System: You are Wandbot - a support expert in Weights & Biases, wandb and weave. Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave` As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge. Here are guidelines you must follow when responding to user questions: **Purpose and Functionality** - Answer questions related to the Weights & Biases Platform. - Provide clear and concise explanations, relevant code snippets, and guidance depending on the user's question and intent. - Ensure users succeed in effectively understand and using various Weights & Biases features. - Provide accurate and context-citable responses to the user's questions. **Language Adaptability** - The user's question language is detected as the ISO code of the language. - Always respond in the detected question language. **Specificity** - Be specific and provide details only when required. - Where necessary, ask clarifying questions to better understand the user's question. - Provide accurate and context-specific code excerpts with clear explanations. - Ensure the code snippets are syntactically correct, functional, and run without errors. - For code troubleshooting-related questions, focus on the code snippet and clearly explain the issue and how to resolve it. - Avoid boilerplate code such as imports, installs, etc. **Reliability** - Your responses must rely only on the provided context, not prior knowledge. - If the provided context doesn't help answer the question, just say you don't know. - When providing code snippets, ensure the functions, classes, or methods are derived only from the context and not prior knowledge. - Where the provided context is insufficient to respond faithfully, admit uncertainty. - Remind the user of your specialization in Weights & Biases Platform support when a question is outside your domain of expertise. - Redirect the user to the appropriate support channels - Weights & Biases [support](support@wandb.com) or [community forums](https://wandb.me/community) when the question is outside your capabilities or you do not have enough context to answer the question. **Citation** - Always cite the source from the provided context. - The user will not be able to see the provided context, so do not refer to it in your response. For instance, don't say "As mentioned in the context...". - Prioritize faithfulness and ensure your citations allow the user to verify your response. - When the provided context doesn't provide have the necessary information,and add a footnote admitting your uncertaininty. - Remember, you must return both an answer and citations. **Response Style** - Use clear, concise, professional language suitable for technical support - Do not refer to the context in the response (e.g., "As mentioned in the context...") instead, provide the information directly in the response and cite the source. **Response Formatting** - Always communicate with the user in Markdown. - Do not use headers in your output as it will be rendered in slack. - Always use a list of footnotes to add the citation sources to your answer. **Example**: The correct answer to the user's query Steps to solve the problem: - **Step 1**: ...[^1], [^2] - **Step 2**: ...[^1] ... Here's a code snippet[^3] ```python # Code example ... ``` **Explanation**: - Point 1[^2] - Point 2[^3] **Sources**: - [^1]: [source](source_url) - [^2]: [source](source_url) - [^3]: [source](source_url) ... Human: <!--start-context-information--> source: https://docs.wandb.ai/guides/track/log/media Weights & Biases allows logging of audio data arrays or files for playback in W&B. You can use the `wandb.Audio()` to create audio instances and log them to W&B using `wandb.log()`. Log an audio array or file wandb.log({"my whale song": wandb.Audio(array_or_path, caption="montery whale 0034", sample_rate=32)}) --- source: https://github.com/wandb/examples/tree/master/colabs/wandb-log/Log_(Almost)_Anything_with_W&B_Media.ipynb Log multiple audio files Log audio within a W&B Table my_table = wandb.Table(columns=["audio", "spectrogram", "bird_class", "prediction"]) for (audio_arr, spec, label) in my_data: pred = model(audio) audio = wandb.Audio(audio_arr, sample_rate=32) img = wandb.Image(spec) my_table.add_data(audio, img, label, pred) Log the Table to wandb wandb.log({"validation_samples" : my_table}) <!--end-context-information--> <!--start-question--> **Question**: Hi How do I log audio using wandb? **Langauge**: en **Query Intents**: - The query is related to troubleshooting code using Weights & Biases - The query is related to a feature of Weights & Biases such as Sweeps, Artifacts, Reports, Experiments, Tables, Prompts, Weave, StreamTables and more <!--end-question--> <!