECT_ID"),  # Optional: auto-detected
    region=os.environ.get("GCP_REGION", "us-central1"),
)

res = s.chat.stream(
    messages=[
        {
            "role": "user",
            "content": "Who is the best French painter? Answer in one short sentence.",
        },
    ],
    model="mistral-small-2503",
    retries=RetryConfig(
        "backoff",
        BackoffStrategy(1, 50, 1.1, 100),
        False
    )
)

if res is not None:
    for event in res:
        # handle event
        print(event)

If you'd like to override the default retry strategy for all operations that support retries, you can use the retry_config optional parameter when initializing the SDK:

import os
from mistralai.gcp.client import MistralGCP
from mistralai.gcp.client.utils import BackoffStrategy, RetryConfig

# The SDK auto-detects credentials and builds the Vertex AI URL
s = MistralGCP(
    project_id=os.environ.get("GCP_PROJECT_ID"),
    region=os.environ.get("GCP_REGION", "us-central1"),
    retry_config=RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False),
)

res = s.chat.stream(
    messages=[
        {
            "role": "user",
            "content": "Who is the best French painter? Answer in one short sentence.",
        },
    ],
    model="mistral-small-2503",
)

if res is not None:
    for event in res:
        # handle event
        print(event)

Error Handling

Handling errors in this SDK should largely match your expectations. All operations return a response object or raise an error. If Error objects are specified in your OpenAPI Spec, the SDK will raise the appropriate Error type.

Error Object Status Code Content Type
models.HTTPValidationError 422 application/json
models.SDKError 4xx-5xx /

Example

import os
from mistralai.gcp.client import MistralGCP
from mistralai.gcp.client import models

# The SDK auto-detects credentials and builds the Vertex AI URL
s = MistralGCP(
    project_id=os.environ.get("GCP_PROJECT_ID"),
    region=os.environ.get("GCP_REGION", "us-central1"),
)

res = None
try:
    res = s.chat.complete(
        messages=[
            {
                "role": "user",
                "content": "Who is the best French painter? Answer in one short sentence.",
            },
        ],
        model="mistral-small-2503",
    )

except models.HTTPValidationError as e:
    # handle exception
    raise(e)
except models.SDKError as e:
    # handle exception
    raise(e)

if res is not None:
    # handle response
    pass

Server Selection

Override Server URL Per-Client

The SDK automatically constructs the Vertex AI endpoint from project_id and region:

import os
from mistralai.gcp.client import MistralGCP

# The SDK auto-detects credentials and builds the Vertex AI URL
s = MistralGCP(
    project_id=os.environ.get("GCP_PROJECT_ID"),  # Optional: auto-detected
    region=os.environ.get("GCP_REGION", "us-central1"),
)

res = s.chat.stream(
    messages=[
        {
            "role": "user",
            "content": "Who is the best French painter? Answer in one short sentence.",
        },
    ],
    model="mistral-small-2503",
)

if res is not None:
    for event in res:
        # handle event
        print(event)

Custom HTTP Client

The Python SDK makes API calls using the httpx HTTP library. In order to provide a convenient way to configure timeouts, cookies, proxies, custom headers, and other low-level configuration, you can initialize the SDK client with your own HTTP client instance. Depending on whether you are using the sync or async version of the SDK, you can pass an instance of HttpClient or AsyncHttpClient respectively, which are Protocols ensuring that the client has the necessary methods to make API calls. This allows you to wrap the client with your own custom logic, such as adding custom headers, logging, or error handling, or you can just pass an instance of httpx.Client or httpx.AsyncClient directly.

For example, you could specify a header for every request that this SDK makes as follows:

import os
from mistralai.gcp.client import MistralGCP
import httpx

http_client = httpx.Client(headers={"x-custom-header": "someValue"})
s = MistralGCP(
    project_id=os.environ.get("GCP_PROJECT_ID"),
    region="us-central1",
    client=http_client,
)

or you could wrap the client with your own custom logic:

from typing import Any, Optional, Union
from mistralai.gcp.client import MistralGCP
from mistralai.gcp.client.httpclient import AsyncHttpClient
import httpx

class CustomClient(AsyncHttpClient):
    client: AsyncHttpClient

    def __init__(self, client: AsyncHttpClient):
        self.client = client

    async def send(
        self,
        request: httpx.Request,
        *,
        stream: bool = False,
        auth: Union[
            httpx._types.AuthTypes, httpx._client.UseClientDefault, None
        ] = httpx.USE_CLIENT_DEFAULT,
        follow_redirects: Union[
            bool, httpx._client.UseClientDefault
        ] = httpx.USE_CLIENT_DEFAULT,
    ) -> httpx.Response:
        request.headers["Client-Level-Header"] = "added by client"

        return await self.client.send(
            request, stream=stream, auth=auth, follow_redirects=follow_redirects
        )

    def build_request(
        self,
        method: str,
        url: httpx._types.URLTypes,
        *,
        content: Optional[httpx._types.RequestContent] = None,
        data: Optional[httpx._types.RequestData] = None,
        files: Optional[httpx._types.RequestFiles] = None,
        json: Optional[Any] = None,
        params: Optional[httpx._types.QueryParamTypes] = None,
        headers: Optional[httpx._types.HeaderTypes] = None,
        cookies: Optional[httpx._types.CookieTypes] = None,
        timeout: Union[
            httpx._types.TimeoutTypes, httpx._client.UseClientDefault
        ] = httpx.USE_CLIENT_DEFAULT,
        extensions: Optional[httpx._types.RequestExtensions] = None,
    ) -> httpx.Request:
        return self.client.build_request(
            method,
            url,
            content=content,
            data=data,
            files=files,
            json=json,
            params=params,
            headers=headers,
            cookies=cookies,
            timeout=timeout,
            extensions=extensions,
        )

s = MistralGCP(
    project_id="<your-project-id>",
    region="us-central1",
    async_client=CustomClient(httpx.AsyncClient()),
)

Authentication

Per-Client Security Schemes

This SDK supports the following security scheme globally:

Name Type Scheme
api_key http HTTP Bearer

The SDK automatically handles GCP authentication via google.auth.default(). Tokens are auto-refreshed when they expire. For example:

import os
from mistralai.gcp.client import MistralGCP

# The SDK auto-detects credentials and builds the Vertex AI URL
s = MistralGCP(
    project_id=os.environ.get("GCP_PROJECT_ID"),  # Optional: auto-detected
    region=os.environ.get("GCP_REGION", "us-central1"),
)

res = s.chat.stream(
    messages=[
        {
            "role": "user",
            "content": "Who is the best French painter? Answer in one short sentence.",
        },
    ],
    model="mistral-small-2503",
)

if res is not None:
    for event in res:
        # handle event
        print(event)

Development

Contributions

While we value open-source contributions to this SDK, this library is generated programmatically. Any manual changes added to internal files will be overwritten on the next generation. We look forward to hearing your feedback. Feel free to open a PR or an issue with a proof of concept and we'll do our best to include it in a future release.