Merge pull request #308 from mistralai/auto/docs-update

Auto-update llms.txt & llms-full.txt

Author: jaccolor2

static/llms-full.txt

@@ -223,6 +223,16 @@ Source: https://docs.mistral.ai/api/#tag/chat_classifications_v1_chat_classifica
 
 post /v1/chat/classifications
 
+# Create Transcription
+Source: https://docs.mistral.ai/api/#tag/audio_api_v1_transcriptions_post
+
+post /v1/audio/transcriptions
+
+# Create streaming transcription (SSE)
+Source: https://docs.mistral.ai/api/#tag/audio_api_v1_transcriptions_post_stream
+
+post /v1/audio/transcriptions#stream
+
 # List all libraries you have access to.
 Source: https://docs.mistral.ai/api/#tag/libraries_list_v1
 
@@ -5305,7 +5315,7 @@ console.log(transcriptionResponse);
 curl --location 'https://api.mistral.ai/v1/audio/transcriptions' \
   --header "x-api-key: $MISTRAL_API_KEY" \
   --form 'file=@"/path/to/file/audio.mp3"' \
-  --form 'model="voxtral-mini-2507"' \
+  --form 'model="voxtral-mini-2507"'
 ```
 
 **With Language defined**  
@@ -5571,7 +5581,7 @@ client = Mistral(api_key=api_key)
 transcription_response = client.audio.transcriptions.complete(
     model=model,
     file_url="https://docs.mistral.ai/audio/obama.mp3",
-    timestamp_granularities="segment"
+    timestamp_granularities=["segment"]
 )
 
 # Print the contents
@@ -5593,7 +5603,7 @@ const client = new Mistral({ apiKey: apiKey });
 const transcriptionResponse = await client.audio.transcriptions.complete({
   model: "voxtral-mini-latest",
   fileUrl: "https://docs.mistral.ai/audio/obama.mp3",
-  timestamp_granularities: "segment"
+  timestamp_granularities: ["segment"]
 });
 
 // Log the contents
@@ -5607,7 +5617,7 @@ console.log(transcriptionResponse);
 curl --location 'https://api.mistral.ai/v1/audio/transcriptions' \
 --header "x-api-key: $MISTRAL_API_KEY" \
 --form 'file_url="https://docs.mistral.ai/audio/obama.mp3"' \
---form 'model="voxtral-mini-latest"'
+--form 'model="voxtral-mini-latest"' \
 --form 'timestamp_granularities="segment"'
 ```
   </TabItem>
@@ -13088,7 +13098,7 @@ Source: https://docs.mistral.ai/docs/capabilities/vision
 
 Vision capabilities enable models to analyze images and provide insights based on visual content in addition to text. This multimodal approach opens up new possibilities for applications that require both textual and visual understanding.
 
-For more specific use cases regarding document parsing and data extraction we recommend taking a look at our Document AI stack [here](../OCR/document_ai_overview).
+For more specific use cases regarding document parsing and data extraction we recommend taking a look at our Document AI stack [here](../document_ai/document_ai_overview).
 
 ## Models with Vision Capabilities:
 - Pixtral 12B (`pixtral-12b-latest`)
@@ -13739,7 +13749,10 @@ in two ways:
 This page focuses on the MaaS offering, where the following models are available:
 
 - Mistral Large (24.11, 24.07)
-- Mistral Small (24.09)
+- Mistral Medium (25.05)
+- Mistral Small (25.03)
+- Mistral Document AI (25.05)
+- Mistral OCR (25.05)
 - Ministral 3B (24.10)
 - Mistral Nemo 
 
@@ -13843,9 +13856,11 @@ To run the examples below, set the following environment variables:
 ## Going further
 
 For more details and examples, refer to the following resources:
+- [Release blog post for Mistral Document AI](https://techcommunity.microsoft.com/blog/aiplatformblog/deepening-our-partnership-with-mistral-ai-on-azure-ai-foundry/4434656)
 - [Release blog post for Mistral Large 2 and Mistral NeMo](https://techcommunity.microsoft.com/t5/ai-machine-learning-blog/ai-innovation-continues-introducing-mistral-large-2-and-mistral/ba-p/4200181).
 - [Azure documentation for MaaS deployment of Mistral models](https://learn.microsoft.com/en-us/azure/ai-studio/how-to/deploy-models-mistral).
 - [Azure ML examples GitHub repository](https://github.com/Azure/azureml-examples/tree/main/sdk/python/foundation-models/mistral) with several Mistral-based samples.
+- [Azure AI Foundry GitHub repository](https://github.com/azure-ai-foundry/foundry-samples/tree/main/samples/mistral)
 
 
 [IBM watsonx.ai]
@@ -14089,7 +14104,7 @@ To run the examples below you will need to set the following environment variabl
 
 Codestral can be queried using an additional completion mode called fill-in-the-middle (FIM).
 For more information, see the
-[code generation section](../../../capabilities/code_generation/#fill-in-the-middle-endpoint).
+[code generation section](../../../capabilities/code_generation).
 
