Examples

This page provides some examples of accessing Unstructured Partition Endpoint via different methods.

To use these examples, you’ll first need to set an environment variable named UNSTRUCTURED_API_KEY, representing your Unstructured API key. Get your API key.

Also, you’ll need to set an environment variable named UNSTRUCTURED_API_URL to the value of the Unstructured API URL for your account. This API URL was provided to you when your Unstructured account was created. If you do not have this API URL, contact Unstructured Sales at [e-mail].

For the Unstructured Python SDK, the API URL is set to https://api.unstructuredapp.io/general/v0/general by default. However, this API URL might not necessarily work for your account.

Changing partition strategy for a PDF

Here’s how you can modify partition strategy for a PDF file, and select an alternative model to use with Unstructured API.

POST

POST

curl -X 'POST' $UNSTRUCTURED_API_URL \
-H 'accept: application/json' \
-H 'Content-Type: multipart/form-data' \
-H 'unstructured-api-key: $UNSTRUCTURED_API_KEY' \
-F 'files=@sample-docs/layout-parser-paper.pdf' \
-F 'strategy=vlm' \
-F 'vlm_model_provider=openai' \
-F 'vlm_model=gpt-4o'

Python SDK

Python

import asyncio
import os
import json
import unstructured_client
from unstructured_client.models import shared

client = unstructured_client.UnstructuredClient(
    api_key_auth=os.getenv("UNSTRUCTURED_API_KEY")
)

async def call_api(filename, input_dir, output_dir):
    req = {
        "partition_parameters": {
            "files": {
                "content": open(filename, "rb"),
                "file_name": os.path.basename(filename),
            },
            "strategy": shared.Strategy.VLM,
            "vlm_model": "gpt-4o",
            "vlm_model_provider": "openai",
            "split_pdf_page": True,
            "split_pdf_allow_failed": True,
            "split_pdf_concurrency_level": 15
        }
    }

    try:
        res = await client.general.partition_async(
            request=req
        )
        element_dicts = [element for element in res.elements]
        json_elements = json.dumps(element_dicts, indent=2)

        # Create the output directory structure.
        relative_path = os.path.relpath(os.path.dirname(filename), input_dir)
        output_subdir = os.path.join(output_dir, relative_path)
        os.makedirs(output_subdir, exist_ok=True)

        # Write the output file.
        output_filename = os.path.join(output_subdir, os.path.basename(filename) + ".json")
        with open(output_filename, "w") as file:
            file.write(json_elements)

    except Exception as e:
        print(f"Error processing {filename}: {e}")

async def process_files(input_directory, output_directory):
    tasks = []

    for root, _, files in os.walk(input_directory):
        for file in files:
            if not file.endswith('.json'):
                full_path = os.path.join(root, file)
                tasks.append(call_api(full_path, input_directory, output_directory))

    await asyncio.gather(*tasks)

if __name__ == "__main__":
    asyncio.run(process_files(
        input_directory=os.getenv("LOCAL_FILE_INPUT_DIR"), 
        output_directory=os.getenv("LOCAL_FILE_OUTPUT_DIR")
    ))

JavaScript/TypeScript SDK

TypeScript

import { UnstructuredClient } from "unstructured-client";
import * as fs from "fs";
import * as path from "path";
import { Strategy } from "unstructured-client/sdk/models/shared/index.js";
import { PartitionResponse } from "unstructured-client/sdk/models/operations";

// Send all files in the source path to Unstructured for processing.
// Send the processed data to the destination path.
function processFiles(
    client: UnstructuredClient,
    sourcePath: string,
    destinationPath: string
): void {

    // If an output directory does not exist for the corresponding input
    // directory, then create it.
    if (!fs.existsSync(destinationPath)) {
        fs.mkdirSync(destinationPath, { recursive: true });
    }

    // Get all folders and files at the current level of the input directory.
    const items = fs.readdirSync(sourcePath);

    // For each folder and file in the input directory...
    for (const item of items) {
        const inputPath = path.join(sourcePath, item);
        const outputPath = path.join(destinationPath, item)

