Create Chunk Handler
Create a new chunk with content.
The chunk is created as a child of the specified parent (must be DOCUMENT_VERSION or SECTION). Content is deduplicated by SHA256 hash.
curl --request POST \
--url http://localhost:8000/v1/chunks \
--header 'Content-Type: application/json' \
--data '
{
"parent_path_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"content": "<string>",
"chunk_metadata": {
"polygons": [
{
"page": 123,
"polygon": {
"x": 123,
"y": 123,
"width": 123,
"height": 123
}
}
],
"s3_urls": [
"<string>"
],
"summary": "<string>",
"extracted_text_s3_uri": "<string>",
"sheet_name": "<string>",
"block_type": "<string>",
"source_uri": "<string>",
"enriched_html": "<string>",
"cell_range": "<string>",
"dependency_summary": {},
"formulas": [
{}
],
"key_cells": [
{}
],
"named_ranges": [
{}
]
},
"prev_sibling_path_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}
'import requests
url = "http://localhost:8000/v1/chunks"
payload = {
"parent_path_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"content": "<string>",
"chunk_metadata": {
"polygons": [
{
"page": 123,
"polygon": {
"x": 123,
"y": 123,
"width": 123,
"height": 123
}
}
],
"s3_urls": ["<string>"],
"summary": "<string>",
"extracted_text_s3_uri": "<string>",
"sheet_name": "<string>",
"block_type": "<string>",
"source_uri": "<string>",
"enriched_html": "<string>",
"cell_range": "<string>",
"dependency_summary": {},
"formulas": [{}],
"key_cells": [{}],
"named_ranges": [{}]
},
"prev_sibling_path_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}
headers = {"Content-Type": "application/json"}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'Content-Type': 'application/json'},
body: JSON.stringify({
parent_path_id: '3c90c3cc-0d44-4b50-8888-8dd25736052a',
content: '<string>',
chunk_metadata: {
polygons: [{page: 123, polygon: {x: 123, y: 123, width: 123, height: 123}}],
s3_urls: ['<string>'],
summary: '<string>',
extracted_text_s3_uri: '<string>',
sheet_name: '<string>',
block_type: '<string>',
source_uri: '<string>',
enriched_html: '<string>',
cell_range: '<string>',
dependency_summary: {},
formulas: [{}],
key_cells: [{}],
named_ranges: [{}]
},
prev_sibling_path_id: '3c90c3cc-0d44-4b50-8888-8dd25736052a'
})
};
fetch('http://localhost:8000/v1/chunks', 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/chunks",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'parent_path_id' => '3c90c3cc-0d44-4b50-8888-8dd25736052a',
'content' => '<string>',
'chunk_metadata' => [
'polygons' => [
[
'page' => 123,
'polygon' => [
'x' => 123,
'y' => 123,
'width' => 123,
'height' => 123
]
]
],
's3_urls' => [
'<string>'
],
'summary' => '<string>',
'extracted_text_s3_uri' => '<string>',
'sheet_name' => '<string>',
'block_type' => '<string>',
'source_uri' => '<string>',
'enriched_html' => '<string>',
'cell_range' => '<string>',
'dependency_summary' => [
],
'formulas' => [
[
]
],
'key_cells' => [
[
]
],
'named_ranges' => [
[
]
]
],
'prev_sibling_path_id' => '3c90c3cc-0d44-4b50-8888-8dd25736052a'
]),
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/chunks"
payload := strings.NewReader("{\n \"parent_path_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n \"content\": \"<string>\",\n \"chunk_metadata\": {\n \"polygons\": [\n {\n \"page\": 123,\n \"polygon\": {\n \"x\": 123,\n \"y\": 123,\n \"width\": 123,\n \"height\": 123\n }\n }\n ],\n \"s3_urls\": [\n \"<string>\"\n ],\n \"summary\": \"<string>\",\n \"extracted_text_s3_uri\": \"<string>\",\n \"sheet_name\": \"<string>\",\n \"block_type\": \"<string>\",\n \"source_uri\": \"<string>\",\n \"enriched_html\": \"<string>\",\n \"cell_range\": \"<string>\",\n \"dependency_summary\": {},\n \"formulas\": [\n {}\n ],\n \"key_cells\": [\n {}\n ],\n \"named_ranges\": [\n {}\n ]\n },\n \"prev_sibling_path_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\n}")
