Create parsing extractor

import requests

url = "https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/parsing-extractors/"

payload = {
    "name": "Default parser",
    "brief": "Agentic OCR parser with figure summarization.",
    "llm_model": "gpt-4o",
    "reducto_parsing_options": {
        "ocr_mode": "agentic",
        "figure_summarization": True
    },
    "use_fast_parsing_for_pdfs": False,
    "document_ids": []
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: 'Default parser',
    brief: 'Agentic OCR parser with figure summarization.',
    llm_model: 'gpt-4o',
    reducto_parsing_options: {ocr_mode: 'agentic', figure_summarization: true},
    use_fast_parsing_for_pdfs: false,
    document_ids: []
  })
};

fetch('https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/parsing-extractors/', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

curl --request POST \
  --url https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/parsing-extractors/ \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "Default parser",
  "brief": "Agentic OCR parser with figure summarization.",
  "llm_model": "gpt-4o",
  "reducto_parsing_options": {
    "ocr_mode": "agentic",
    "figure_summarization": true
  },
  "use_fast_parsing_for_pdfs": false,
  "document_ids": []
}
'

{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "name": "Default parser",
  "brief": "Agentic OCR parser with figure summarization.",
  "llm_model": "gpt-4o",
  "reducto_parsing_options": {
    "ocr_mode": "agentic",
    "figure_summarization": true
  },
  "use_fast_parsing_for_pdfs": false,
  "document_ids": [],
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "extracted_parsed_documents_table": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "extracted_blocks_table": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "versions": [
    {
      "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
      "name": "<string>",
      "created_at": "2023-11-07T05:31:56Z",
      "updated_at": "2023-11-07T05:31:56Z",
      "is_default": true,
      "reducto_parsing_options": {
        "ocr_mode": "agentic",
        "figure_summarization": true
      },
      "llm_model": "gpt-4o",
      "use_fast_parsing_for_pdfs": false
    }
  ],
  "default_version": {
    "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "name": "<string>",
    "created_at": "2023-11-07T05:31:56Z",
    "updated_at": "2023-11-07T05:31:56Z",
    "is_default": true,
    "reducto_parsing_options": {
      "ocr_mode": "agentic",
      "figure_summarization": true
    },
    "llm_model": "gpt-4o",
    "use_fast_parsing_for_pdfs": false
  },
  "latest_version": {
    "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "name": "<string>",
    "created_at": "2023-11-07T05:31:56Z",
    "updated_at": "2023-11-07T05:31:56Z",
    "is_default": true,
    "reducto_parsing_options": {
      "ocr_mode": "agentic",
      "figure_summarization": true
    },
    "llm_model": "gpt-4o",
    "use_fast_parsing_for_pdfs": false
  }
}

{
  "error": "User not found"
}

{
  "error": "Authentication credentials were not provided."
}

{
  "error": "You do not have permission to perform this action."
}

POST

projects

{project_id}

parsing-extractors

Create parsing extractor

import requests

url = "https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/parsing-extractors/"

payload = {
    "name": "Default parser",
    "brief": "Agentic OCR parser with figure summarization.",
    "llm_model": "gpt-4o",
    "reducto_parsing_options": {
        "ocr_mode": "agentic",
        "figure_summarization": True
    },
    "use_fast_parsing_for_pdfs": False,
    "document_ids": []
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: 'Default parser',
    brief: 'Agentic OCR parser with figure summarization.',
    llm_model: 'gpt-4o',
    reducto_parsing_options: {ocr_mode: 'agentic', figure_summarization: true},
    use_fast_parsing_for_pdfs: false,
    document_ids: []
  })
};

fetch('https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/parsing-extractors/', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

curl --request POST \
  --url https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/parsing-extractors/ \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "Default parser",
  "brief": "Agentic OCR parser with figure summarization.",
  "llm_model": "gpt-4o",
  "reducto_parsing_options": {
    "ocr_mode": "agentic",
    "figure_summarization": true
  },
  "use_fast_parsing_for_pdfs": false,
  "document_ids": []
}
'

{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "name": "Default parser",
  "brief": "Agentic OCR parser with figure summarization.",
  "llm_model": "gpt-4o",
  "reducto_parsing_options": {
    "ocr_mode": "agentic",
    "figure_summarization": true
  },
  "use_fast_parsing_for_pdfs": false,
  "document_ids": [],
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "extracted_parsed_documents_table": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "extracted_blocks_table": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "versions": [
    {
      "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
      "name": "<string>",
      "created_at": "2023-11-07T05:31:56Z",
      "updated_at": "2023-11-07T05:31:56Z",
      "is_default": true,
      "reducto_parsing_options": {
        "ocr_mode": "agentic",
        "figure_summarization": true
      },
      "llm_model": "gpt-4o",
      "use_fast_parsing_for_pdfs": false
    }
  ],
  "default_version": {
    "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "name": "<string>",
    "created_at": "2023-11-07T05:31:56Z",
    "updated_at": "2023-11-07T05:31:56Z",
    "is_default": true,
    "reducto_parsing_options": {
      "ocr_mode": "agentic",
      "figure_summarization": true
    },
    "llm_model": "gpt-4o",
    "use_fast_parsing_for_pdfs": false
  },
  "latest_version": {
    "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "name": "<string>",
    "created_at": "2023-11-07T05:31:56Z",
    "updated_at": "2023-11-07T05:31:56Z",
    "is_default": true,
    "reducto_parsing_options": {
      "ocr_mode": "agentic",
      "figure_summarization": true
    },
    "llm_model": "gpt-4o",
    "use_fast_parsing_for_pdfs": false
  }
}

{
  "error": "User not found"
}

{
  "error": "Authentication credentials were not provided."
}

{
  "error": "You do not have permission to perform this action."
}

Authorizations

Authorization

string

header

required

Use Authorization: Bearer

Path Parameters

project_id

string<uuid>

required

UUID of the project

Body

application/json

Converts source documents to text blocks via the parsing pipeline.

name

string

Example:

"Default parser"

brief

string

Example:

"Agentic OCR parser with figure summarization."

llm_model

string | null

Example:

"gpt-4o"

reducto_parsing_options

object

Example:

{
  "ocr_mode": "agentic",
  "figure_summarization": true
}

use_fast_parsing_for_pdfs

boolean

Example:

false

document_ids

string<uuid>[]

Example:

[]

import_mode

boolean

default:false

write-only

Response

Created

Converts source documents to text blocks via the parsing pipeline.

string<uuid>

read-only

name

string

Example:

"Default parser"

brief

string

Example:

"Agentic OCR parser with figure summarization."

llm_model

string | null

Example:

"gpt-4o"

reducto_parsing_options

object

Example:

{
  "ocr_mode": "agentic",
  "figure_summarization": true
}

use_fast_parsing_for_pdfs

boolean

Example:

false

document_ids

string<uuid>[]

Example:

[]

created_at

string<date-time>

read-only

updated_at

string<date-time>

read-only

extracted_parsed_documents_table

string<uuid> | null

read-only

extracted_blocks_table

string<uuid> | null

read-only

versions

object[]

read-only

Show child attributes

default_version

object | null

Immutable snapshot of a ParsingExtractor's version-bearing configuration.

Show child attributes

latest_version

object | null

Immutable snapshot of a ParsingExtractor's version-bearing configuration.

Show child attributes

Concepts

Endpoints

Create parsing extractor

Authorizations

Path Parameters

Body

Response