Introducing Pipelines for Lengthy-Working AI Workflows

This weblog submit focuses on new options and enhancements. For a complete record, together with bug fixes, please see the launch notes.

Clarifai’s Compute Orchestration enables you to deploy fashions by yourself compute, management how they scale, and resolve the place inference runs throughout clusters and nodepools.

As AI methods transfer past single inference calls towards long-running duties, multi-step workflows, and agent-driven execution, orchestration must do extra than simply begin containers. It must handle execution over time, deal with failure, and route visitors intelligently throughout compute.

This launch builds on that basis with native assist for long-running pipelines, mannequin routing throughout nodepools and environments, and agentic mannequin execution utilizing Mannequin Context Protocol (MCP).

Introducing Pipelines for Lengthy-Working, Multi-Step AI Workflows

AI methods don’t break at inference. They break when workflows span a number of steps, run for hours, or must get better from failure.

At present, groups depend on stitched-together scripts, cron jobs, and queue employees to handle these workflows. As agent workloads and MLOps pipelines develop extra complicated, this setup turns into exhausting to function, debug, and scale.

With Clarifai 12.0, we’re introducing Pipelines, a local strategy to outline, run, and handle long-running, multi-step AI workflows straight on the Clarifai platform.

Why Pipelines

Most AI platforms are optimized for short-lived inference calls. However actual manufacturing workflows look very totally different:

• Multi-step agent logic that spans instruments, fashions, and exterior APIs

• Lengthy-running jobs like batch processing, fine-tuning, or evaluations

• Finish-to-end MLOps workflows that require reproducibility, versioning, and management

Pipelines are constructed to deal with this class of issues.

Clarifai Pipelines act because the orchestration spine for superior AI methods. They allow you to outline container-based steps, management execution order or parallelism, handle state and secrets and techniques, and monitor runs from begin to end, all with out bolting collectively separate orchestration infrastructure.

Every pipeline is versioned, reproducible, and executed on Clarifai-managed compute, providing you with fine-grained management over how complicated AI workflows run at scale.

Let’s stroll by how Pipelines work, what you’ll be able to construct with them, and easy methods to get began utilizing the CLI and API. 

How Pipelines Work

At a excessive degree, a Clarifai Pipeline is a versioned, multi-step workflow made up of containerized steps that run asynchronously on Clarifai compute.

Every step is an remoted unit of execution with its personal code, dependencies, and useful resource settings. Pipelines outline how these steps join, whether or not they run sequentially or in parallel, and the way knowledge flows between them.

You outline a pipeline as soon as, add it, after which set off runs that may execute for minutes, hours, or longer.

Initialize a pipeline venture

This scaffolds a whole pipeline venture utilizing the identical construction and conventions as Clarifai customized fashions.

Every pipeline step follows the very same footprint builders already use when importing fashions to Clarifai: a configuration file, a dependency file, and an executable Python entrypoint.

A typical scaffolded pipeline seems like this:

On the pipeline degree, config.yaml defines how steps are linked and orchestrated, together with execution order, parameters, and dependencies between steps.

Every step is a self-contained unit that appears and behaves similar to a customized mannequin:

• config.yaml defines the step’s inputs, runtime, and compute necessities

• necessities.txt specifies the Python dependencies for that step

• pipeline_step.py accommodates the precise execution logic, the place you write code to course of knowledge, name fashions, or work together with exterior methods

This implies constructing pipelines feels instantly acquainted. If you happen to’ve already uploaded customized fashions to Clarifai, you’re working with the identical configuration fashion, the identical versioning mannequin, and the identical deployment mechanics—simply composed into multi-step workflows.

Add the pipeline

Clarifai builds and variations every step as a containerized artifact, guaranteeing reproducible runs.

Run the pipeline

As soon as operating, you’ll be able to monitor progress, examine logs, and handle executions straight by the platform.

Below the hood, pipeline execution is powered by Argo Workflows, permitting Clarifai to reliably orchestrate long-running, multi-step jobs with correct dependency administration, retries, and fault dealing with.

Pipelines are designed to assist the whole lot from automated MLOps workflows to superior AI agent orchestration, with out requiring you to function your individual workflow engine.

Word: Pipelines are at the moment out there in Public Preview.

You can begin attempting them at present and we welcome your suggestions as we proceed to iterate. For a step-by-step information on defining steps, importing pipelines, managing runs, and constructing extra superior workflows, take a look at the detailed documentation right here.

Mannequin Routing with Multi-Nodepool Deployments

With this launch, Compute Orchestration now helps mannequin routing throughout a number of nodepools inside a single deployment.

Mannequin routing permits a deployment to reference a number of pre-existing nodepools by a deployment_config.yaml. These nodepools can belong to totally different clusters and may span cloud, on-prem, or hybrid environments.

Right here’s how mannequin routing works:

• Nodepools are handled as an ordered precedence record. Requests are routed to the primary nodepool by default.

• A nodepool is taken into account absolutely loaded when queued requests exceed configured age or amount thresholds and the deployment has reached its max_replicas, or the nodepool has reached its most occasion capability.

• When this occurs, the subsequent nodepool within the record is routinely warmed and a portion of visitors is routed to it.

• The deployment’s min_replicas applies solely to the first nodepool.

• The deployment’s max_replicas applies independently to every nodepool, not as a world sum.

