@mistralai/mistralai 0.5.0 → 1.0.0-rc.2

package/.devcontainer/README.md

@@ -0,0 +1,35 @@
+
+<div align="center">
+    <a href="https://codespaces.new/mistralai/mistral-ts-client.git/tree/main"><img src="https://github.com/codespaces/badge.svg" /></a>
+</div>
+<br>
+
+> **Remember to shutdown a GitHub Codespace when it is not in use!**
+
+# Dev Containers Quick Start
+
+The default location for usage snippets is the `samples` directory.
+
+## Running a Usage Sample
+
+A sample usage example has been provided in a `root.ts` file. As you work with the SDK, it's expected that you will modify these samples to fit your needs. To execute this particular snippet, use the command below.
+
+```
+ts-node root.ts
+```
+
+## Generating Additional Usage Samples
+
+The speakeasy CLI allows you to generate more usage snippets. Here's how:
+
+- To generate a sample for a specific operation by providing an operation ID, use:
+
+```
+speakeasy generate usage -s registry.speakeasyapi.dev/mistral-dev/mistral-dev/mistral-openapi -l typescript -i {INPUT_OPERATION_ID} -o ./samples
+```
+
+- To generate samples for an entire namespace (like a tag or group name), use:
+
+```
+speakeasy generate usage -s registry.speakeasyapi.dev/mistral-dev/mistral-dev/mistral-openapi -l typescript -n {INPUT_TAG_NAME} -o ./samples
+```

package/LICENSE

@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright [yyyy] [name of copyright owner]
+   Copyright 2024 Mistral AI
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

package/README.md

@@ -1,166 +1,503 @@
-This JavaScript client is inspired from [cohere-typescript](https://github.com/cohere-ai/cohere-typescript)
+# mistralai
 
-# Mistral JavaScript Client
+<div align="left">
+    <a href="https://speakeasyapi.dev/"><img src="https://custom-icon-badges.demolab.com/badge/-Built%20By%20Speakeasy-212015?style=for-the-badge&logoColor=FBE331&logo=speakeasy&labelColor=545454" /></a>
+</div>
 
-You can use the Mistral JavaScript client to interact with the Mistral AI API.
+<!-- Start SDK Installation [installation] -->
+## SDK Installation
 
-## Installing
+### NPM
 
-You can install the library in your project using:
+```bash
+npm add @mistralai/mistralai
+```
+
+### PNPM
+
+```bash
+pnpm add @mistralai/mistralai
+```
+
+### Bun
+
+```bash
+bun add @mistralai/mistralai
+```
+
+### Yarn
+
+```bash
+yarn add @mistralai/mistralai zod
+
+# Note that Yarn does not install peer dependencies automatically. You will need
+# to install zod as shown above.
+```
+<!-- End SDK Installation [installation] -->
+
+<!-- Start Requirements [requirements] -->
+## Requirements
 
-`npm install @mistralai/mistralai`
+For supported JavaScript runtimes, please consult [RUNTIMES.md](RUNTIMES.md).
+<!-- End Requirements [requirements] -->
 
-## Usage
+<!-- Start SDK Example Usage [usage] -->
+## SDK Example Usage
 
-You can watch a free course on using the Mistral JavaScript client [here.](https://scrimba.com/links/mistral)
+### Create Chat Completions
 
-### Set up
+This example shows how to create chat completions.
 
 ```typescript
-import MistralClient from '@mistralai/mistralai';
+import { Mistral } from "@mistralai/mistralai";
 
-const apiKey = process.env.MISTRAL_API_KEY || 'your_api_key';
+const mistral = new Mistral({
+    apiKey: process.env.MISTRAL_API_KEY,
+});
+
+async function run() {
+    const result = await mistral.chat.create({
+        model: "mistral-small-latest",
+        messages: [
+            {
+                content: "Who is the best French painter? Answer in one short sentence.",
+                role: "user",
+            },
+        ],
+    });
+
+    // Handle the result
+    console.log(result);
+}
+
+run();
 
-const client = new MistralClient(apiKey);
 ```
 
