Change

fb140cf

fb140cfa2401e9204846e12172c30411fa85123c · commit on GitHub

mistral-llms-txt: changed (81195 bytes, HTTP 200)

raw/mistral-llms-txt/response.txt modified

Source: mistral-llms-txt
Lines added: +28
Lines removed: -28
Stored bytes at this commit: 81,195
Timestamp: 4 November 2026 06:10 UTC origin
Raw artifact at this commit: raw/mistral-llms-txt/response.txt

Recorded headers

observed_at	2026-11-04T06:21:54.692Z
origin_date	2026-11-04T06:10:56.000Z
status	200
final URL	https://docs.mistral.ai/llms.txt
etag	"67e1a3982d7bf7dec249f7c2715c7b0c-ssl-df"
last-modified	null
date	Wed, 04 Nov 2026 06:21:54 GMT
age	658
cache-control	public,max-age=0,must-revalidate
cf-cache-status	null
content-encoding	br
content-length	20155

@@@ -270,34 +270,34 @@ Every link points to the markdown version of a page (same URL with a `.md` exten

- [Code Embeddings](https://docs.mistral.ai/studio/knowledge-rag/embeddings/code_embeddings.md): Embeddings are at the core of multiple enterprise use cases, such as retrieval systems, clustering, code analytics, classification, and a variety of search applications.

- [Embeddings](https://docs.mistral.ai/studio/knowledge-rag/embeddings.md): Embeddings are vector representations of text that capture the semantic meaning of paragraphs through their position in a high-dimensional vector space.

- [Text Embeddings](https://docs.mistral.ai/studio/knowledge-rag/embeddings/text_embeddings.md): Embeddings are at the core of multiple enterprise use cases, such as retrieval systems, clustering, code analytics, classification, and a variety of search applications.

- [Use context objects](https://docs.mistral.ai/studio/observability/evaluations/advanced-guides/context-objects.md): Tasks, scorers, and metadata callbacks receive their inputs through context objects: typed Pydantic models that bundle all available data into a single parameter.

- [Iterate locally](https://docs.mistral.ai/studio/observability/evaluations/advanced-guides/local-mode.md): Set local=True to run evaluations without uploading results to Studio.

- [Multiple evaluators](https://docs.mistral.ai/studio/observability/evaluations/advanced-guides/multiple-evaluators.md): A run can hold any number of evaluators — pass them as a list to evaluators.

- [Reduce variance with multiple generations](https://docs.mistral.ai/studio/observability/evaluations/advanced-guides/num-generations.md): When your task is non-deterministic (for example, temperature > 0), a single generation per input may not give you a reliable picture.

- [Rescore persisted runs](https://docs.mistral.ai/studio/observability/evaluations/advanced-guides/rescoring.md): An expensive task execution should be produced once and scored as many times as you like. evaluation.rescore() scores the outputs already persisted in Studio without re-running the task…

- [Retry failed records](https://docs.mistral.ai/studio/observability/evaluations/advanced-guides/retry-failed-records.md): Evaluations can fail partially: a transient API error, a rate limit, or a bug in your scorer.

- [Use run-level evaluators](https://docs.mistral.ai/studio/observability/evaluations/advanced-guides/run-evaluators.md): While regular evaluators score each record individually, run evaluators operate on the full set of results after all records have been processed.

- [API reference](https://docs.mistral.ai/studio/observability/evaluations/api-reference.md): Reference for the Evaluation SDK's core types and the main evaluation.run() entry point.

- [Datasets](https://docs.mistral.ai/studio/observability/evaluations/datasets.md): A dataset is the set of test cases that drives an offline evaluation.

- [Evaluators](https://docs.mistral.ai/studio/observability/evaluations/evaluators.md): An evaluator scores each record of a run.

- [Set goals](https://docs.mistral.ai/studio/observability/evaluations/goals.md): Goals let you define pass/fail criteria on evaluator scores.

- [Limits](https://docs.mistral.ai/studio/observability/evaluations/limits.md): The evaluations API enforces limits to keep the service stable under large or high-fan-out evaluations.

- [Optimize prompts and parameters](https://docs.mistral.ai/studio/observability/evaluations/optimization.md): Optimization turns an evaluation into a search: instead of measuring a single prompt or set of system params, the SDK automatically explores variations of it and returns the best one it fin…

- [Offline evaluations](https://docs.mistral.ai/studio/observability/evaluations.md): The Evaluation SDK (mistralai-evaluations) lets you run offline evaluations on your LLM pipelines in a few lines of Python.