        // If it's a folder, call this function recursively.
        if (fs.statSync(inputPath).isDirectory()) {
            processFiles(client, inputPath, outputPath);
        } else {
            // If it's a file, send it to Unstructured for processing.
            const data = fs.readFileSync(inputPath);

            client.general.partition({
                partitionParameters: {
                    files: {
                        content: data,
                        fileName: inputPath
                    },
                    strategy: Strategy.HiRes,
                    hiResModelName: "layout_v1.1.0", 
                    splitPdfPage: true,
                    splitPdfConcurrencyLevel: 15,
                    splitPdfAllowFailed: true
                }
            }).then((res: PartitionResponse) => {
                // If successfully processed, write the processed data to
                // the destination directory.
                if (res.statusCode == 200) {
                    const jsonElements = JSON.stringify(res, null, 2)
                    fs.writeFileSync(outputPath + ".json", jsonElements)
                }
            }).catch((e) => {
                if (e.statusCode) {
                    console.log(e.statusCode);
                    console.log(e.body);
                } else {
                    console.log(e);
                }
            });
        }
    }
}

const client = new UnstructuredClient({
    security: { apiKeyAuth: process.env.UNSTRUCTURED_API_KEY },
    serverURL: process.env.UNSTRUCTURED_API_URL
});

processFiles(
    client,
    process.env.LOCAL_FILE_INPUT_DIR,
    process.env.LOCAL_FILE_OUTPUT_DIR
);

If you have a local deployment of the Unstructured API, you can use other supported models, such as yolox.

Specifying the language of a document for better OCR results

For better OCR results, you can specify what languages your document is in using the languages parameter. View the list of available languages.

POST

POST

curl -X 'POST' $UNSTRUCTURED_API_URL \
-H 'accept: application/json' \
-H 'Content-Type: multipart/form-data' \
-H 'unstructured-api-key: $UNSTRUCTURED_API_KEY' \
-F 'files=@sample-docs/korean.png' \
-F 'strategy=vlm' \
-F 'vlm_model_provider=openai' \
-F 'vlm_model=gpt-4o' \-F 'languages=kor'

Python SDK

Python

import asyncio
import os
import json
import unstructured_client
from unstructured_client.models import shared

client = unstructured_client.UnstructuredClient(
    api_key_auth=os.getenv("UNSTRUCTURED_API_KEY")
)

async def call_api(filename, input_dir, output_dir):
    req = {
        "partition_parameters": {
            "files": {
                "content": open(filename, "rb"),
                "file_name": os.path.basename(filename),
            },
            "strategy": shared.Strategy.OCR_ONLY,
            "languages": ["kor"],
            "split_pdf_page": True,
            "split_pdf_allow_failed": True,
            "split_pdf_concurrency_level": 15
        }
    }

    try:
        res = await client.general.partition_async(
            request=req
        )
        element_dicts = [element for element in res.elements]
        json_elements = json.dumps(element_dicts, indent=2)

        # Create the output directory structure.
        relative_path = os.path.relpath(os.path.dirname(filename), input_dir)
        output_subdir = os.path.join(output_dir, relative_path)
        os.makedirs(output_subdir, exist_ok=True)

        # Write the output file.
        output_filename = os.path.join(output_subdir, os.path.basename(filename) + ".json")
        with open(output_filename, "w") as file:
            file.write(json_elements)

    except Exception as e:
        print(f"Error processing {filename}: {e}")

async def process_files(input_directory, output_directory):
    tasks = []

    for root, _, files in os.walk(input_directory):
        for file in files:
            if not file.endswith('.json'):
                full_path = os.path.join(root, file)
                tasks.append(call_api(full_path, input_directory, output_directory))

    await asyncio.gather(*tasks)

if __name__ == "__main__":
    asyncio.run(process_files(
        input_directory=os.getenv("LOCAL_FILE_INPUT_DIR"), 
        output_directory=os.getenv("LOCAL_FILE_OUTPUT_DIR")
    ))

JavaScript/TypeScript SDK

TypeScript

import { UnstructuredClient } from "unstructured-client";
import * as fs from "fs";
import * as path from "path";
import { Strategy } from "unstructured-client/sdk/models/shared/index.js";
import { PartitionResponse } from "unstructured-client/sdk/models/operations";

// Send all files in the source path to Unstructured for processing.
// Send the processed data to the destination path.
function processFiles(
    client: UnstructuredClient,
    sourcePath: string,
    destinationPath: string
): void {