 
 <Tabs>
@@ -14390,7 +14405,7 @@ for more details.
 
 Codestral can be queried using an additional completion mode called fill-in-the-middle (FIM).
 For more information, see the
-[code generation section](../../../capabilities/code_generation/#fill-in-the-middle-endpoint).
+[code generation section](../../../capabilities/code_generation).
 
 
 <Tabs>
@@ -15693,7 +15708,7 @@ The [Mistral AI APIs](https://console.mistral.ai/) empower LLM applications via:
 
 - [Text generation](/capabilities/completion), enables streaming and provides the ability to display partial model results in real-time
 - [Vision](/capabilities/vision), enables the analysis of images and provides insights based on visual content in addition to text.
-- [OCR](/capabilities/OCR/basic_ocr), allows the extraction of interleaved text and images from documents.
+- [OCR](/capabilities/document_ai/basic_ocr), allows the extraction of interleaved text and images from documents.
 - [Code generation](/capabilities/code_generation), enpowers code generation tasks, including fill-in-the-middle and code completion.
 - [Embeddings](/capabilities/embeddings/overview), useful for RAG where it represents the meaning of text as a list of numbers.
 - [Function calling](/capabilities/function_calling), enables Mistral models to connect to external tools.
@@ -16198,7 +16213,7 @@ Mistral provides two types of models: open models and premier models.
 
 | Model               | Weight availability|Available via API| Description | Max Tokens| API Endpoints|Version|
 |--------------------|:--------------------:|:--------------------:|:--------------------:|:--------------------:|:--------------------:|:--------------------:|
-| Mistral Medium 3 | | :heavy_check_mark: | Our frontier-class multimodal model released May 2025. Learn more in our [blog post](https://mistral.ai/news/mistral-medium-3/) | 128k | `mistral-medium-2505` | 25.05|
+| Mistral Medium 3.1 | | :heavy_check_mark: | Our frontier-class multimodal model released August 2025. Improving tone and performance. Read more about Medium 3 in our [blog post](https://mistral.ai/news/mistral-medium-3/) | 128k | `mistral-medium-2508` | 25.08|
 | Magistral Medium 1.1 | | :heavy_check_mark: | Our frontier-class reasoning model released July 2025. | 40k | `magistral-medium-2507` | 25.07|
 | Codestral 2508 | | :heavy_check_mark: | Our cutting-edge language model for coding released end of July 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Learn more in our [blog post](https://mistral.ai/news/codestral-25-08/) | 256k  | `codestral-2508` | 25.08|
 | Voxtral Mini Transcribe | | :heavy_check_mark: | An efficient audio input model, fine-tuned and optimized for transcription purposes only. | | `voxtral-mini-2507` via `audio/transcriptions` | 25.07|
@@ -16207,6 +16222,7 @@ Mistral provides two types of models: open models and premier models.
 | Magistral Medium 1 | | :heavy_check_mark: | Our first frontier-class reasoning model released June 2025. Learn more in our [blog post](https://mistral.ai/news/magistral/) | 40k | `magistral-medium-2506` | 25.06|
 | Ministral 3B | | :heavy_check_mark: | World’s best edge model. Learn more in our [blog post](https://mistral.ai/news/ministraux/) | 128k  | `ministral-3b-2410` | 24.10|
 | Ministral 8B | :heavy_check_mark: <br/> [Mistral Research License](https://mistral.ai/licenses/MRL-0.1.md)| :heavy_check_mark: |Powerful edge model with extremely high performance/price ratio. Learn more in our [blog post](https://mistral.ai/news/ministraux/) | 128k  | `ministral-8b-2410` | 24.10|
+| Mistral Medium 3 | | :heavy_check_mark: | Our frontier-class multimodal model released May 2025. Learn more in our [blog post](https://mistral.ai/news/mistral-medium-3/) | 128k | `mistral-medium-2505` | 25.05|
 | Codestral 2501 | | :heavy_check_mark: | Our cutting-edge language model for coding with the second version released January 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Learn more in our [blog post](https://mistral.ai/news/codestral-2501/) | 256k  | `codestral-2501` | 25.01|
 | Mistral Large 2.1 |:heavy_check_mark: <br/> [Mistral Research License](https://mistral.ai/licenses/MRL-0.1.md)| :heavy_check_mark: | Our top-tier large model for high-complexity tasks with the lastest version released November 2024. Learn more in our [blog post](https://mistral.ai/news/pixtral-large/) | 128k  | `mistral-large-2411` | 24.11|
 | Pixtral Large |:heavy_check_mark: <br/> [Mistral Research License](https://mistral.ai/licenses/MRL-0.1.md)| :heavy_check_mark: | Our first frontier-class multimodal model released November 2024. Learn more in our [blog post](https://mistral.ai/news/pixtral-large/) | 128k  | `pixtral-large-2411` | 24.11|
@@ -16241,8 +16257,8 @@ Additionally, be prepared for the deprecation of certain endpoints in the coming
 Here are the details of the available versions:
 - `magistral-medium-latest`: currently points to `magistral-medium-2507`. 
 - `magistral-small-latest`: currently points to `magistral-small-2507`. 
-- `mistral-medium-latest`: currently points to `mistral-medium-2505`. 
-- `mistral-large-latest`: currently points to `mistral-large-2411`. 
+- `mistral-medium-latest`: currently points to `mistral-medium-2508`. 
+- `mistral-large-latest`: currently points to `mistral-medium-2508`, previously `mistral-large-2411`. 
 - `pixtral-large-latest`: currently points to `pixtral-large-2411`. 
 - `mistral-moderation-latest`: currently points to `mistral-moderation-2411`.
 - `ministral-3b-latest`: currently points to `ministral-3b-2410`.
@@ -18984,6 +19000,24 @@ Here is an [example notebook](https://github.com/mistralai/cookbook/blob/main/th
 