This method permits excessive availability and predictable scaling with out duplicating deployments or manually managing failover. Deployments can now span a number of compute swimming pools whereas behaving as a single, resilient service.

Learn extra about Multi-Nodepool Deployment right here. 

Agentic Capabilities with MCP Assist

Clarifai expands assist for agentic AI methods by making it simpler to mix agent-aware fashions with Mannequin Context Protocol integration. Fashions can uncover, name, and motive over each customized and open-source MCP servers throughout inference, whereas remaining absolutely managed on the Clarifai platform.

Agentic Fashions with MCP Integration

You’ll be able to add fashions with agentic capabilities through the use of the AgenticModelClass, which extends the usual mannequin class to assist instrument discovery and execution. The add workflow stays the identical as present customized fashions, utilizing the identical venture construction, configuration information, and deployment course of.

Agentic fashions are configured to work with MCP servers, which expose instruments that the mannequin can name throughout inference.

Key capabilities embrace:

• Iterative instrument calling inside a single predict or generate request

• Instrument discovery and execution dealt with by the agentic mannequin class

• Assist for each streaming and non-streaming inference

• Compatibility with the OpenAI-compatible API and Clarifai SDKs

An entire instance of importing and operating an agentic mannequin is accessible right here. This repository exhibits easy methods to add a GPT-OSS-20B mannequin with agentic capabilities enabled utilizing the AgenticModelClass.

Deploying Public MCP Servers on Clarifai

Clarifai has already supported deploying customized MCP servers, permitting groups to construct their very own instrument servers and run them on the platform. This launch expands that functionality by making it straightforward to deploy public MCP servers straight on the Platform.

Public MCP servers can now be uploaded utilizing a easy configuration, with out requiring groups to host or handle the server infrastructure themselves. As soon as deployed, these servers may be shared throughout fashions and workflows, permitting agentic fashions to entry the identical instruments.

This instance demonstrates easy methods to deploy a public, open-source MCP server on Clarifai as an API endpoint.

Pay-As-You-Go Billing with Pay as you go Credit

We’ve launched a brand new Pay-As-You-Go (PAYG) plan to make billing easier and extra predictable for self-serve customers.

The PAYG plan has no month-to-month minimums and much fewer characteristic gates. You prepay credit, use them throughout the platform, and pay just for what you eat. To enhance reliability, the plan additionally consists of auto-recharge, so long-running jobs don’t cease unexpectedly when credit run low.

That will help you get began, each verified consumer receives a one-time $5 welcome credit score, which can be utilized throughout inference, Compute Orchestration, deployments, and extra. It’s also possible to declare a further $5 in your group.

In order for you a deeper breakdown of how pay as you go credit work, what’s altering from earlier plans, and why we made this shift, get extra particulars on this weblog.

Clarifai as an Inference Supplier within the Vercel AI SDK

Clarifai is now out there as an inference supplier within the Vercel AI SDK. You should use Clarifai-hosted fashions straight by the OpenAI-compatible interface in @ai-sdk/openai-compatible, with out altering your present utility logic.

This makes it straightforward to swap in Clarifai-backed fashions for manufacturing inference whereas persevering with to make use of the identical Vercel AI SDK workflows you already depend on. Be taught extra right here

New Reasoning Fashions from the Ministral 3 Household

We’ve revealed two new open-weight reasoning fashions from the Ministral 3 household on Clarifai:

• Ministral-3-3B-Reasoning-2512

  A compact reasoning mannequin designed for effectivity, providing sturdy efficiency whereas remaining sensible to deploy on lifelike {hardware}.

• Ministral-3-14B-Reasoning-2512

  The biggest mannequin within the Ministral 3 household, delivering reasoning efficiency near a lot bigger methods whereas retaining the advantages of an environment friendly open-weight design.

Each fashions can be found now and can be utilized throughout Clarifai’s inference, orchestration, and deployment workflows.

Further Modifications

Platform Updates

We’ve made a couple of focused enhancements throughout the platform to enhance usability and day-to-day workflows.

• Added cleaner filters within the Management Middle, making charts simpler to navigate and interpret.

• Improved the Group & Logs view to make sure at present’s audit logs are included when choosing the final 7 days.

• Enabled stopping responses straight from the fitting panel when utilizing Examine mode within the Playground.

Python SDK Updates

This launch features a broad set of enhancements to the Python SDK and CLI, centered on stability, native runners, and developer expertise.

• Improved reliability of native mannequin runners, together with fixes for vLLM compatibility, checkpoint downloads, and runner ID conflicts.

• Launched higher artifact administration and interactive config.yaml creation throughout the mannequin add circulate.

• Expanded check protection and improved error dealing with throughout runners, mannequin loading, and OpenAI-compatible API calls.

A number of extra fixes and enhancements are included, overlaying dependency upgrades, surroundings dealing with, and CLI robustness. Be taught extra right here.

Able to Begin Constructing?

You can begin constructing with Clarifai Pipelines at present to run long-running, multi-step workflows straight on the platform. Outline steps, add them with the CLI, and monitor execution throughout your compute.

For manufacturing deployments, mannequin routing enables you to scale throughout a number of nodepools and clusters with built-in spillover and excessive availability.

If you happen to’re constructing agentic methods, you may as well allow agentic mannequin assist with MCP servers to provide fashions entry to instruments throughout inference.

Pipelines can be found in public preview. We’d love your suggestions as you construct.