    // If an output directory does not exist for the corresponding input
    // directory, then create it.
    if (!fs.existsSync(destinationPath)) {
        fs.mkdirSync(destinationPath, { recursive: true });
    }

    // Get all folders and files at the current level of the input directory.
    const items = fs.readdirSync(sourcePath);

    // For each folder and file in the input directory...
    for (const item of items) {
        const inputPath = path.join(sourcePath, item);
        const outputPath = path.join(destinationPath, item)

        // If it's a folder, call this function recursively.
        if (fs.statSync(inputPath).isDirectory()) {
            processFiles(client, inputPath, outputPath);
        } else {
            // If it's a file, send it to Unstructured for processing.
            const data = fs.readFileSync(inputPath);

            client.general.partition({
                partitionParameters: {
                    files: {
                        content: data,
                        fileName: inputPath
                    },
                    strategy: Strategy.OcrOnly,
                    languages: ["kor"],
                    splitPdfPage: true,
                    splitPdfConcurrencyLevel: 15,
                    splitPdfAllowFailed: true
                }
            }).then((res: PartitionResponse) => {
                // If successfully processed, write the processed data to
                // the destination directory.
                if (res.statusCode == 200) {
                    const jsonElements = JSON.stringify(res, null, 2)
                    fs.writeFileSync(outputPath + ".json", jsonElements)
                }
            }).catch((e) => {
                if (e.statusCode) {
                    console.log(e.statusCode);
                    console.log(e.body);
                } else {
                    console.log(e);
                }
            });
        }
    }
}

const client = new UnstructuredClient({
    security: { apiKeyAuth: process.env.UNSTRUCTURED_API_KEY },
    serverURL: process.env.UNSTRUCTURED_API_URL
});

processFiles(
    client,
    process.env.LOCAL_FILE_INPUT_DIR,
    process.env.LOCAL_FILE_OUTPUT_DIR
);

Saving bounding box coordinates

When elements are extracted from PDFs or images, it may be useful to get their bounding boxes as well. Set the coordinates parameter to true to add this field to the elements in the response.

POST

POST

curl -X 'POST' $UNSTRUCTURED_API_URL \
-H 'accept: application/json' \
-H 'Content-Type: multipart/form-data' \
-H 'unstructured-api-key: $UNSTRUCTURED_API_KEY' \
-F 'files=@sample-docs/layout-parser-paper.pdf' \
-F 'coordinates=true' \
-F 'strategy=hi_res'

Python SDK

Python

import asyncio
import os
import json
import unstructured_client
from unstructured_client.models import shared

client = unstructured_client.UnstructuredClient(
    api_key_auth=os.getenv("UNSTRUCTURED_API_KEY")
)

async def call_api(filename, input_dir, output_dir):
    req = {
        "partition_parameters": {
            "files": {
                "content": open(filename, "rb"),
                "file_name": os.path.basename(filename),
            },
            "strategy": shared.Strategy.HI_RES,
            "coordinates": True,
            "split_pdf_page": True,
            "split_pdf_allow_failed": True,
            "split_pdf_concurrency_level": 15
        }
    }

    try:
        res = await client.general.partition_async(
            request=req
        )
        element_dicts = [element for element in res.elements]
        json_elements = json.dumps(element_dicts, indent=2)

        # Create the output directory structure.
        relative_path = os.path.relpath(os.path.dirname(filename), input_dir)
        output_subdir = os.path.join(output_dir, relative_path)
        os.makedirs(output_subdir, exist_ok=True)

        # Write the output file.
        output_filename = os.path.join(output_subdir, os.path.basename(filename) + ".json")
        with open(output_filename, "w") as file:
            file.write(json_elements)

    except Exception as e:
        print(f"Error processing {filename}: {e}")

async def process_files(input_directory, output_directory):
    tasks = []

    for root, _, files in os.walk(input_directory):
        for file in files:
            if not file.endswith('.json'):
                full_path = os.path.join(root, file)
                tasks.append(call_api(full_path, input_directory, output_directory))

    await asyncio.gather(*tasks)

if __name__ == "__main__":
    asyncio.run(process_files(
        input_directory=os.getenv("LOCAL_FILE_INPUT_DIR"), 
        output_directory=os.getenv("LOCAL_FILE_OUTPUT_DIR")
    ))