-### List models
+### Upload a file
+
+This example shows how to upload a file.
 
 ```typescript
-const listModelsResponse = await client.listModels();
-const listModels = listModelsResponse.data;
-listModels.forEach((model) => {
-  console.log('Model:', model);
+import { Mistral } from "@mistralai/mistralai";
+import { openAsBlob } from "node:fs";
+
+const mistral = new Mistral({
+    apiKey: process.env.MISTRAL_API_KEY,
 });
+
+async function run() {
+    const result = await mistral.files.upload({
+        file: await openAsBlob("./sample-file"),
+    });
+
+    // Handle the result
+    console.log(result);
+}
+
+run();
+
 ```
+<!-- End SDK Example Usage [usage] -->
+
+## Providers' SDKs
+
+We have dedicated SDKs for the following providers:
+
+- [GCP](/packages/mistralai-gcp/README.md)
+- [Azure](/packages/mistralai-azure/README.md)
+
+<!-- Start Available Resources and Operations [operations] -->
+## Available Resources and Operations
 
-### Chat with streaming
+### [models](docs/sdks/models/README.md)
+
+* [list](docs/sdks/models/README.md#list) - List Models
+* [retrieve](docs/sdks/models/README.md#retrieve) - Retrieve Model
+* [delete](docs/sdks/models/README.md#delete) - Delete Model
+* [update](docs/sdks/models/README.md#update) - Update Fine Tuned Model
+* [archive](docs/sdks/models/README.md#archive) - Archive Fine Tuned Model
+* [unarchive](docs/sdks/models/README.md#unarchive) - Unarchive Fine Tuned Model
+
+### [files](docs/sdks/files/README.md)
+
+* [upload](docs/sdks/files/README.md#upload) - Upload File
+* [list](docs/sdks/files/README.md#list) - List Files
+* [retrieve](docs/sdks/files/README.md#retrieve) - Retrieve File
+* [delete](docs/sdks/files/README.md#delete) - Delete File
+
+### [fineTuning](docs/sdks/finetuning/README.md)
+
+* [listJobs](docs/sdks/finetuning/README.md#listjobs) - Get Fine Tuning Jobs
+* [createJob](docs/sdks/finetuning/README.md#createjob) - Create Fine Tuning Job
+* [getJob](docs/sdks/finetuning/README.md#getjob) - Get Fine Tuning Job
+* [cancelJob](docs/sdks/finetuning/README.md#canceljob) - Cancel Fine Tuning Job
+* [startJob](docs/sdks/finetuning/README.md#startjob) - Start Fine Tuning Job
+
+### [chat](docs/sdks/chat/README.md)
+
+* [create](docs/sdks/chat/README.md#create) - Chat Completion
+* [stream](docs/sdks/chat/README.md#stream) - Stream chat completion
+
+### [fim](docs/sdks/fim/README.md)
+
+* [create](docs/sdks/fim/README.md#create) - Fim Completion
+* [stream](docs/sdks/fim/README.md#stream) - Stream fim completion
+
+### [embeddings](docs/sdks/embeddings/README.md)
+
+* [create](docs/sdks/embeddings/README.md#create) - Embeddings
+<!-- End Available Resources and Operations [operations] -->
+
+<!-- Start Server-sent event streaming [eventstream] -->
+## Server-sent event streaming
+
+[Server-sent events][mdn-sse] are used to stream content from certain
+operations. These operations will expose the stream as an async iterable that
+can be consumed using a [`for await...of`][mdn-for-await-of] loop. The loop will
+terminate when the server no longer has any events to send and closes the
+underlying connection.
 
 ```typescript
-const chatStreamResponse = await client.chatStream({
-  model: 'mistral-tiny',
-  messages: [{role: 'user', content: 'What is the best French cheese?'}],
+import { Mistral } from "@mistralai/mistralai";
+
+const mistral = new Mistral({
+    apiKey: process.env.MISTRAL_API_KEY,
 });
 
-console.log('Chat Stream:');
-for await (const chunk of chatStreamResponse) {
-  if (chunk.choices[0].delta.content !== undefined) {
-    const streamText = chunk.choices[0].delta.content;
-    process.stdout.write(streamText);
-  }
+async function run() {
+    const result = await mistral.chat.stream({
+        model: "mistral-small-latest",
+        messages: [
+            {
+                content: "Who is the best French painter? Answer in one short sentence.",
+                role: "user",
+            },
+        ],
+    });
+
+    for await (const event of result) {
+        // Handle the event
+    }
 }
+
+run();
+
 ```
 