req, _ := http.NewRequest("POST", 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.post("http://localhost:8000/v1/chunks")
.header("Content-Type", "application/json")
.body("{\n \"parent_path_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n \"content\": \"<string>\",\n \"chunk_metadata\": {\n \"polygons\": [\n {\n \"page\": 123,\n \"polygon\": {\n \"x\": 123,\n \"y\": 123,\n \"width\": 123,\n \"height\": 123\n }\n }\n ],\n \"s3_urls\": [\n \"<string>\"\n ],\n \"summary\": \"<string>\",\n \"extracted_text_s3_uri\": \"<string>\",\n \"sheet_name\": \"<string>\",\n \"block_type\": \"<string>\",\n \"source_uri\": \"<string>\",\n \"enriched_html\": \"<string>\",\n \"cell_range\": \"<string>\",\n \"dependency_summary\": {},\n \"formulas\": [\n {}\n ],\n \"key_cells\": [\n {}\n ],\n \"named_ranges\": [\n {}\n ]\n },\n \"prev_sibling_path_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("http://localhost:8000/v1/chunks")
http = Net::HTTP.new(url.host, url.port)
request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n \"parent_path_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n \"content\": \"<string>\",\n \"chunk_metadata\": {\n \"polygons\": [\n {\n \"page\": 123,\n \"polygon\": {\n \"x\": 123,\n \"y\": 123,\n \"width\": 123,\n \"height\": 123\n }\n }\n ],\n \"s3_urls\": [\n \"<string>\"\n ],\n \"summary\": \"<string>\",\n \"extracted_text_s3_uri\": \"<string>\",\n \"sheet_name\": \"<string>\",\n \"block_type\": \"<string>\",\n \"source_uri\": \"<string>\",\n \"enriched_html\": \"<string>\",\n \"cell_range\": \"<string>\",\n \"dependency_summary\": {},\n \"formulas\": [\n {}\n ],\n \"key_cells\": [\n {}\n ],\n \"named_ranges\": [\n {}\n ]\n },\n \"prev_sibling_path_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\n}"
response = http.request(request)
puts response.read_body{
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"path_part_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"content_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"content": "<string>",
"chunk_metadata": {
"polygons": [
{
"page": 123,
"polygon": {
"x": 123,
"y": 123,
"width": 123,
"height": 123
}
}
],
"s3_urls": [
"<string>"
],
"summary": "<string>",
"extracted_text_s3_uri": "<string>",
"sheet_name": "<string>",
"block_type": "<string>",
"source_uri": "<string>",
"enriched_html": "<string>",
"cell_range": "<string>",
"dependency_summary": {},
"formulas": [
{}
],
"key_cells": [
{}
],
"named_ranges": [
{}
]
},
"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",
"num_tokens": 123,
"prev_sibling_path_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"next_sibling_path_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"asset_s3_urls": [
"<string>"
],
"document": {
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"name": "<string>"
},
"document_version": {
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"version": 123,
"name": "<string>"
}
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}Headers
Cookies
Body
Request to create a new chunk.
Parent PathPart ID (must be DOCUMENT_VERSION or SECTION)
Chunk text content
1Type of chunk content (TEXT, TABLE, IMAGE, HTML, UNKNOWN)
TEXT, TABLE, IMAGE, HTML, UNKNOWN Chunk metadata as JSON (title, description, etc.)
Show child attributes
Show child attributes
PathPart ID to insert after (null = append to tail)
Response
Successful Response
Chunk response model.