JavaScript/TypeScript SDK

TypeScript

import { UnstructuredClient } from "unstructured-client";
import * as fs from "fs";
import * as path from "path";
import { Strategy } from "unstructured-client/sdk/models/shared/index.js";
import { PartitionResponse } from "unstructured-client/sdk/models/operations";

// Send all files in the source path to Unstructured for processing.
// Send the processed data to the destination path.
function processFiles(
    client: UnstructuredClient,
    sourcePath: string,
    destinationPath: string
): void {

    // If an output directory does not exist for the corresponding input
    // directory, then create it.
    if (!fs.existsSync(destinationPath)) {
        fs.mkdirSync(destinationPath, { recursive: true });
    }

    // Get all folders and files at the current level of the input directory.
    const items = fs.readdirSync(sourcePath);

    // For each folder and file in the input directory...
    for (const item of items) {
        const inputPath = path.join(sourcePath, item);
        const outputPath = path.join(destinationPath, item)

        // If it's a folder, call this function recursively.
        if (fs.statSync(inputPath).isDirectory()) {
            processFiles(client, inputPath, outputPath);
        } else {
            // If it's a file, send it to Unstructured for processing.
            const data = fs.readFileSync(inputPath);

            client.general.partition({
                partitionParameters: {
                    files: {
                        content: data,
                        fileName: inputPath
                    },
                    strategy: Strategy.HiRes,
                    coordinates: true,
                    splitPdfPage: true,
                    splitPdfConcurrencyLevel: 15,
                    splitPdfAllowFailed: true
                }
            }).then((res: PartitionResponse) => {
                // If successfully processed, write the processed data to
                // the destination directory.
                if (res.statusCode == 200) {
                    const jsonElements = JSON.stringify(res, null, 2)
                    fs.writeFileSync(outputPath + ".json", jsonElements)
                }
            }).catch((e) => {
                if (e.statusCode) {
                    console.log(e.statusCode);
                    console.log(e.body);
                } else {
                    console.log(e);
                }
            });
        }
    }
}

const client = new UnstructuredClient({
    security: { apiKeyAuth: process.env.UNSTRUCTURED_API_KEY },
    serverURL: process.env.UNSTRUCTURED_API_URL
});

processFiles(
    client,
    process.env.LOCAL_FILE_INPUT_DIR,
    process.env.LOCAL_FILE_OUTPUT_DIR
);

Returning unique element IDs

By default, the element ID is a SHA-256 hash of the element text. This is to ensure that the ID is deterministic. One downside is that the ID is not guaranteed to be unique. Different elements with the same text will have the same ID, and there could also be hash collisions. To use UUIDs in the output instead, set unique_element_ids=true. Note: this means that the element IDs will be random, so with every partition of the same file, you will get different IDs. This can be helpful if you’d like to use the IDs as a primary key in a database, for example.

POST

POST

curl -X 'POST' $UNSTRUCTURED_API_URL \
-H 'accept: application/json'  \
-H 'Content-Type: multipart/form-data' \
-H 'unstructured-api-key: $UNSTRUCTURED_API_KEY' \
-F 'files=@sample-docs/layout-parser-paper-fast.pdf' \
-F 'unique_element_ids=true' \
-F 'strategy=vlm' \
-F 'vlm_model_provider=openai' \
-F 'vlm_model=gpt-4o'

Python SDK

Python

import asyncio
import os
import json
import unstructured_client
from unstructured_client.models import shared

client = unstructured_client.UnstructuredClient(
    api_key_auth=os.getenv("UNSTRUCTURED_API_KEY")
)

async def call_api(filename, input_dir, output_dir):
    req = {
        "partition_parameters": {
            "files": {
                "content": open(filename, "rb"),
                "file_name": os.path.basename(filename),
            },
            "strategy": shared.Strategy.VLM,
            "vlm_model": "gpt-4o",
            "vlm_model_provider": "openai",
            "unique_element_ids": True,
            "split_pdf_page": True,
            "split_pdf_allow_failed": True,
            "split_pdf_concurrency_level": 15
        }
    }

    try:
        res = await client.general.partition_async(
            request=req
        )
        element_dicts = [element for element in res.elements]
        json_elements = json.dumps(element_dicts, indent=2)

