Jina AI Integration — ModuleX AI

Field	Description	Required	Format
Jina AI API Key	Your Jina AI API key for authentication. Get your free key at https://jina.ai/?sui=apikey	Yes	`jina_xxxxxxxxxxxxxxxxxxxxxxxxxxxx`

generate_embeddings — Generate embeddings for text or images. Converts inputs to fixed-length vectors for semantic search, similarity matching, clustering, and RAG applications.

Parameters

input

array

required

Array of input strings or objects with ‘text’, ‘image’, or ‘pdf’ keys

model

string

Embedding model to use (Default: jina-embeddings-v3)

task

string

Task optimization type

dimensions

integer

Truncate embeddings to specified size

late_chunking

boolean

Enable late chunking mode (Default: false)

truncate

boolean

Auto-truncate content beyond max length (Default: false)

Response

{
  "additionalProperties": false,
  "properties": {
    "success": {
      "title": "Success",
      "type": "boolean"
    },
    "error": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Error"
    },
    "data": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Data"
    }
  },
  "required": [
    "success"
  ],
  "title": "GenerateEmbeddingsOutput",
  "type": "object"
}

rerank_documents — Re-rank documents by relevance to a query. Improves search result relevance for RAG and search applications.

Parameters

query

string

required

Search query to rank documents against

documents

array

required

Documents to rerank (strings or objects)

model

string

Reranker model to use (Default: jina-reranker-v2-base-multilingual)

top_n

integer

Number of top results to return

return_documents

boolean

Include document text in response (Default: true)

Response

{
  "additionalProperties": false,
  "properties": {
    "success": {
      "title": "Success",
      "type": "boolean"
    },
    "error": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Error"
    },
    "data": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Data"
    }
  },
  "required": [
    "success"
  ],
  "title": "RerankDocumentsOutput",
  "type": "object"
}

read_webpage — Read and parse web content in LLM-friendly format. Extracts structured content from web pages optimized for AI processing.

Parameters

url

string

required

The URL to read and parse

return_format

string

Output format (Default: markdown)

target_selector

string

CSS selectors to focus on specific elements

remove_selector

string

CSS selectors to exclude from page

wait_for_selector

string

CSS selectors to wait for before returning

with_links_summary

boolean

Gather all links at the end of response (Default: false)

with_images_summary

boolean

Gather all images at the end of response (Default: false)

timeout

integer

Maximum time in seconds to wait for webpage to load

no_cache

boolean

Bypass cache for fresh retrieval (Default: false)

Response

{
  "additionalProperties": false,
  "properties": {
    "success": {
      "title": "Success",
      "type": "boolean"
    },
    "error": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Error"
    },
    "data": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Data"
    },
    "title": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Title"
    },
    "description": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Description"
    },
    "url": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Url"
    },
    "content": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Content"
    },
    "links": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Links"
    },
    "images": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Images"
    },
    "usage": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Usage"
    }
  },
  "required": [
    "success"
  ],
  "title": "ReadWebpageOutput",
  "type": "object"
}

web_search — Search the web with LLM-optimized results. Returns search results in formats optimized for AI and enterprise search.

Parameters

query

string

required

The search query to execute

site

string

Limit search to specific domain (e.g. ‘github.com’)

return_format

string

Output format (Default: markdown)

num

integer

Maximum number of results to return

string

Two-letter country code for localized results

string

Two-letter language code for search

with_links_summary

boolean

Include links summary (Default: false)

with_images_summary

boolean

Include images summary (Default: false)

no_cache

boolean

Bypass cache for real-time data (Default: false)

Response

{
  "additionalProperties": false,
  "properties": {
    "success": {
      "title": "Success",
      "type": "boolean"
    },
    "error": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Error"
    },
    "data": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Data"
    },
    "results": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Results",
      "type": "array"
    },
    "count": {
      "default": 0,
      "title": "Count",
      "type": "integer"
    }
  },
  "required": [
    "success"
  ],
  "title": "WebSearchOutput",
  "type": "object"
}

deep_search — Perform comprehensive research combining web searching, reading, and reasoning. Acts as a research agent for thorough investigation.