-### Chat without streaming
+[mdn-sse]: https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events
+[mdn-for-await-of]: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Statements/for-await...of
+<!-- End Server-sent event streaming [eventstream] -->
+
+<!-- Start File uploads [file-upload] -->
+## File uploads
+
+Certain SDK methods accept files as part of a multi-part request. It is possible and typically recommended to upload files as a stream rather than reading the entire contents into memory. This avoids excessive memory consumption and potentially crashing with out-of-memory errors when working with very large files. The following example demonstrates how to attach a file stream to a request.
+
+> [!TIP]
+>
+> Depending on your JavaScript runtime, there are convenient utilities that return a handle to a file without reading the entire contents into memory:
+>
+> - **Node.js v20+:** Since v20, Node.js comes with a native `openAsBlob` function in [`node:fs`](https://nodejs.org/docs/latest-v20.x/api/fs.html#fsopenasblobpath-options).
+> - **Bun:** The native [`Bun.file`](https://bun.sh/docs/api/file-io#reading-files-bun-file) function produces a file handle that can be used for streaming file uploads.
+> - **Browsers:** All supported browsers return an instance to a [`File`](https://developer.mozilla.org/en-US/docs/Web/API/File) when reading the value from an `<input type="file">` element.
+> - **Node.js v18:** A file stream can be created using the `fileFrom` helper from [`fetch-blob/from.js`](https://www.npmjs.com/package/fetch-blob).
 
 ```typescript
-const chatResponse = await client.chat({
-  model: 'mistral-tiny',
-  messages: [{role: 'user', content: 'What is the best French cheese?'}],
+import { Mistral } from "@mistralai/mistralai";
+import { openAsBlob } from "node:fs";
+
+const mistral = new Mistral({
+    apiKey: process.env.MISTRAL_API_KEY,
 });
 
-console.log('Chat:', chatResponse.choices[0].message.content);
+async function run() {
+    const result = await mistral.files.upload({
+        file: await openAsBlob("./sample-file"),
+    });
+
+    // Handle the result
+    console.log(result);
+}
+
+run();
+
 ```
+<!-- End File uploads [file-upload] -->
 
-### Embeddings
+<!-- Start Retries [retries] -->
+## 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:
 ```typescript
-const input = [];
-for (let i = 0; i < 1; i++) {
-  input.push('What is the best French cheese?');
+import { Mistral } from "@mistralai/mistralai";
+
+const mistral = new Mistral({
+    apiKey: process.env.MISTRAL_API_KEY,
+});
+
+async function run() {
+    const result = await mistral.models.list({
+        retries: {
+            strategy: "backoff",
+            backoff: {
+                initialInterval: 1,
+                maxInterval: 50,
+                exponent: 1.1,
+                maxElapsedTime: 100,
+            },
+            retryConnectionErrors: false,
+        },
+    });
+
+    // Handle the result
+    console.log(result);
 }
 
-const embeddingsBatchResponse = await client.embeddings({
-  model: 'mistral-embed',
-  input: input,
+run();
+
+```
+
+If you'd like to override the default retry strategy for all operations that support retries, you can provide a retryConfig at SDK initialization:
+```typescript
+import { Mistral } from "@mistralai/mistralai";
+
+const mistral = new Mistral({
+    retryConfig: {
+        strategy: "backoff",
+        backoff: {
+            initialInterval: 1,
+            maxInterval: 50,
+            exponent: 1.1,
+            maxElapsedTime: 100,
+        },
+        retryConnectionErrors: false,
+    },
+    apiKey: process.env.MISTRAL_API_KEY,
 });
 
-console.log('Embeddings Batch:', embeddingsBatchResponse.data);
+async function run() {
+    const result = await mistral.models.list();
+
+    // Handle the result
+    console.log(result);
+}
+
+run();
+
 ```
+<!-- End Retries [retries] -->
+
+<!-- Start Error Handling [errors] -->
+## Error Handling
+
+All SDK methods return a response object or throw an error. If Error objects are specified in your OpenAPI Spec, the SDK will throw the appropriate Error type.
+
+| Error Object               | Status Code                | Content Type               |
+| -------------------------- | -------------------------- | -------------------------- |
+| errors.HTTPValidationError | 422                        | application/json           |
+| errors.SDKError            | 4xx-5xx                    | */*                        |
+
+Validation errors can also occur when either method arguments or data returned from the server do not match the expected format. The `SDKValidationError` that is thrown as a result will capture the raw value that failed validation in an attribute called `rawValue`. Additionally, a `pretty()` method is available on this error that can be used to log a nicely formatted string since validation errors can list many issues and the plain error string may be difficult read when debugging. 
 
