Update version to v0.0.119

Author: GitHub Actions

docs/capabilities/agents.md

@@ -76,7 +76,7 @@ curl --location "https://api.mistral.ai/v1/agents" \
 ### Use an agent
 
 
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
 
 ```python

docs/capabilities/batch.md

@@ -22,8 +22,9 @@ Here's an example of how to structure a batch request:
 
 Save your batch into a .jsonl file. Once saved, you can upload your batch input file to ensure it is correctly referenced when initiating batch processes: 
 
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
+
 ```python
 from mistralai import Mistral
 import os
@@ -40,8 +41,10 @@ batch_data = client.files.upload(
 
 )
 ```
+
   </TabItem>
   <TabItem value="typescript" label="typescript">
+
 ```typescript
 import { Mistral } from '@mistralai/mistralai';
 import fs from 'fs';
@@ -58,14 +61,17 @@ const batchData = await client.files.upload({
     }
 });
 ```
+
   </TabItem>
   <TabItem value="curl" label="curl">
+
 ```curl
 curl https://api.mistral.ai/v1/files \
   -H "Authorization: Bearer $MISTRAL_API_KEY" \
   -F purpose="batch" \
   -F file="@batch_input_file.jsonl"
 ```
+
   </TabItem>
 </Tabs>
 
@@ -78,7 +84,7 @@ Create a new batch job, it will be queued for processing.
 - `endpoint`: we currently support `/v1/embeddings`, `/v1/chat/completions`, `/v1/fim/completions`, `/v1/moderations`, `/v1/chat/moderations`.
 - `metadata`: optional custom metadata for the batch.
 
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
 ```python
 created_job = client.batch.jobs.create(
@@ -90,6 +96,7 @@ created_job = client.batch.jobs.create(
 ```
   </TabItem>
   <TabItem value="typescript" label="typescript">
+
 ```typescript
 import { Mistral } from '@mistralai/mistralai';
 
@@ -105,7 +112,9 @@ const createdJob = await client.batch.jobs.create({
 });
 ```
   </TabItem>
+
   <TabItem value="curl" label="curl">
+
 ```bash
 curl --location "https://api.mistral.ai/v1/batch/jobs" \
 --header "Authorization: Bearer $MISTRAL_API_KEY" \
@@ -128,43 +137,55 @@ curl --location "https://api.mistral.ai/v1/batch/jobs" \
 
 ## Get a batch job details 
 
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
+
 ```python
 retrieved_job = client.batch.jobs.get(job_id=created_job.id)
 ```
+
   </TabItem>
   <TabItem value="typescript" label="typescript">
+
 ```typescript
 const retrievedJob = await client.batch.jobs.get({ jobId: createdJob.id}); 
 ```
+
   </TabItem>
   <TabItem value="curl" label="curl">
+
 ```bash
 curl https://api.mistral.ai/v1/batch/jobs/<jobid> \
 --header "Authorization: Bearer $MISTRAL_API_KEY" \
 --header 'Content-Type: application/json'
 ```
+
   </TabItem>
 </Tabs>
 
 ## Get batch job results
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
+
 ```python
 client.files.download(file_id=retrieved_job.output_file)
 ```
+
   </TabItem>
   <TabItem value="typescript" label="typescript">
+
 ```typescript
 client.files.download({ fileId: retrieved_job.output_file}); 
 ```
+
   </TabItem>
   <TabItem value="curl" label="curl">
+
 ```bash
 curl 'https://api.mistral.ai/v1/files/<uuid>/content' \
 --header "Authorization: Bearer $MISTRAL_API_KEY" \
 ```
+
   </TabItem>
 </Tabs>
 
@@ -176,16 +197,19 @@ You can view a list of your batch jobs and filter them by various criteria, incl
 `CANCELLED`
 - Metadata: custom metadata key and value for the batch
 
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
+
 ```python
 list_job = client.batch.jobs.list(
     status="RUNNING",   
     metadata={"job_type": "testing"}
 )
 ```
+
   </TabItem>
   <TabItem value="typescript" label="typescript">
+
 ```typescript
 const listJob = await client.batch.jobs.list({ 
     status: "RUNNING",
@@ -194,38 +218,47 @@ const listJob = await client.batch.jobs.list({
     }
 });
 ```
+
   </TabItem>
   <TabItem value="curl" label="curl">
+
 ```bash
 curl 'https://api.mistral.ai/v1/batch/jobs?status=RUNNING&job_type=testing'\
 --header 'x-api-key: $MISTRAL_API_KEY' \
 --header 'Content-Type: application/json'
 ```
+
   </TabItem>
 </Tabs>
 
 
 ## Request the cancellation of a batch job
 
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
+
 ```python
 canceled_job = client.batch.jobs.cancel(job_id=created_job.id)
 ```
+
   </TabItem>
   <TabItem value="typescript" label="typescript">
+
 ```typescript
 const canceledJob = await mistral.fineTuning.jobs.cancel({
   jobId: createdJob.id,
 });
 ```
+
   </TabItem>
   <TabItem value="curl" label="curl">
+
 ```bash
 curl -X POST https://api.mistral.ai/v1/batch/jobs/<jobid>/cancel \
 --header "Authorization: Bearer $MISTRAL_API_KEY" \
 --header 'Content-Type: application/json'
 ```
+
   </TabItem>
 </Tabs>
 

docs/capabilities/code-generation.mdx

@@ -38,7 +38,7 @@ This guide will walk you through how to use Codestral fill-in-the-middle endpoin
 With this feature, users can define the starting point of the code using a `prompt`, and the ending point of the code using an optional `suffix` and an optional `stop`. The Codestral model will then generate the code that fits in between, making it ideal for tasks that require a specific piece of code to be generated. Below are three examples:  
 