        # Create the output directory structure.
        relative_path = os.path.relpath(os.path.dirname(filename), input_dir)
        output_subdir = os.path.join(output_dir, relative_path)
        os.makedirs(output_subdir, exist_ok=True)

        # Write the output file.
        output_filename = os.path.join(output_subdir, os.path.basename(filename) + ".json")
        with open(output_filename, "w") as file:
            file.write(json_elements)

    except Exception as e:
        print(f"Error processing {filename}: {e}")

async def process_files(input_directory, output_directory):
    tasks = []

    for root, _, files in os.walk(input_directory):
        for file in files:
            if not file.endswith('.json'):
                full_path = os.path.join(root, file)
                tasks.append(call_api(full_path, input_directory, output_directory))

    await asyncio.gather(*tasks)

if __name__ == "__main__":
    asyncio.run(process_files(
        input_directory=os.getenv("LOCAL_FILE_INPUT_DIR"), 
        output_directory=os.getenv("LOCAL_FILE_OUTPUT_DIR")
    ))

JavaScript/TypeScript SDK

TypeScript

import { UnstructuredClient } from "unstructured-client";
import * as fs from "fs";
import * as path from "path";
import { Strategy } from "unstructured-client/sdk/models/shared/index.js";
import { PartitionResponse } from "unstructured-client/sdk/models/operations";

// Send all files in the source path to Unstructured for processing.
// Send the processed data to the destination path.
function processFiles(
    client: UnstructuredClient,
    sourcePath: string,
    destinationPath: string
): void {

    // If an output directory does not exist for the corresponding input
    // directory, then create it.
    if (!fs.existsSync(destinationPath)) {
        fs.mkdirSync(destinationPath, { recursive: true });
    }

    // Get all folders and files at the current level of the input directory.
    const items = fs.readdirSync(sourcePath);

    // For each folder and file in the input directory...
    for (const item of items) {
        const inputPath = path.join(sourcePath, item);
        const outputPath = path.join(destinationPath, item)

        // If it's a folder, call this function recursively.
        if (fs.statSync(inputPath).isDirectory()) {
            processFiles(client, inputPath, outputPath);
        } else {
            // If it's a file, send it to Unstructured for processing.
            const data = fs.readFileSync(inputPath);

            client.general.partition({
                partitionParameters: {
                    files: {
                        content: data,
                        fileName: inputPath
                    },
                    uniqueElementIds: true,
                    strategy: Strategy.HiRes,
                    splitPdfPage: true,
                    splitPdfConcurrencyLevel: 15,
                    splitPdfAllowFailed: true
                }
            }).then((res: PartitionResponse) => {
                // If successfully processed, write the processed data to
                // the destination directory.
                if (res.statusCode == 200) {
                    const jsonElements = JSON.stringify(res, null, 2)
                    fs.writeFileSync(outputPath + ".json", jsonElements)
                }
            }).catch((e) => {
                if (e.statusCode) {
                    console.log(e.statusCode);
                    console.log(e.body);
                } else {
                    console.log(e);
                }
            });
        }
    }
}

const client = new UnstructuredClient({
    security: { apiKeyAuth: process.env.UNSTRUCTURED_API_KEY },
    serverURL: process.env.UNSTRUCTURED_API_URL
});

processFiles(
    client,
    process.env.LOCAL_FILE_INPUT_DIR,
    process.env.LOCAL_FILE_OUTPUT_DIR
);

Adding the chunking step after partitioning

You can combine partitioning and subsequent chunking in a single request by setting the chunking_strategy parameter. By default, the chunking_strategy is set to None, and no chunking is performed.