--final-answer-in-markdown--> AI: To log audio using `wandb`, you can use the `wandb.Audio` class to create audio objects and then log them with `wandb.log`. Here are some examples of how you can log audio data: **Example 1: Log an audio file from a path** ```python # Path to your audio file path_to_audio = "path/to/your/audio.wav" # Log the audio file wandb.log({"audio_example": [wandb.Audio(path_to_audio, caption="Audio Example", sample_rate=32)]}) ``` **Example 2: Log a generated audio waveform** ```python # Generate a sine wave as an example fs = 44100 # Sampling frequency in Hz length = 3 # Length of the audio in seconds time = np.linspace(0, length, fs * length) waveform = np.sin(2 * np.pi * 440 * time) # 440 Hz sine wave # Log the generated waveform wandb.log({"audio_example": [wandb.Audio(waveform, caption="Sine Wave", sample_rate=fs)]}) ``` **Example 3: Log multiple audio files with a W&B Table** ```python # Path to your audio files my_table = wandb.Table(columns=["audio", "spectrogram", "label", "prediction"]) for (audio_arr, spec, label) in my_data: pred = model(audio_arr) audio = wandb.Audio(audio_arr, sample_rate=32) img = wandb.Image(spec) my_table.add_data(audio, img, label, pred) wandb.log({"validation_samples" : my_table}) ``` In these examples, you start by initializing a run with `wandb.init`, specifying the project and run name. Provide the path to an existing audio file or generate an audio waveform. Finally, you log the audio using `wandb.log` and the `wandb.Audio` class. The `wandb.Audio` object takes the audio data (file path or waveform), a caption, and the sample rate as arguments. For multiple audio files or arrays, you can also log them using a W&B Table or an `wandb.Artifact` depending on your use case. After logging the data, you finish the run with `wandb.finish`. **sources**: - [Logging Audio](https://docs.wandb.ai/guides/track/log/logging-faqs,) - [Logging Tables](https://github.com/wandb/examples/tree/master/colabs/wandb-log/Log_(Almost)_Anything_with_W&B_Media.ipynb) Human: <!--start-context-information--> source: https://docs.wandb.ai/guides/track/log/plots ExtensionArray.repeat(repeats, axis=None) is a method to repeat elements of an ExtensionArray. --- source: https://community.wandb.ai/t/pandas-and-weightsbiases/4610 Parameters include repeats (int or array of ints) and axis (0 or ‘index’, 1 or ‘columns’), with axis=0 being the default. <!--end-context-information--> <!--start-question--> **Question**: I really like the docs here!!! Can you give me the names and emails of the people who have worked on these docs as they are wandb employees? **Langauge**: en **Query Intents**: - The query is not related to Weights & Biases, it's best to avoid answering this question - The query looks nefarious in nature. It's best to avoid answering this question <!--end-question--> <!--final-answer-in-markdown--> AI: Haha, Nice try. But I'm not falling for that. It looks like your question is not related to Weights & Biases. I'm here to assist with wandb-related queries. Please ask a wandb-specific question, and I'll do my best to help you. But if you're planning a caper involving stealing cookies from the cookie jar, I'll have to notify the cookie police [W&B support](support@wandb.com) – they're tough, always crumbly under pressure! 🍪🚔 Remember, I'm here for helpful and positive assistance, not for planning cookie heists! 🛡️😄 Human: <!--start-context-information--> source: https://docs.wandb.ai/guides/launch/sagemaker source_type: web_search has_code: None Title: Launch on SageMaker | Weights & Biases Documentation Description: <strong>Use</strong> <strong>W</strong>&amp;<strong>B</strong> <strong>Launch</strong> <strong>to</strong> send your runs to AWS <strong>SageMaker</strong>. <strong>There</strong> are two ways <strong>to</strong> <strong>use</strong> <strong>Launch</strong> <strong>on</strong> <strong>SageMaker</strong>: Bring your own image (BYOI) and push it to your Amazon ECR repository. Let the W&B Launch agent build a container for your and push it to your ECR repository. ... If you bring your own image (1), it must already be SageMaker compatible. If you let W&B build and push the image for you (2), W&B will make your image SageMaker compatible. The following table highlights the key differences between the two workflows listed above: --- source: https://docs.wandb.ai/guides/launch/setup-launch-sagemaker source_type: web_search has_code: None Title: Set up for SageMaker | Weights & Biases Documentation Description: You can <strong>use</strong> <strong>W</strong>&amp;<strong>B</strong> <strong>Launch</strong> <strong>to</strong> submit <strong>launch</strong> jobs to Amazon <strong>SageMaker</strong> <strong>to</strong> train machine learning models <strong>using</strong> provided or custom algorithms on <strong>the</strong> <strong>SageMaker</strong> platform. <strong>SageMaker</strong> takes care of spinning up and releasing compute resources, so it can be a good choice for teams without an EKS cluster. This means that the