Update Document Version Metadata Handler

curl --request PATCH \
  --url http://localhost:8000/v1/document_versions/{version_id}/metadata \
  --header 'Content-Type: application/json' \
  --data '
{
  "source_s3": "<string>",
  "cleaned_source_s3": "<string>",
  "standard_pipeline_json_s3": "<string>",
  "fast_plaintext_s3": "<string>",
  "high_accuracy_content_list_s3": "<string>",
  "high_accuracy_middle_s3": "<string>",
  "hash": "<string>",
  "pipeline_state": {
    "last_run_timestamp": "2023-11-07T05:31:56Z",
    "last_state_update_timestamp": "2023-11-07T05:31:56Z",
    "last_activity": "<string>",
    "error": "<string>",
    "temporal_workflow_id": "<string>",
    "chunks_processed": 123,
    "page_dpi": 123
  },
  "total_pages": 123,
  "total_sections": 123,
  "total_chunks": 123,
  "total_formulas": 123,
  "xlsx_parse_result_s3": "<string>",
  "xlsx_named_ranges": [
    {}
  ],
  "xlsx_kpi_catalog": [
    {}
  ],
  "information_statistics": {
    "num_chunks_by_type": {},
    "total_tokens": 0,
    "num_direct_children": 0,
    "children_depth": 0
  }
}
'

import requests

url = "http://localhost:8000/v1/document_versions/{version_id}/metadata"

payload = {
    "source_s3": "<string>",
    "cleaned_source_s3": "<string>",
    "standard_pipeline_json_s3": "<string>",
    "fast_plaintext_s3": "<string>",
    "high_accuracy_content_list_s3": "<string>",
    "high_accuracy_middle_s3": "<string>",
    "hash": "<string>",
    "pipeline_state": {
        "last_run_timestamp": "2023-11-07T05:31:56Z",
        "last_state_update_timestamp": "2023-11-07T05:31:56Z",
        "last_activity": "<string>",
        "error": "<string>",
        "temporal_workflow_id": "<string>",
        "chunks_processed": 123,
        "page_dpi": 123
    },
    "total_pages": 123,
    "total_sections": 123,
    "total_chunks": 123,
    "total_formulas": 123,
    "xlsx_parse_result_s3": "<string>",
    "xlsx_named_ranges": [{}],
    "xlsx_kpi_catalog": [{}],
    "information_statistics": {
        "num_chunks_by_type": {},
        "total_tokens": 0,
        "num_direct_children": 0,
        "children_depth": 0
    }
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

const options = {
  method: 'PATCH',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    source_s3: '<string>',
    cleaned_source_s3: '<string>',
    standard_pipeline_json_s3: '<string>',
    fast_plaintext_s3: '<string>',
    high_accuracy_content_list_s3: '<string>',
    high_accuracy_middle_s3: '<string>',
    hash: '<string>',
    pipeline_state: {
      last_run_timestamp: '2023-11-07T05:31:56Z',
      last_state_update_timestamp: '2023-11-07T05:31:56Z',
      last_activity: '<string>',
      error: '<string>',
      temporal_workflow_id: '<string>',
      chunks_processed: 123,
      page_dpi: 123
    },
    total_pages: 123,
    total_sections: 123,
    total_chunks: 123,
    total_formulas: 123,
    xlsx_parse_result_s3: '<string>',
    xlsx_named_ranges: [{}],
    xlsx_kpi_catalog: [{}],
    information_statistics: {
      num_chunks_by_type: {},
      total_tokens: 0,
      num_direct_children: 0,
      children_depth: 0
    }
  })
};

fetch('http://localhost:8000/v1/document_versions/{version_id}/metadata', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_PORT => "8000",
  CURLOPT_URL => "http://localhost:8000/v1/document_versions/{version_id}/metadata",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "PATCH",
  CURLOPT_POSTFIELDS => json_encode([
    'source_s3' => '<string>',
    'cleaned_source_s3' => '<string>',
    'standard_pipeline_json_s3' => '<string>',
    'fast_plaintext_s3' => '<string>',
    'high_accuracy_content_list_s3' => '<string>',
    'high_accuracy_middle_s3' => '<string>',
    'hash' => '<string>',
    'pipeline_state' => [
        'last_run_timestamp' => '2023-11-07T05:31:56Z',
        'last_state_update_timestamp' => '2023-11-07T05:31:56Z',
        'last_activity' => '<string>',
        'error' => '<string>',
        'temporal_workflow_id' => '<string>',
        'chunks_processed' => 123,
        'page_dpi' => 123
    ],
    'total_pages' => 123,
    'total_sections' => 123,
    'total_chunks' => 123,
    'total_formulas' => 123,
    'xlsx_parse_result_s3' => '<string>',
    'xlsx_named_ranges' => [
        [
                
