Taxonomies

Suggest

Suggest a tag taxonomy based on file content and existing metadata.

Request Body

Field	Type	Description
`data_connector_name`	`str`	Name of the data connector (vector database profile) to use.
`file_names`	`Optional[List[str]]`	List of specific files to analyze for the hierarchy suggestion.
`dataslice_id`	`Optional[str]`	ID of a dataslice to pull files from for the suggestion.
`progress_tracking_id`	`Optional[str]`	Custom tracking ID for monitoring the suggestion progress.
`taxonomy_name`	`Optional[str]`	Name for the suggested schema/taxonomy.
`current_tree`	`Optional[Dict]`	Existing hierarchy tree to build upon.
`condition`	`Optional[Condition]`	Filtering condition to select specific files for analysis.
`node`	`Optional[GraphNode]`	Node location in the existing hierarchy tree to build upon. Default: `{}`
`user_context`	`Optional[str]`	User-provided context to guide the suggestion process.
`context_level`	`Optional[str]`	Level at which to analyze content: `file` or `chunk`. Default: `"file"`
`max_height`	`Optional[int]`	Maximum depth of the generated hierarchy tree. Default: `2`
`use_existing_tags`	`Optional[bool]`	Whether to incorporate existing tags in suggestions. Default: `false`
`use_extracted_tags`	`Optional[bool]`	Whether to use previously extracted tags. Default: `false`
`use_mix_llm_and_source`	`Optional[bool]`	Whether to mix LLM-generated and source-based tags. Default: `false`

Response

200: Schema suggestion generated successfully
- Returns: { "status_code": int, "message": str, "suggestion": Dict, "suggested_tags": Optional[Dict], "node": Optional[GraphNode], "tag_not_found_rates": Optional[Dict] }
500: Internal Server Error

Example

{
  "data_connector_name": "my-connector",
  "file_names": ["document1.pdf", "document2.pdf"],
  "context_level": "file",
  "max_height": 3,
  "use_existing_tags": true,
  "user_context": "Suggest categories for financial documents"
}

POST

suggest_schema

Python

import os
from unstructured import UnstructuredClient

client = UnstructuredClient(
    username=os.environ.get("UNSTRUCTURED_USERNAME"),  # This is the default and can be omitted
    password=os.environ.get("UNSTRUCTURED_PASSWORD"),  # This is the default and can be omitted
)
response = client.taxonomy.suggest(
    data_connector_name="data_connector_name",
)
print(response.job_id)

import UnstructuredClient from 'unstructured-sdk';

const client = new UnstructuredClient({
  authMethod: 'My Auth Method',
  username: process.env['UNSTRUCTURED_USERNAME'], // This is the default and can be omitted
  password: process.env['UNSTRUCTURED_PASSWORD'], // This is the default and can be omitted
});

const response = await client.taxonomy.suggest({ data_connector_name: 'data_connector_name' });

console.log(response.job_id);

{
  "status_code": 200,
  "message": "",
  "job_id": "<string>",
  "suggestion": {},
  "suggested_tags": {},
  "node": {
    "label": "Root",
    "path": []
  },
  "tag_not_found_rates": {}
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

Authorizations

Authorization

string

header

required

Basic authentication header of the form Basic <encoded-value>, where <encoded-value> is the base64-encoded string username:password.

Body

application/json

data_connector_name

string

required

file_names

string[] | null

dataslice_id

string | null

progress_tracking_id

string | null

taxonomy_name

string | null

current_tree

Current Tree · object | null

condition

Condition · object | null

Show child attributes

node

GraphNode · object | null

Legacy graph node model - kept for backwards compatibility

Show child attributes

user_context

string | null

context_level

string | null

default:file

max_height

integer | null

default:1

use_existing_tags

boolean | null

default:false

use_extracted_tags

boolean | null

default:false

use_mix_llm_and_source

boolean | null

default:false

graph_tag_type

enum<string> | null

default:open_ended

Available options:

open_ended,

binary,

mixed,

defined_values,

hierarchy

min_tags_per_level

integer | null

default:1

max_tags_per_level

integer | null

default:10

set_max_values

boolean | null

default:true

values_per_tag

integer | null

auto_save

boolean | null

default:true

validate_tags

boolean | null

default:true

validation_sample_size

integer | null

default:10

not_found_threshold

number | null

default:1

use_hierarchical_clustering

boolean | null

default:true

deep_suggestion_mode

boolean | null

default:false

Response

Successful Response

status_code

integer | null

default:200

message

string | null

default:""

job_id

string | null

suggestion

Suggestion · object | null

suggested_tags

Suggested Tags · object | null

Show child attributes

node

GraphNode · object | null

Legacy graph node model - kept for backwards compatibility

Show child attributes

tag_not_found_rates

Tag Not Found Rates · object | null

Show child attributes

⌘I

Python

import os
from unstructured import UnstructuredClient

client = UnstructuredClient(
    username=os.environ.get("UNSTRUCTURED_USERNAME"),  # This is the default and can be omitted
    password=os.environ.get("UNSTRUCTURED_PASSWORD"),  # This is the default and can be omitted
)
response = client.taxonomy.suggest(
    data_connector_name="data_connector_name",
)
print(response.job_id)

import UnstructuredClient from 'unstructured-sdk';

const client = new UnstructuredClient({
  authMethod: 'My Auth Method',
  username: process.env['UNSTRUCTURED_USERNAME'], // This is the default and can be omitted
  password: process.env['UNSTRUCTURED_PASSWORD'], // This is the default and can be omitted
});

const response = await client.taxonomy.suggest({ data_connector_name: 'data_connector_name' });

console.log(response.job_id);

{
  "status_code": 200,
  "message": "",
  "job_id": "<string>",
  "suggestion": {},
  "suggested_tags": {},
  "node": {
    "label": "Root",
    "path": []
  },
  "tag_not_found_rates": {}
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

Overview

Data Connectors

Tags

Taxonomies

Metadata

Data Slices

Destinations

Projects

Workflows

Task Tracking

Suggest

Request Body

Response

Example

Authorizations

Body

Response