 <img src="/img/guides/obs_mlflow.png" alt="drawing" width="700"/>
 
+### Integration with Maxim
+
+Maxim AI provides comprehensive observability for your Mistral based AI applications. With Maxim's one-line integration, you can easily trace and analyse LLM calls, metrics, and more.
+
+**Pros:**
+
+* Performance Analytics: Track latency, tokens consumed, and costs
+* Advanced Visualisation: Understand agent trajectories through intuitive dashboards
+
+**Mistral integration Example:**
+
+* Learn how to integrate Maxim observability with the Mistral SDK in just one line of code - [Colab Notebook](https://github.com/mistralai/cookbook/blob/main/third_party/Maxim/cookbook_maxim_mistral_integration.ipynb)
+
+Maxim Documentation to use Mistral as an LLM Provider and Maxim as Logger - [Docs Link](https://www.getmaxim.ai/docs/sdk/python/integrations/mistral/mistral)
+
+
+![Gif](https://raw.githubusercontent.com/akmadan/platform-docs-public/docs/observability-maxim-provider/static/img/guides/maxim_traces.gif)
+
 
 [Other resources]
 Source: https://docs.mistral.ai/docs/guides/other-resources
@@ -20736,18 +20770,3 @@ Mistral AI's LLM API endpoints charge based on the number of tokens in the input
 
 To help you estimate your costs, our tokenization API makes it easy to count the number of tokens in your text. Simply run `len(tokens)` as shown in the example above to get the total number of tokens in the text, which you can then use to estimate your cost based on our pricing information.
 
-
-[Mistral AI Crawlers]
-Source: https://docs.mistral.ai/docs/robots
-
-## Mistral AI Crawlers
-
-Mistral AI employs web crawlers ("robots") and user agents to execute tasks for its products, either automatically or upon user request. To facilitate webmasters in managing how their sites and content interact with AI, Mistral AI utilizes specific robots.txt tags.
-
-### MistralAI-User
-
-MistralAI-User is for user actions in LeChat. When users ask LeChat a question, it may visit a web page to help answer and include a link to the source in its response. MistralAI-User governs which sites these user requests can be made to. It is not used for crawling the web in any automatic fashion, nor to crawl content for generative AI training.
-
-Full user-agent string: Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; MistralAI-User/1.0; +https://docs.mistral.ai/robots)
-
-Published IP addresses: https://mistral.ai/mistralai-user-ips.json