-### Files
 
 ```typescript
-// Create a new file
-const file = fs.readFileSync('file.jsonl');
-const createdFile = await client.files.create({ file });
+import { Mistral } from "@mistralai/mistralai";
+import { SDKValidationError } from "@mistralai/mistralai/models/errors";
 
-// List files
-const files = await client.files.list();
+const mistral = new Mistral({
+    apiKey: process.env.MISTRAL_API_KEY,
+});
 
-// Retrieve a file
-const retrievedFile = await client.files.retrieve({ fileId: createdFile.id });
+async function run() {
+    let result;
+    try {
+        result = await mistral.models.list();
+    } catch (err) {
+        switch (true) {
+            case err instanceof SDKValidationError: {
+                // Validation errors can be pretty-printed
+                console.error(err.pretty());
+                // Raw value may also be inspected
+                console.error(err.rawValue);
+                return;
+            }
+            case err instanceof errors.HTTPValidationError: {
+                console.error(err); // handle exception
+                return;
+            }
+            default: {
+                throw err;
+            }
+        }
+    }
+
+    // Handle the result
+    console.log(result);
+}
+
+run();
 
-// Delete a file
-const deletedFile = await client.files.delete({ fileId: createdFile.id });
 ```
+<!-- End Error Handling [errors] -->
+
+<!-- Start Server Selection [server] -->
+## Server Selection
 
-### Fine-tuning Jobs
+### Select Server by Name
+
+You can override the default server globally by passing a server name to the `server` optional parameter when initializing the SDK client instance. The selected server will then be used as the default on the operations that use it. This table lists the names associated with the available servers:
+
+| Name | Server | Variables |
+| ----- | ------ | --------- |
+| `prod` | `https://api.mistral.ai` | None |
 
 ```typescript
-// Create a new job
-const createdJob = await client.jobs.create({
-  model: 'open-mistral-7B',
-  trainingFiles: [trainingFile.id],
-  validationFiles: [validationFile.id],
-  hyperparameters: {
-    trainingSteps: 10,
-    learningRate: 0.0001,
-  },
+import { Mistral } from "@mistralai/mistralai";
+
+const mistral = new Mistral({
+    server: "prod",
+    apiKey: process.env.MISTRAL_API_KEY,
 });
 
-// List jobs
-const jobs = await client.jobs.list();
+async function run() {
+    const result = await mistral.models.list();
+
+    // Handle the result
+    console.log(result);
+}
 
-// Retrieve a job
-const retrievedJob = await client.jobs.retrieve({ jobId: createdJob.id });
+run();
 
-// Cancel a job
-const canceledJob = await client.jobs.cancel({ jobId: createdJob.id });
 ```
 
-## Run examples
 
-You can run the examples in the examples directory by installing them locally:
+### Override Server URL Per-Client
 
-```bash
-cd examples
-npm install .
-```
+The default server can also be overridden globally by passing a URL to the `serverURL` optional parameter when initializing the SDK client instance. For example:
 
-### API key setup
+```typescript
+import { Mistral } from "@mistralai/mistralai";
 
-Running the examples requires a Mistral AI API key.
+const mistral = new Mistral({
+    serverURL: "https://api.mistral.ai",
+    apiKey: process.env.MISTRAL_API_KEY,
+});
+
+async function run() {
+    const result = await mistral.models.list();
 