- [Configure statistics](https://docs.mistral.ai/studio/observability/evaluations/statistics.md): Statistics are the run-level values an evaluator exposes from its per-record scores: an average, a total, a percentile, or a classification metric such as F1.

- [Configure system params](https://docs.mistral.ai/studio/observability/evaluations/system-params.md): When you run an LLM pipeline, many parameters influence the output: the model, temperature, system prompt, tool definitions, retrieval settings, and more.

- [Workflow evaluation plugin API reference](https://docs.mistral.ai/studio/observability/evaluations/workflows-plugin/api-reference.md): Reference for evaluation.run(), its result, and the plugin's imports.

- [Building blocks](https://docs.mistral.ai/studio/observability/evaluations/workflows-plugin/building-blocks.md): When your workflow already manages its own fan-out, for example with custom child workflow orchestration, call the steps of evaluation.run() yourself instead.

- [Decorators](https://docs.mistral.ai/studio/observability/evaluations/workflows-plugin/decorators.md): Every function you pass to the plugin runs as a Temporal activity.

- [Optimize prompts and parameters in a workflow](https://docs.mistral.ai/studio/observability/evaluations/workflows-plugin/optimization.md): evaluation.optimize() runs the optimizer inside a workflow.

- [Workflow evaluation plugin](https://docs.mistral.ai/studio/observability/evaluations/workflows-plugin.md): The Workflow evaluation plugin (mistralai-workflows-plugins-evaluations) runs offline evaluations inside Mistral Workflows.

- [Rescore persisted runs in a workflow](https://docs.mistral.ai/studio/observability/evaluations/workflows-plugin/rescoring.md): evaluation.rescore() scores the outputs already persisted in Studio without re-running the task, with your scorers running as activities.

- [Task modes](https://docs.mistral.ai/studio/observability/evaluations/workflows-plugin/task-modes.md): The task parameter of evaluation.run() accepts three kinds of values.

- [Observability](https://docs.mistral.ai/studio/observability.md): Observability is in Private Preview and is available for Enterprise-tier organizations only.

- [Data redaction](https://docs.mistral.ai/studio/observability/traces/data-redaction.md): Spans capture the input and output of each operation, including prompts, responses, and tool call arguments and results.

- [Explore traces](https://docs.mistral.ai/studio/observability/traces/explorer.md): The Trace Explorer is where you search, filter, and inspect every trace flowing through your AI applications.

- [Distributed tracing](https://docs.mistral.ai/studio/observability/traces.md): Every request in your AI application is captured as a trace: a tree of spans representing every step in the execution chain.

- [Send traces](https://docs.mistral.ai/studio/observability/traces/send-traces.md): This page covers how to instrument each supported data source so it sends OpenTelemetry traces to Mistral.

- [Use context objects](https://docs.mistral.ai/studio/observability/evaluations/advanced-guides/context-objects.md): Reference for the typed context objects passed to tasks, scorers, run evaluators, and metadata callbacks.

- [Iterate locally](https://docs.mistral.ai/studio/observability/evaluations/advanced-guides/local-mode.md): Run evaluations with local=True to skip uploading results to Studio during development.

- [Multiple evaluators](https://docs.mistral.ai/studio/observability/evaluations/advanced-guides/multiple-evaluators.md): Pass several evaluators to a single run and get independent statistics for each metric.

- [Reduce variance with multiple generations](https://docs.mistral.ai/studio/observability/evaluations/advanced-guides/num-generations.md): Run a non-deterministic task several times per record with num_generations to reduce variance.

- [Rescore persisted runs](https://docs.mistral.ai/studio/observability/evaluations/advanced-guides/rescoring.md): Score outputs already persisted in Studio with evaluation.rescore(), without re-running the task.

- [Retry failed records](https://docs.mistral.ai/studio/observability/evaluations/advanced-guides/retry-failed-records.md): Retry only the failed records of an evaluation run and patch the results in place.

- [Use run-level evaluators](https://docs.mistral.ai/studio/observability/evaluations/advanced-guides/run-evaluators.md): Use run evaluators to compute global assertions and aggregate metrics over all records of a run.

- [API reference](https://docs.mistral.ai/studio/observability/evaluations/api-reference.md): Reference for the Evaluation SDK's core types and the evaluation.run() entry point.