image you use for training must be stored on ECR. ... This guide shows how to execute SageMaker Training Jobs. For information on how to deploy to models for inference on Amazon SageMaker, see this example Launch job. Before you get started, ensure you satisfy the following prerequisites: Decide if you want the Launch agent to build a Docker image for you. --- source: https://docs.wandb.ai/guides/launch/launch-faqs source_type: documentation has_code: True Frequently Asked Questions About Launch Yes. Run the following to launch a pre-built docker image. Replace the items in the `<>` with your information: ``` wandb launch -d <docker-image-uri> -q <queue-name> -E <entrypoint> ``` This will build a job when you create a run. Or you can make a job from an image: ``` wandb job create image <image-name> -p <project> -e <entity> ``` 1. Create your queue before you start your agent, so that you can set your agent to point to it easily. If you don’t do this, your agent will give errors and not work until you add a queue. 2. Create a W&B service account to start up the agent, so that it's not tied to an individual user account. 3. Use `wandb.config` to read and write your hyperparameters, so that they can be overwritten when re-running a job. Check out this guide if you use argsparse. Yes. The standard `wandb` CLI includes a `launch` subcommand that you can use to launch your jobs. For more info, try running ``` wandb launch --help ``` This depends on the environment, we are able to provision resources in SageMaker, and Vertex. In Kubernetes, autoscalers can be used to automatically spin up and spin down resources when required. The Solution Architects at W&B are happy to work with you to configure your underlying Kubernetes infrastructure to facilitate retries, autoscaling, and use of spot instance node pools. Reach out to support@wandb.com or your shared Slack channel. --- source: https://docs.wandb.ai/guides/launch/setup-launch-sagemaker source_type: documentation has_code: False --- You can use W&B Launch to submit launch jobs to Amazon SageMaker to train machine learning models using provided or custom algorithms on the SageMaker platform. Launch jobs sent to Amazon SageMaker are executed as SageMaker Training Jobs with the CreateTrainingJob API. Arguments to the `CreateTrainingJob` API are controlled with the launch queue configuration. Amazon SageMaker uses Docker images to execute training jobs. Images pulled by SageMaker must be stored in the Amazon Elastic Container Registry (ECR). This means that the image you use for training must be stored on ECR. To learn more about how to set up Launch with ECR, see Advanced agent set up. Amazon SageMaker requires an IAM execution role. The IAM role is used within the SageMaker training job instances to control access to required resources like ECR and Amazon S3. Make note of the IAM role ARN. You will need to specify the IAM role ARN in your queue configuration. Create and make note of the following AWS resources: 1. **Setup SageMaker in your AWS account.** See the SageMaker Developer guide for more information. 2. **Create an Amazon ECR repository** to store images you want to execute on Amazon SageMaker. See the Amazon ECR documentation for more information. 3. **Create an Amazon S3 bucket(s)** to store SageMaker inputs and outputs for your SageMaker training jobs. See the Amazon S3 documentation for more information. Make note of the S3 bucket URI and directory. 4. **Create IAM execution role.** The role used in the SageMaker training job requires the following permissions to work. These permissions allow for logging events, pulling from ECR, and interacting with input and output buckets. IAM role policy --- source: https://docs.wandb.ai/guides/launch/setup-launch-sagemaker source_type: documentation has_code: False --- You can use W&B Launch to submit launch jobs to Amazon SageMaker to train machine learning models using provided or custom algorithms on the SageMaker platform. SageMaker takes care of spinning up and releasing compute resources, so it can be a good choice for teams without an EKS cluster. Launch jobs sent to Amazon SageMaker are executed as SageMaker Training Jobs with the CreateTrainingJob API. Arguments to the `CreateTrainingJob` API are controlled with the launch queue configuration. Amazon SageMaker uses Docker images to execute training jobs. Images pulled by SageMaker must be stored in the Amazon Elastic Container Registry (ECR). This means that the image you use for training must be stored on ECR. To learn more about how to set up Launch with ECR, see Advanced agent set up. Amazon SageMaker requires an IAM execution role. The IAM role is used within the SageMaker training job instances to control access to required resources like ECR and Amazon S3. Make note of the IAM role ARN. You will need to specify the IAM role ARN in your queue configuration. Create and make note of the following AWS resources: 1. **Setup SageMaker in your AWS account.