-Get your own Mistral API Key: <https://docs.mistral.ai/#api-access>
+    // Handle the result
+    console.log(result);
+}
 
-### Run the examples
+run();
 
-```bash
-MISTRAL_API_KEY='your_api_key' node chat_with_streaming.js
 ```
+<!-- End Server Selection [server] -->
 
-### Persisting the API key in environment
+<!-- Start Custom HTTP Client [http-client] -->
+## Custom HTTP Client
 
-Set your Mistral API Key as an environment variable. You only need to do this once.
+The TypeScript SDK makes API calls using an `HTTPClient` that wraps the native
+[Fetch API](https://developer.mozilla.org/en-US/docs/Web/API/Fetch_API). This
+client is a thin wrapper around `fetch` and provides the ability to attach hooks
+around the request lifecycle that can be used to modify the request or handle
+errors and response.
 
-```bash
-# set Mistral API Key (using zsh for example)
-$ echo 'export MISTRAL_API_KEY=[your_api_key]' >> ~/.zshenv
+The `HTTPClient` constructor takes an optional `fetcher` argument that can be
+used to integrate a third-party HTTP client or when writing tests to mock out
+the HTTP client and feed in fixtures.
 
-# reload the environment (or just quit and open a new terminal)
-$ source ~/.zshenv
-```
+The following example shows how to use the `"beforeRequest"` hook to to add a
+custom header and a timeout to requests and how to use the `"requestError"` hook
+to log errors:
+
+```typescript
+import { Mistral } from "@mistralai/mistralai";
+import { HTTPClient } from "@mistralai/mistralai/lib/http";
 
-You can then run the examples without appending the API key:
+const httpClient = new HTTPClient({
+  // fetcher takes a function that has the same signature as native `fetch`.
+  fetcher: (request) => {
+    return fetch(request);
+  }
+});
 
-```bash
-node chat_with_streaming.js
+httpClient.addHook("beforeRequest", (request) => {
+  const nextRequest = new Request(request, {
+    signal: request.signal || AbortSignal.timeout(5000)
+  });
+
+  nextRequest.headers.set("x-custom-header", "custom value");
+
+  return nextRequest;
+});
+
+httpClient.addHook("requestError", (error, request) => {
+  console.group("Request Error");
+  console.log("Reason:", `${error}`);
+  console.log("Endpoint:", `${request.method} ${request.url}`);
+  console.groupEnd();
+});
+
+const sdk = new Mistral({ httpClient });
 ```
-After the env variable setup the client will find the `MISTRAL_API_KEY` by itself
+<!-- End Custom HTTP Client [http-client] -->
+
+<!-- Start Authentication [security] -->
+## Authentication
+
+### Per-Client Security Schemes
 
+This SDK supports the following security scheme globally:
+
+| Name        | Type        | Scheme      |
+| ----------- | ----------- | ----------- |
+| `apiKey`    | http        | HTTP Bearer |
+
+To authenticate with the API the `apiKey` parameter must be set when initializing the SDK client instance. For example:
 ```typescript
-import MistralClient from '@mistralai/mistralai';
+import { Mistral } from "@mistralai/mistralai";
+
+const mistral = new Mistral({
+    apiKey: process.env.MISTRAL_API_KEY,
+});
+
+async function run() {
+    const result = await mistral.models.list();
+
+    // Handle the result
+    console.log(result);
+}
+
+run();
 
-const client = new MistralClient();
 ```
+<!-- End Authentication [security] -->
+
+## Providers Support
+
+We also provide provider specific SDK for:
+
+- [GCP](packages/mistralai-gcp/README.md)
+- [Azure](packages/mistralai-azure/README.md)
+
+<!-- Placeholder for Future Speakeasy SDK Sections -->
+
+# Development
+
+## Maturity
+
+This SDK is in beta, and there may be breaking changes between versions without a major version update. Therefore, we recommend pinning usage
+to a specific package version. This way, you can install the same version each time without breaking changes unless you are intentionally
+looking for the latest version.
+
+## 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. 
+
+### SDK Created by [Speakeasy](https://docs.speakeasyapi.dev/docs/using-speakeasy/client-sdks)