Parameters

query

string

required

Research query or question to investigate

reasoning_effort

string

Reasoning effort level (low, medium, high) (Default: medium)

budget_tokens

integer

Maximum tokens for the process (overrides reasoning_effort)

max_attempts

integer

Maximum retries for problem solving

no_direct_answer

boolean

Force deeper search even for simple queries (Default: false)

max_returned_urls

integer

Maximum URLs in final answer

boost_hostnames

array

Domains to prioritize for content retrieval

bad_hostnames

array

Domains to exclude from content retrieval

only_hostnames

array

Only retrieve content from these domains

Response

{
  "additionalProperties": false,
  "properties": {
    "success": {
      "title": "Success",
      "type": "boolean"
    },
    "error": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Error"
    },
    "data": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Data"
    }
  },
  "required": [
    "success"
  ],
  "title": "DeepSearchOutput",
  "type": "object"
}

segment_text — Tokenize and segment text into chunks. Useful for counting tokens and preparing text for embedding in RAG applications.

Parameters

content

string

required

Text content to segment

tokenizer

string

Tokenizer to use (Default: cl100k_base)

return_tokens

boolean

Include tokens and IDs in response (Default: false)

return_chunks

boolean

Segment into semantic chunks (Default: true)

max_chunk_length

integer

Maximum characters per chunk (Default: 1000)

head

integer

Return only first N tokens (exclusive with tail)

tail

integer

Return only last N tokens (exclusive with head)

Response

{
  "additionalProperties": false,
  "properties": {
    "success": {
      "title": "Success",
      "type": "boolean"
    },
    "error": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Error"
    },
    "data": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Data"
    },
    "num_tokens": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Num Tokens"
    },
    "num_chunks": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Num Chunks"
    },
    "chunks": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Chunks"
    },
    "chunk_positions": {
      "anyOf": [
        {
          "items": {
            "items": {
              "type": "integer"
            },
            "type": "array"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Chunk Positions"
    },
    "tokens": {
      "anyOf": [
        {
          "items": {},
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Tokens"
    },
    "tokenizer": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Tokenizer"
    },
    "usage": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Usage"
    }
  },
  "required": [
    "success"
  ],
  "title": "SegmentTextOutput",
  "type": "object"
}

classify — Zero-shot classification for text or images. Classifies content into provided categories without training.

Parameters

input

array

required

Array of texts or image objects to classify

labels

array

required

List of classification categories

model

string

Classification model (Default: jina-embeddings-v3)

classifier_id

string

Existing classifier ID to reuse

Response

{
  "additionalProperties": false,
  "properties": {
    "success": {
      "title": "Success",
      "type": "boolean"
    },
    "error": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Error"
    },
    "data": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Data"
    },
    "classifications": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Classifications",
      "type": "array"
    },
    "usage": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Usage"
    }
  },
  "required": [
    "success"
  ],
  "title": "ClassifyOutput",
  "type": "object"
}

Jina AI Integration for AI Agents & Workflows

Overview

Authentication

API Key Authentication

Required Credentials

ModuleX Managed Key

Available Actions

Parameters

Response

Parameters

Response

Parameters

Response

Parameters

Response

Parameters

Response

Parameters

Response

Parameters

Response

Limits & Quotas

Tavily Search

Ahrefs

Airweave

Links

​Overview

​Authentication

​API Key Authentication

​Required Credentials

​ModuleX Managed Key

​Available Actions

​Parameters

​Response

​Parameters

​Response

​Parameters

​Response

​Parameters

​Response

​Parameters

​Response

​Parameters

​Response

​Parameters

​Response

​Limits & Quotas

​Related integrations

Tavily Search

Ahrefs

Airweave

​Links

Overview

Authentication

API Key Authentication

Required Credentials

ModuleX Managed Key

Available Actions

Parameters

Response

Parameters

Response

Parameters

Response

Parameters

Response

Parameters

Response

Parameters

Response

Parameters

Response

Limits & Quotas

Related integrations

Links