- [Datasets](https://docs.mistral.ai/studio/observability/evaluations/datasets.md): Build the test cases that drive an offline evaluation, from Python dicts or Studio datasets.

- [Evaluators](https://docs.mistral.ai/studio/observability/evaluations/evaluators.md): Define evaluators that score each record of a run with a scorer function, an optional description, and a goal.

- [Set goals](https://docs.mistral.ai/studio/observability/evaluations/goals.md): Set pass/fail goals on evaluator scores and see PASS or FAIL verdicts in the terminal and in Studio.

- [Limits](https://docs.mistral.ai/studio/observability/evaluations/limits.md): Limits enforced by the evaluations API, what happens when you exceed them, and how to restructure an evaluation.

- [Optimize prompts and parameters](https://docs.mistral.ai/studio/observability/evaluations/optimization.md): Automatically search for the best prompt or parameters by scoring variations against your existing evaluators.

- [Offline evaluations](https://docs.mistral.ai/studio/observability/evaluations.md): Run offline evaluations on your LLM pipelines with the Evaluation SDK: define a dataset, a task, and scorers, then review results in Studio.

- [Configure statistics](https://docs.mistral.ai/studio/observability/evaluations/statistics.md): Configure the run-level statistics an evaluator exposes, such as averages, totals, percentiles, or F1.

- [Configure system params](https://docs.mistral.ai/studio/observability/evaluations/system-params.md): Externalize model, prompt, and other task settings with System so each run records which parameters produced its results.

- [Workflow evaluation plugin API reference](https://docs.mistral.ai/studio/observability/evaluations/workflows-plugin/api-reference.md): Reference for evaluation.run(), its result, and the imports of the workflows evaluation plugin.

- [Building blocks](https://docs.mistral.ai/studio/observability/evaluations/workflows-plugin/building-blocks.md): Call the individual steps of evaluation.run() yourself when your workflow manages its own fan-out.

- [Decorators](https://docs.mistral.ai/studio/observability/evaluations/workflows-plugin/decorators.md): Mark tasks, scorers, and callbacks as Temporal activities and set their timeout, retries, and concurrency.

- [Optimize prompts and parameters in a workflow](https://docs.mistral.ai/studio/observability/evaluations/workflows-plugin/optimization.md): Run evaluation.optimize() inside a workflow to search over tunable slots and return the best configuration.

- [Workflow evaluation plugin](https://docs.mistral.ai/studio/observability/evaluations/workflows-plugin.md): Run offline evaluations inside Mistral Workflows with the evaluation plugin, which executes tasks and scorers as Temporal activities.

- [Rescore persisted runs in a workflow](https://docs.mistral.ai/studio/observability/evaluations/workflows-plugin/rescoring.md): Rescore persisted runs from a workflow with evaluation.rescore(), running your scorers as activities.

- [Task modes](https://docs.mistral.ai/studio/observability/evaluations/workflows-plugin/task-modes.md): Pass a decorated function, a workflow class, or a workflow name as the task, and see how each one fans out the dataset.

- [Observability](https://docs.mistral.ai/studio/observability.md): Trace, debug, and evaluate your AI applications in Mistral Studio with distributed tracing and offline evaluations.

- [Data redaction](https://docs.mistral.ai/studio/observability/traces/data-redaction.md): How client-side redaction scrubs secrets and personally identifiable information from spans before they leave your environment.

- [Explore traces](https://docs.mistral.ai/studio/observability/traces/explorer.md): Search, filter, and inspect traces and spans in the Trace Explorer, and turn spans into dataset records.

- [Distributed tracing](https://docs.mistral.ai/studio/observability/traces.md): Capture every request in your AI application as an OpenTelemetry trace, a tree of spans with inputs, outputs, latency, and token counts.

- [Send traces](https://docs.mistral.ai/studio/observability/traces/send-traces.md): Instrument Mistral products, the Mistral SDK, and your own code to send OpenTelemetry traces to Mistral.

- [Studio](https://docs.mistral.ai/studio.md): Studio is Mistral's developer platform for AI applications.

- [Moderation & Guardrailing](https://docs.mistral.ai/studio/safety-moderation.md): When deploying LLMs in production, different verticals may require different levels of guardrailing.

- [Agentic Search](https://docs.mistral.ai/studio/search/agentic-search.md): Agentic Search helps agents answer questions when the answer is not in the first chunk returned by retrieval.

2 lines shown here cut at 300 characters. The raw artifact at this commit is linked above.