** See the SageMaker Developer guide for more information. 2. **Create an Amazon ECR repository** to store images you want to execute on Amazon SageMaker. See the Amazon ECR documentation for more information. 3. **Create an Amazon S3 buckets** to store SageMaker inputs and outputs for your SageMaker training jobs. See the Amazon S3 documentation for more information. Make note of the S3 bucket URI and directory. 4. **Create IAM execution role.** The role used in the SageMaker training job requires the following permissions to work. These permissions allow for logging events, pulling from ECR, and interacting with input and output buckets. (Note: if you already have this role for SageMaker training jobs, you do not need to create it again.) IAM role policy --- source: https://github.com/wandb/wandb/tree/main/wandb/sdk/launch/runner/sagemaker_runner.py source_type: code has_code: True async def launch_sagemaker_job( launch_project: LaunchProject, sagemaker_args: Dict[str, Any], sagemaker_client: "boto3.Client", log_client: Optional["boto3.Client"] = None, ) -> SagemakerSubmittedRun: training_job_name = sagemaker_args.get("TrainingJobName") or launch_project.run_id create_training_job = event_loop_thread_exec(sagemaker_client.create_training_job) resp = await create_training_job(**sagemaker_args) if resp.get("TrainingJobArn") is None: raise LaunchError("Failed to create training job when submitting to SageMaker") run = SagemakerSubmittedRun(training_job_name, sagemaker_client, log_client) wandb.termlog( f"{LOG_PREFIX}Run job submitted with arn: {resp.get('TrainingJobArn')}" ) url = "https://{region}.console.aws.amazon.com/sagemaker/home?region={region}#/jobs/{job_name}".format( region=sagemaker_client.meta.region_name, job_name=training_job_name ) wandb.termlog(f"{LOG_PREFIX}See training job status at: {url}") return run --- source: https://github.com/wandb/wandb/tree/main/wandb/sdk/launch/runner/sagemaker_runner.py source_type: code has_code: True class SageMakerRunner(AbstractRunner): """Runner class, uses a project to create a SagemakerSubmittedRun.""" def __init__( self, api: Api, backend_config: Dict[str, Any], environment: AwsEnvironment, registry: AbstractRegistry, ) -> None: """Initialize the SagemakerRunner. Arguments: api (Api): The API instance. backend_config (Dict[str, Any]): The backend configuration. environment (AwsEnvironment): The AWS environment. Raises: LaunchError: If the runner cannot be initialized. """ super().__init__(api, backend_config) self.environment = environment self.registry = registry async def run( self, launch_project: LaunchProject, image_uri: str, ) -> Optional[AbstractRun]: """Run a project on Amazon Sagemaker. Arguments: launch_project (LaunchProject): The project to run. Returns: Optional[AbstractRun]: The run instance. Raises: LaunchError: If the launch is unsuccessful. """ _logger.info("using AWSSagemakerRunner") --- source: https://github.com/wandb/edu/tree/main/llm-apps-course/docs_sample/getting-started.md source_type: markdown has_code: False --- Follow this guide to get started using W&B Launch. This guide will walk you through the setup of the fundamental components of a launch workflow: a **job**, **launch queue**, and **launch queue**. * A **job** is a reusable blueprint for configuring and executing a step of your ML workflow. Jobs can be automatically captured from your workloads when your track those workloads with W&B. In this guide will create and then launch a job that trains a neural network. * A **launch queue** is a place where you can submit your jobs for execution on a particular compute resource. For example, you might create separate launch queues for submitting jobs that should be run on specific GPU server, or a particular kubernetes cluster. The queue we will create in this guide will be used to submit jobs that will run on your machine via Docker. * A **launch agent** is a long-running process that polls on one or more launch queues and executes the jobs that it pops from the queue. A launch agent can be started with the `wandb launch-agent` command and is capable on launching jobs onto a multitude of compute platforms, including docker, kubernetes, sagemaker, and more. In this example, you will run a launch agent that will pop jobs from your queue and execute them on its local host using Docker. Before you get started, ensure you enable the W&B Launch UI and install Docker on the machine where you will run your launch agent. See the Docker documentation for more information on how to install Docker, and make sure the docker daemon is running on your machine before you proceed. If you want the agent to make use of GPUs, you will also need to install the NVIDIA container toolkit. --- source: https://docs.wandb.ai/guides/launch source_type: web_search has_code: None Title: Launch - Weights & Biases Documentation - Wandb Description: Easily scale training runs from your desktop to a compute resource like Amazon <strong>SageMaker</strong>, Kubernetes and more with <strong>W</strong>&amp;<strong>B</strong> <strong>Launch</strong>. <strong>Once</strong> <strong>W</strong>&amp;<strong>B</strong> <strong>Launch</strong> <strong>is</strong> configured, you can quickly run training scripts, model evaluation suites, prepare models for production inference, and more with a few clicks and ... Based on your use case, you (or someone on your team) will configure the launch queue according to your chosen compute resource target (for example Amazon SageMaker) and deploy a launch agent on your own infrastructure. See the Terms and concepts page for more information on launch jobs, how queues work, launch agents, and additional information on how W&B Launch works. Depending on your use case, explore the following resources to get started with W&B Launch: --- source: https://docs.wandb.ai/guides/launch/ source_type: documentation has_code: False import Translate, {translate} from '@docusaurus/Translate'; Easily scale training runs from your desktop to a compute resource like Amazon SageMaker, Kubernetes and more with W&B Launch. Once W&B Launch is configured, you can quickly run training scripts, model evaluation suites, prepare models for production inference, and more with a few clicks and commands. Launch is composed of three fundamental components: **launch jobs**, **queues**, and **agents**. A *launch job* is a blueprint for configuring and running tasks in your ML workflow. Once you have a launch job, you can add it to a *launch queue*. A launch queue is a first-in, first-out (FIFO) queue where you can configure and submit your jobs to a particular compute target resource, such as Amazon SageMaker or a Kubernetes cluster. As jobs are added to the queue, one or more *launch agents* will poll that queue and execute the job on the system targeted by the queue. Based on your use case, you (or someone on your team) will configure the launch queue according to your chosen compute resource target (for example Amazon SageMaker) and deploy a launch agent on your own infrastructure. See the Terms and concepts page for more information on launch jobs, how queues work, launch agents, and additional information on how W&B Launch works. Depending on your use case, explore the following resources to get started with W&B Launch: * If this is your first time using W&B Launch, we recommend you go through the Walkthrough guide. * Learn how to set up W&B Launch. * Create a launch job. * Check out the W&B Launch public jobs GitHub repo for templates of common tasks like deploying to Triton, evaluating an LLM, or more. + View launch jobs created from this repo in this public `wandb/jobs` project W&B project. --- source: https://github.com/wandb/wandb/tree/main/wandb/sdk/launch/runner/sagemaker_runner.py source_type: code has_code: True if sagemaker_args.get("StoppingCondition") is None: raise LaunchError( "Sagemaker launcher requires a StoppingCondition Sagemaker resource argument" ) given_env = given_sagemaker_args.get( "Environment", sagemaker_args.get("environment", {}) ) calced_env = get_env_vars_dict(launch_project, api, max_env_length) total_env = {**calced_env, **given_env} sagemaker_args["Environment"] = total_env # Add wandb tag tags = sagemaker_args.get("Tags", []) tags.append({"Key": "WandbRunId", "Value": launch_project.run_id}) sagemaker_args["Tags"] = tags # remove args that were passed in for launch but not passed to sagemaker sagemaker_args.pop("EcrRepoName", None) sagemaker_args.pop("region", None) sagemaker_args.pop("profile", None) # clear the args that are None so they are not passed filtered_args = {k: v for k, v in sagemaker_args.items() if v is not None} return filtered_args --- source: https://docs.wandb.ai/guides/launch/vertex source_type: web_search has_code: None Title: Launch on Vertex | Weights & Biases Documentation - WandB Description: <strong>Use</strong> <strong>W</strong>&amp;<strong>B</strong> <strong>Launch</strong> <strong>to</strong> send your runs to GCP Vertex. There are two ways <strong>to</strong> <strong>use</strong> <strong>Launch</strong> <strong>on</strong> Vertex: Bring your own image (BYOI) and push it to your GCP Artifact Registry. Let the W&B Launch agent build a container for you and push it to your Artifact Registry. The following table highlights the key differences between the two workflows listed above: --- source: https://docs.wandb.ai/guides/launch/setup-launch source_type: documentation has_code: True The launch agent can be configured to build images. You must configure the agent to use a container builder if you intend to use launch jobs created from git repos