 #### Example 1: Fill in the middle
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
 ```python
 import os
@@ -89,7 +89,7 @@ curl --location 'https://api.mistral.ai/v1/fim/completions' \
 </Tabs>
 
 #### Example 2: Completion
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
 ```python
 import os
@@ -136,7 +136,7 @@ curl --location 'https://api.mistral.ai/v1/fim/completions' \
 We recommend adding stop tokens for IDE autocomplete integrations to prevent the model from being too verbose.
 :::
 
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
 ```python
 import os
@@ -189,7 +189,7 @@ The only difference is the endpoint used:
 - Instruct endpoint: https://api.mistral.ai/v1/chat/completions
 
 
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
 ```python
 import os
@@ -226,7 +226,7 @@ curl --location "https://api.mistral.ai/v1/chat/completions" \
 
 ## Codestral Mamba
 We have also released Codestral Mamba 7B, a Mamba2 language model specialized in code generation with the instruct endpoint. 
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
 ```python
 import os

docs/capabilities/completion.mdx

@@ -18,7 +18,7 @@ The chat completion API accepts a list of chat messages as input and
 generates a response. This response is in the form of a new chat message with
 the role "assistant" as output. 
 
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
 
 ### No streaming

docs/capabilities/document.md

@@ -22,7 +22,7 @@ The Document OCR (Optical Character Recognition) processor, powered by our lates
 The OCR processor returns both the extracted text content and metadata about the document structure, making it easy to work with the recognized content programmatically.
 
 ### OCR with PDF
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python">
 
 ```python
@@ -56,7 +56,7 @@ const ocrResponse = await client.ocr.process({
         type: "document_url",
         documentUrl: "https://arxiv.org/pdf/2201.04234"
     },
-    include_image_base64: true
+    includeImageBase64: true
 });
 ```
   </TabItem>
@@ -470,7 +470,7 @@ curl https://api.mistral.ai/v1/ocr \
 You can also upload a PDF file and get the OCR results from the uploaded PDF. 
 
 #### Upload a file
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
 
 ```python
@@ -525,7 +525,7 @@ curl https://api.mistral.ai/v1/files \
 </Tabs>
 
 #### Retrieve File
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python">
 
 ```python
@@ -559,7 +559,7 @@ id='00edaf84-95b0-45db-8f83-f71138491f23' object='file' size_bytes=3749788 creat
 ```
 
 #### Get signed URL
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python">
 
 ```python
@@ -570,7 +570,7 @@ signed_url = client.files.get_signed_url(file_id=uploaded_pdf.id)
   <TabItem value="typescript" label="typescript">
 
 ```typescript
-const signedUrl = await mistral.files.getSignedUrl({
+const signedUrl = await client.files.getSignedUrl({
     fileId: uploaded_pdf.id,
 });
 ```
@@ -590,7 +590,7 @@ curl -X GET "https://api.mistral.ai/v1/files/$id/url?expiry=24" \
 
 #### Get OCR results
 
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python">
 
 ```python
@@ -644,7 +644,7 @@ curl https://api.mistral.ai/v1/ocr \
 </Tabs>
 
 ### OCR with image
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python">
 
 ```python
@@ -760,7 +760,7 @@ The Document understanding capability combines OCR with large language model cap
 
 The examples below show how to interact with a PDF document using natural language:
 
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
 
 ```python
@@ -874,3 +874,7 @@ For more information and guides on how to make use of OCR and leverage document
 - [Tool Use and Document Understanding](https://colab.research.google.com/github/mistralai/cookbook/blob/main/mistral/ocr/document_understanding.ipynb)
 - [Batch OCR](https://colab.research.google.com/github/mistralai/cookbook/blob/main/mistral/ocr/batch_ocr.ipynb)
 - [Structured OCR](https://colab.research.google.com/github/mistralai/cookbook/blob/main/mistral/ocr/structured_ocr.ipynb)
+
+## FAQ
+### Are there any limits regarding the OCR API?
+Yes, there are certain limitations for the OCR API. Uploaded document files must not exceed 50 MB in size and should be no longer than 1,000 pages.

docs/capabilities/finetuning.mdx

@@ -171,7 +171,7 @@ Once you have the data file with the right format,
 you can upload the data file to the Mistral Client, 
 making them available for use in fine-tuning jobs.
 
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
 
 ```python
@@ -246,7 +246,7 @@ The next step is to create a fine-tuning job.
     - `auto_start=True`: Your job will be launched immediately after validation.
     - `auto_start=False` (default): You can manually start the training after validation by sending a POST request to `/fine_tuning/jobs/<uuid>/start`.
 
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
 
 ```python
@@ -318,7 +318,7 @@ You can also list jobs, retrieve a job, or cancel a job.
 You can filter and view a list of jobs using various parameters such as 
 `page`, `page_size`, `model`, `created_after`, `created_by_me`, `status`, `wandb_project`, `wandb_name`, and `suffix`. Check out our [API specs](https://docs.mistral.ai/api/#tag/fine-tuning) for details.
 
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
 
 ```python
@@ -378,7 +378,7 @@ curl -X POST https://api.mistral.ai/v1/fine_tuning/jobs/<jobid>/cancel \
 ## Use a fine-tuned model
 When a fine-tuned job is finished, you will be able to see the fine-tuned model name via `retrieved_jobs.fine_tuned_model`. Then you can use our `chat` endpoint to chat with the fine-tuned model: 
 
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
 
 ```python
@@ -418,7 +418,7 @@ curl "https://api.mistral.ai/v1/chat/completions" \
 
 ## Delete a fine-tuned model
 
-<Tabs>
+<Tabs groupId="code">
   <TabItem value="python" label="python" default>
 
 ```python