Chunk ID
PathPart ID
ChunkContent ID
Chunk text content
Type of chunk content
TEXT, TABLE, IMAGE, HTML, UNKNOWN Chunk metadata
Show child attributes
Show child attributes
Parent PathPart ID
Full materialized path from root
Whether this chunk is system-managed
Tenant ID
Creation timestamp
Last update timestamp
Number of tokens in chunk content
Previous sibling PathPart ID
Next sibling PathPart ID
Presigned URLs to download the chunk's visual assets (6-hour validity)
Ancestor document info (populated when with_document=true)
Show child attributes
Show child attributes
Ancestor document version info (populated when with_document=true)
Show child attributes
Show child attributes
curl --request POST \
--url http://localhost:8000/v1/chunks \
--header 'Content-Type: application/json' \
--data '
{
"parent_path_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"content": "<string>",
"chunk_metadata": {
"polygons": [
{
"page": 123,
"polygon": {
"x": 123,
"y": 123,
"width": 123,
"height": 123
}
}
],
"s3_urls": [
"<string>"
],
"summary": "<string>",
"extracted_text_s3_uri": "<string>",
"sheet_name": "<string>",
"block_type": "<string>",
"source_uri": "<string>",
"enriched_html": "<string>",
"cell_range": "<string>",
"dependency_summary": {},
"formulas": [
{}
],
"key_cells": [
{}
],
"named_ranges": [
{}
]
},
"prev_sibling_path_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}
'import requests
url = "http://localhost:8000/v1/chunks"
payload = {
"parent_path_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"content": "<string>",
"chunk_metadata": {
"polygons": [
{
"page": 123,
"polygon": {
"x": 123,
"y": 123,
"width": 123,
"height": 123
}
}
],
"s3_urls": ["<string>"],
"summary": "<string>",
"extracted_text_s3_uri": "<string>",
"sheet_name": "<string>",
"block_type": "<string>",
"source_uri": "<string>",
"enriched_html": "<string>",
"cell_range": "<string>",
"dependency_summary": {},
"formulas": [{}],
"key_cells": [{}],
"named_ranges": [{}]
},
"prev_sibling_path_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}
headers = {"Content-Type": "application/json"}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'Content-Type': 'application/json'},
body: JSON.stringify({
parent_path_id: '3c90c3cc-0d44-4b50-8888-8dd25736052a',
content: '<string>',
chunk_metadata: {
polygons: [{page: 123, polygon: {x: 123, y: 123, width: 123, height: 123}}],
s3_urls: ['<string>'],
summary: '<string>',
extracted_text_s3_uri: '<string>',
sheet_name: '<string>',
block_type: '<string>',
source_uri: '<string>',
enriched_html: '<string>',
cell_range: '<string>',
dependency_summary: {},
formulas: [{}],
key_cells: [{}],
named_ranges: [{}]
},
prev_sibling_path_id: '3c90c3cc-0d44-4b50-8888-8dd25736052a'
})
};
fetch('http://localhost:8000/v1/chunks', 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/chunks",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'parent_path_id' => '3c90c3cc-0d44-4b50-8888-8dd25736052a',
'content' => '<string>',
'chunk_metadata' => [
'polygons' => [
[
'page' => 123,
'polygon' => [
'x' => 123,
'y' => 123,
'width' => 123,
'height' => 123
]
]
],
's3_urls' => [
'<string>'
],
'summary' => '<string>',
'extracted_text_s3_uri' => '<string>',
'sheet_name' => '<string>',
'block_type' => '<string>',
'source_uri' => '<string>',
'enriched_html' => '<string>',
'cell_range' => '<string>',
'dependency_summary' => [
],
'formulas' => [
[
]
],
'key_cells' => [
[
]
],
'named_ranges' => [
[
]
]
],
'prev_sibling_path_id' => '3c90c3cc-0d44-4b50-8888-8dd25736052a'
]),
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/chunks"