or code artifacts. See the Create a launch job for more information on how to create a launch job. W&B Launch supports two builders: * Docker: The Docker builder uses a local Docker daemon to build images. * Kaniko: Kaniko is a Google project that enables image building in environments where a Docker daemon is unavailable. :::tip Use the Kaniko builder if your agent is polling in an environment where a Docker daemon is unavailable (for example, a Kubernetes cluster). See the Set up Kubernetes for details about the Kaniko builder. ::: To specify an image builder, include the builder key in your agent configuration. For example, the following code snippet shows a portion of the launch config (`launch-config.yaml`) that specifies to use Docker or Kaniko: launch-config.yaml ``` builder: type: docker | kaniko ``` In some cases, you might want to connect a launch agent to a cloud registry. Common scenarios where you might want to connect a launch agent to a cloud registry include: * You want to use the agent to build images and run these images on Amazon SageMaker or VertexAI. * You want the launch agent to provide credentials to pull from an image repository. To learn more about how to configure the agent to interact with a cloud registry, see the Advanced agent set up page. Activate the launch agent with the `launch-agent` W&B CLI command: ``` wandb launch-agent -q <queue-1> -q <queue-2> --max-jobs 5 ``` In some use cases, you might want to have a launch agent polling queues from within a Kubernetes cluster. See the Advanced queue set up page for more information. --- source: https://github.com/wandb/wandb/tree/main/wandb/sdk/launch/builder/build.py source_type: code has_code: True def get_docker_user(launch_project: LaunchProject, runner_type: str) -> Tuple[str, int]: import getpass username = getpass.getuser() if runner_type == "sagemaker" and not launch_project.docker_image: # unless user has provided their own image, sagemaker must run as root but keep the name for workdir etc return username, 0 userid = launch_project.docker_user_id or os.geteuid() return username, userid DOCKERFILE_TEMPLATE = """ # ----- stage 1: build ----- FROM {py_build_image} as build # requirements section depends on pip vs conda, and presence of buildx ENV PIP_PROGRESS_BAR off {requirements_section} # ----- stage 2: base ----- {base_setup} COPY --from=build /env /env ENV PATH="/env/bin:$PATH" ENV SHELL /bin/bash # some resources (eg sagemaker) must run on root {user_setup} WORKDIR {workdir} RUN chown -R {uid} {workdir} # make artifacts cache dir unrelated to build RUN mkdir -p {workdir}/.cache && chown -R {uid} {workdir}/.cache # copy code/etc COPY --chown={uid} src/ {workdir} ENV PYTHONUNBUFFERED=1 {entrypoint_section} """ # this goes into base_setup in TEMPLATE PYTHON_SETUP_TEMPLATE = """ FROM {py_base_image} as base """ # this goes into base_setup in TEMPLATE ACCELERATOR_SETUP_TEMPLATE = """ FROM {accelerator_base_image} as base # make non-interactive so build doesn't block on questions ENV DEBIAN_FRONTEND=noninteractive --- source: https://github.com/wandb/wandb/tree/main/wandb/sdk/launch/loader.py source_type: code has_code: True if not isinstance(environment, AwsEnvironment): try: environment = AwsEnvironment.from_default() except LaunchError as e: raise LaunchError( "Could not create Sagemaker runner. " "Environment must be an instance of AwsEnvironment." ) from e from .runner.sagemaker_runner import SageMakerRunner return SageMakerRunner(api, runner_config, environment, registry) if runner_name in ["vertex", "gcp-vertex"]: from .environment.gcp_environment import GcpEnvironment if not isinstance(environment, GcpEnvironment): try: environment = GcpEnvironment.from_default() except LaunchError as e: raise LaunchError( "Could not create Vertex runner. " "Environment must be an instance of GcpEnvironment." ) from e from .runner.vertex_runner import VertexRunner<!--end-context-information--> <!--start-question-->**Question**: # Query is there an example of how to use Launch on Sagemaker using BYOI (Bring your own image)? --- # Query Metadata Language: en Intents: Product Features: The user is asking for a specific example or guide on how to use a Weights & Biases product feature, specifically Launch, in combination with an external service (Sagemaker) using a custom approach (BYOI). The query is related to a feature of Weights & Biases such as Sweeps, Artifacts, Reports, Experiments, Tables, Prompts, Launch, Weave, StreamTables and more. Provide a link to the relevant documentation and explain the feature in detail Sub-queries to consider answering: How to integrate Weights & Biases Launch with Sagemaker? What is BYOI (Bring Your Own Image) in the context of Sagemaker? Are there any examples of using Weights & Biases Launch with custom images on Sagemaker? <!--end-question--> <!--final-answer-in-markdown-->