Hugging Face · Arazzo Workflow

Hugging Face Search and Inspect a Model

Version 1.0.0

Search the Hub for a model, fetch its full record, then inspect a specific revision.

1 workflow 2 source APIs 1 provider
View Spec View on GitHub ArazzoWorkflows

Provider

hugging-face

Workflows

search-and-inspect-model
Find a model by search term and inspect it at a chosen revision.
Searches the Hub for models matching a query, takes the first result, loads the full model card, and resolves the model state at a specific revision.
3 steps inputs: limit, pipelineTag, revision, search outputs: modelTags, revisionSha, topModelId
1
searchModels
Run a full-text search against the Hub, returning the most relevant models with full card data so the top match can be resolved.
2
getModelInfo
Retrieve the detailed model record for the top search result using its repository id.
3
getModelAtRevision
Read the model information pinned to the requested Git revision so the caller can compare the default branch against a tagged or committed state.

Source API Descriptions

Arazzo Workflow Specification

Raw ↑
arazzo: 1.0.1
info:
  title: Hugging Face Search and Inspect a Model
  summary: Search the Hub for a model, fetch its full record, then inspect a specific revision.
  description: >-
    A discovery flow over the Hugging Face Hub API. The workflow runs a
    full-text model search, selects the top match, retrieves the detailed model
    record by its repository id, and then reads the model information pinned to a
    specific Git revision (branch, tag, or commit SHA). Every step spells out its
    request inline so the flow can be read and executed without opening the
    underlying OpenAPI description.
  version: 1.0.0
  x-realizes-capability-ids:
  - BC-610.60
  x-capability-derivation:
    method: 'deterministic join: sourceDescriptions -> per-tag OpenAPI -> tag/capability edge. No classification at this step.'
    min_confidence: 0.7
    sources:
    - capability_id: BC-610.60
      capability_name: Artificial Intelligence Management
      spec: hugging-face-models-api-openapi.yml
      confidence: 0.7
    model: Turbo EA Capabilities by Vincent Verdet — Turbo EA, https://github.com/vincentmakes/turbo-ea-capabilities, CC BY 4.0
sourceDescriptions:
- name: infoApi
  url: ../openapi/hugging-face-info-api-openapi.yml
  type: openapi
- name: modelsApi
  url: ../openapi/hugging-face-models-api-openapi.yml
  type: openapi
workflows:
- workflowId: search-and-inspect-model
  summary: Find a model by search term and inspect it at a chosen revision.
  description: >-
    Searches the Hub for models matching a query, takes the first result, loads
    the full model card, and resolves the model state at a specific revision.
  inputs:
    type: object
    required:
    - search
    - revision
    properties:
      search:
        type: string
        description: Full-text search query used to find models on the Hub.
      pipelineTag:
        type: string
        description: Optional pipeline task type to narrow the search (e.g. text-generation).
      revision:
        type: string
        description: Git revision (branch, tag, or commit SHA) to inspect.
      limit:
        type: integer
        description: Maximum number of search results to return.
        default: 10
  steps:
  - stepId: searchModels
    description: >-
      Run a full-text search against the Hub, returning the most relevant models
      with full card data so the top match can be resolved.
    operationId: listModels
    parameters:
    - name: search
      in: query
      value: $inputs.search
    - name: pipeline_tag
      in: query
      value: $inputs.pipelineTag
    - name: limit
      in: query
      value: $inputs.limit
    - name: full
      in: query
      value: true
    - name: sort
      in: query
      value: downloads
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      topModelId: $response.body#/0/id
      results: $response.body
    onSuccess:
    - name: haveMatch
      type: goto
      stepId: getModelInfo
      criteria:
      - context: $response.body
        condition: $.length > 0
        type: jsonpath
  - stepId: getModelInfo
    description: >-
      Retrieve the detailed model record for the top search result using its
      repository id.
    operationId: getModel
    parameters:
    - name: repo_id
      in: path
      value: $steps.searchModels.outputs.topModelId
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      modelId: $response.body#/id
      sha: $response.body#/sha
      tags: $response.body#/tags
  - stepId: getModelAtRevision
    description: >-
      Read the model information pinned to the requested Git revision so the
      caller can compare the default branch against a tagged or committed state.
    operationId: getModelRevision
    parameters:
    - name: repo_id
      in: path
      value: $steps.searchModels.outputs.topModelId
    - name: revision
      in: path
      value: $inputs.revision
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      revisionSha: $response.body#/sha
  outputs:
    topModelId: $steps.searchModels.outputs.topModelId
    modelTags: $steps.getModelInfo.outputs.tags
    revisionSha: $steps.getModelAtRevision.outputs.revisionSha

Work with this as data

Every workflow here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for arazzo workflows

4 MCP tools reach this
  • find_arazzoBrowse and filter every workflow in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This workflow
curl "https://apis.io/api/v1/arazzo/hugging-face-search-and-inspect-model-workflow"
All arazzo workflows
curl "https://apis.io/api/v1/arazzo?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.