payload := strings.NewReader("{\n \"parent_path_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n \"content\": \"<string>\",\n \"chunk_metadata\": {\n \"polygons\": [\n {\n \"page\": 123,\n \"polygon\": {\n \"x\": 123,\n \"y\": 123,\n \"width\": 123,\n \"height\": 123\n }\n }\n ],\n \"s3_urls\": [\n \"<string>\"\n ],\n \"summary\": \"<string>\",\n \"extracted_text_s3_uri\": \"<string>\",\n \"sheet_name\": \"<string>\",\n \"block_type\": \"<string>\",\n \"source_uri\": \"<string>\",\n \"enriched_html\": \"<string>\",\n \"cell_range\": \"<string>\",\n \"dependency_summary\": {},\n \"formulas\": [\n {}\n ],\n \"key_cells\": [\n {}\n ],\n \"named_ranges\": [\n {}\n ]\n },\n \"prev_sibling_path_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\n}")
req, _ := http.NewRequest("POST", 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.post("http://localhost:8000/v1/chunks")
.header("Content-Type", "application/json")
.body("{\n \"parent_path_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n \"content\": \"<string>\",\n \"chunk_metadata\": {\n \"polygons\": [\n {\n \"page\": 123,\n \"polygon\": {\n \"x\": 123,\n \"y\": 123,\n \"width\": 123,\n \"height\": 123\n }\n }\n ],\n \"s3_urls\": [\n \"<string>\"\n ],\n \"summary\": \"<string>\",\n \"extracted_text_s3_uri\": \"<string>\",\n \"sheet_name\": \"<string>\",\n \"block_type\": \"<string>\",\n \"source_uri\": \"<string>\",\n \"enriched_html\": \"<string>\",\n \"cell_range\": \"<string>\",\n \"dependency_summary\": {},\n \"formulas\": [\n {}\n ],\n \"key_cells\": [\n {}\n ],\n \"named_ranges\": [\n {}\n ]\n },\n \"prev_sibling_path_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("http://localhost:8000/v1/chunks")
http = Net::HTTP.new(url.host, url.port)
request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n \"parent_path_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n \"content\": \"<string>\",\n \"chunk_metadata\": {\n \"polygons\": [\n {\n \"page\": 123,\n \"polygon\": {\n \"x\": 123,\n \"y\": 123,\n \"width\": 123,\n \"height\": 123\n }\n }\n ],\n \"s3_urls\": [\n \"<string>\"\n ],\n \"summary\": \"<string>\",\n \"extracted_text_s3_uri\": \"<string>\",\n \"sheet_name\": \"<string>\",\n \"block_type\": \"<string>\",\n \"source_uri\": \"<string>\",\n \"enriched_html\": \"<string>\",\n \"cell_range\": \"<string>\",\n \"dependency_summary\": {},\n \"formulas\": [\n {}\n ],\n \"key_cells\": [\n {}\n ],\n \"named_ranges\": [\n {}\n ]\n },\n \"prev_sibling_path_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\n}"
response = http.request(request)
puts response.read_body{
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"path_part_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"content_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"content": "<string>",
"chunk_metadata": {
"polygons": [
{
"page": 123,
"polygon": {
"x": 123,
"y": 123,
"width": 123,
"height": 123
}
}
],
"s3_urls": [
"<string>"
],
"summary": "<string>",
"extracted_text_s3_uri": "<string>",
"sheet_name": "<string>",
"block_type": "<string>",
"source_uri": "<string>",
"enriched_html": "<string>",
"cell_range": "<string>",
"dependency_summary": {},
"formulas": [
{}
],
"key_cells": [
{}
],
"named_ranges": [
{}
]
},
"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",
"num_tokens": 123,
"prev_sibling_path_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"next_sibling_path_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"asset_s3_urls": [
"<string>"
],
"document": {
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"name": "<string>"
},
"document_version": {
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"version": 123,
"name": "<string>"
}
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}