        ]
    ],
    'xlsx_kpi_catalog' => [
        [
                
        ]
    ],
    'information_statistics' => [
        'num_chunks_by_type' => [
                
        ],
        'total_tokens' => 0,
        'num_direct_children' => 0,
        'children_depth' => 0
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "http://localhost:8000/v1/document_versions/{version_id}/metadata"

	payload := strings.NewReader("{\n  \"source_s3\": \"<string>\",\n  \"cleaned_source_s3\": \"<string>\",\n  \"standard_pipeline_json_s3\": \"<string>\",\n  \"fast_plaintext_s3\": \"<string>\",\n  \"high_accuracy_content_list_s3\": \"<string>\",\n  \"high_accuracy_middle_s3\": \"<string>\",\n  \"hash\": \"<string>\",\n  \"pipeline_state\": {\n    \"last_run_timestamp\": \"2023-11-07T05:31:56Z\",\n    \"last_state_update_timestamp\": \"2023-11-07T05:31:56Z\",\n    \"last_activity\": \"<string>\",\n    \"error\": \"<string>\",\n    \"temporal_workflow_id\": \"<string>\",\n    \"chunks_processed\": 123,\n    \"page_dpi\": 123\n  },\n  \"total_pages\": 123,\n  \"total_sections\": 123,\n  \"total_chunks\": 123,\n  \"total_formulas\": 123,\n  \"xlsx_parse_result_s3\": \"<string>\",\n  \"xlsx_named_ranges\": [\n    {}\n  ],\n  \"xlsx_kpi_catalog\": [\n    {}\n  ],\n  \"information_statistics\": {\n    \"num_chunks_by_type\": {},\n    \"total_tokens\": 0,\n    \"num_direct_children\": 0,\n    \"children_depth\": 0\n  }\n}")

	req, _ := http.NewRequest("PATCH", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.patch("http://localhost:8000/v1/document_versions/{version_id}/metadata")
  .header("Content-Type", "application/json")
  .body("{\n  \"source_s3\": \"<string>\",\n  \"cleaned_source_s3\": \"<string>\",\n  \"standard_pipeline_json_s3\": \"<string>\",\n  \"fast_plaintext_s3\": \"<string>\",\n  \"high_accuracy_content_list_s3\": \"<string>\",\n  \"high_accuracy_middle_s3\": \"<string>\",\n  \"hash\": \"<string>\",\n  \"pipeline_state\": {\n    \"last_run_timestamp\": \"2023-11-07T05:31:56Z\",\n    \"last_state_update_timestamp\": \"2023-11-07T05:31:56Z\",\n    \"last_activity\": \"<string>\",\n    \"error\": \"<string>\",\n    \"temporal_workflow_id\": \"<string>\",\n    \"chunks_processed\": 123,\n    \"page_dpi\": 123\n  },\n  \"total_pages\": 123,\n  \"total_sections\": 123,\n  \"total_chunks\": 123,\n  \"total_formulas\": 123,\n  \"xlsx_parse_result_s3\": \"<string>\",\n  \"xlsx_named_ranges\": [\n    {}\n  ],\n  \"xlsx_kpi_catalog\": [\n    {}\n  ],\n  \"information_statistics\": {\n    \"num_chunks_by_type\": {},\n    \"total_tokens\": 0,\n    \"num_direct_children\": 0,\n    \"children_depth\": 0\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("http://localhost:8000/v1/document_versions/{version_id}/metadata")

http = Net::HTTP.new(url.host, url.port)

request = Net::HTTP::Patch.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"source_s3\": \"<string>\",\n  \"cleaned_source_s3\": \"<string>\",\n  \"standard_pipeline_json_s3\": \"<string>\",\n  \"fast_plaintext_s3\": \"<string>\",\n  \"high_accuracy_content_list_s3\": \"<string>\",\n  \"high_accuracy_middle_s3\": \"<string>\",\n  \"hash\": \"<string>\",\n  \"pipeline_state\": {\n    \"last_run_timestamp\": \"2023-11-07T05:31:56Z\",\n    \"last_state_update_timestamp\": \"2023-11-07T05:31:56Z\",\n    \"last_activity\": \"<string>\",\n    \"error\": \"<string>\",\n    \"temporal_workflow_id\": \"<string>\",\n    \"chunks_processed\": 123,\n    \"page_dpi\": 123\n  },\n  \"total_pages\": 123,\n  \"total_sections\": 123,\n  \"total_chunks\": 123,\n  \"total_formulas\": 123,\n  \"xlsx_parse_result_s3\": \"<string>\",\n  \"xlsx_named_ranges\": [\n    {}\n  ],\n  \"xlsx_kpi_catalog\": [\n    {}\n  ],\n  \"information_statistics\": {\n    \"num_chunks_by_type\": {},\n    \"total_tokens\": 0,\n    \"num_direct_children\": 0,\n    \"children_depth\": 0\n  }\n}"

response = http.request(request)
puts response.read_body

{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "path_part_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "version": 123,
  "name": "<string>",
  "parent_path_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "materialized_path": "<string>",
  "system_managed": true,
  "tenant_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "asset_s3_url": "<string>",
  "fast_plaintext_url": "<string>",
  "system_metadata": {
    "source_s3": "<string>",
    "cleaned_source_s3": "<string>",
    "fast_plaintext_s3": "<string>",
    "hash": "<string>",
    "pipeline_state": {
      "last_run_timestamp": "2023-11-07T05:31:56Z",
      "last_state_update_timestamp": "2023-11-07T05:31:56Z",
      "last_activity": "<string>",
      "error": "<string>",
      "temporal_workflow_id": "<string>",
      "chunks_processed": 123,
      "page_dpi": 123
    },
    "total_pages": 123,
    "total_sections": 123,
    "total_chunks": 123,
    "total_formulas": 123,
    "xlsx_parse_result_s3": "<string>",
    "xlsx_named_ranges": [
      {}
    ],
    "xlsx_kpi_catalog": [
      {}
    ],
    "information_statistics": {
      "num_chunks_by_type": {},
      "total_tokens": 0,
      "num_direct_children": 0,
      "children_depth": 0
    }
  }
}

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