POST

POST

curl -X 'POST' $UNSTRUCTURED_API_URL \
-H 'accept: application/json'  \
-H 'Content-Type: multipart/form-data' \
-H 'unstructured-api-key: $UNSTRUCTURED_API_KEY' \
-F 'files=@sample-docs/layout-parser-paper-fast.pdf' \
-F 'chunking_strategy=by_title' \
-F 'max_characters=1024' \
-F 'strategy=vlm' \
-F 'vlm_model_provider=openai' \
-F 'vlm_model=gpt-4o'

Python SDK

Python

import asyncio
import os
import json
import unstructured_client
from unstructured_client.models import shared

client = unstructured_client.UnstructuredClient(
    api_key_auth=os.getenv("UNSTRUCTURED_API_KEY")
)

async def call_api(filename, input_dir, output_dir):
    req = {
        "partition_parameters": {
            "files": {
                "content": open(filename, "rb"),
                "file_name": os.path.basename(filename),
            },
            "chunking_strategy": "by_title",
            "max_characters": 1024,
            "strategy": shared.Strategy.VLM,
            "vlm_model": "gpt-4o",
            "vlm_model_provider": "openai",
            "split_pdf_page": True,
            "split_pdf_allow_failed": True,
            "split_pdf_concurrency_level": 15
        }
    }

    try:
        res = await client.general.partition_async(
            request=req
        )
        element_dicts = [element for element in res.elements]
        json_elements = json.dumps(element_dicts, indent=2)

        # Create the output directory structure.
        relative_path = os.path.relpath(os.path.dirname(filename), input_dir)
        output_subdir = os.path.join(output_dir, relative_path)
        os.makedirs(output_subdir, exist_ok=True)

        # Write the output file.
        output_filename = os.path.join(output_subdir, os.path.basename(filename) + ".json")
        with open(output_filename, "w") as file:
            file.write(json_elements)

    except Exception as e:
        print(f"Error processing {filename}: {e}")

async def process_files(input_directory, output_directory):
    tasks = []

    for root, _, files in os.walk(input_directory):
        for file in files:
            if not file.endswith('.json'):
                full_path = os.path.join(root, file)
                tasks.append(call_api(full_path, input_directory, output_directory))

    await asyncio.gather(*tasks)

if __name__ == "__main__":
    asyncio.run(process_files(
        input_directory=os.getenv("LOCAL_FILE_INPUT_DIR"), 
        output_directory=os.getenv("LOCAL_FILE_OUTPUT_DIR")
    ))

JavaScript/TypeScript SDK

TypeScript

import { UnstructuredClient } from "unstructured-client";
import * as fs from "fs";
import * as path from "path";
import { ChunkingStrategy, Strategy } from "unstructured-client/sdk/models/shared/index.js";
import { PartitionResponse } from "unstructured-client/sdk/models/operations";

// Send all files in the source path to Unstructured for processing.
// Send the processed data to the destination path.
function processFiles(
    client: UnstructuredClient,
    sourcePath: string,
    destinationPath: string
): void {

    // If an output directory does not exist for the corresponding input
    // directory, then create it.
    if (!fs.existsSync(destinationPath)) {
        fs.mkdirSync(destinationPath, { recursive: true });
    }

    // Get all folders and files at the current level of the input directory.
    const items = fs.readdirSync(sourcePath);

    // For each folder and file in the input directory...
    for (const item of items) {
        const inputPath = path.join(sourcePath, item);
        const outputPath = path.join(destinationPath, item)

        // If it's a folder, call this function recursively.
        if (fs.statSync(inputPath).isDirectory()) {
            processFiles(client, inputPath, outputPath);
        } else {
            // If it's a file, send it to Unstructured for processing.
            const data = fs.readFileSync(inputPath);

            client.general.partition({
                partitionParameters: {
                    files: {
                        content: data,
                        fileName: inputPath
                    },
                    strategy: Strategy.HiRes,
                    chunkingStrategy: ChunkingStrategy.ByTitle,
                    maxCharacters: 1024,
                    splitPdfPage: true,
                    splitPdfConcurrencyLevel: 15,
                    splitPdfAllowFailed: true
                }
            }).then((res: PartitionResponse) => {
                // If successfully processed, write the processed data to
                // the destination directory.
                if (res.statusCode == 200) {
                    const jsonElements = JSON.stringify(res, null, 2)
                    fs.writeFileSync(outputPath + ".json", jsonElements)
                }
            }).catch((e) => {
                if (e.statusCode) {
                    console.log(e.statusCode);
                    console.log(e.body);
                } else {
                    console.log(e);
                }
            });
        }
    }
}

const client = new UnstructuredClient({
    security: { apiKeyAuth: process.env.UNSTRUCTURED_API_KEY },
    serverURL: process.env.UNSTRUCTURED_API_URL
});

processFiles(
    client,
    process.env.LOCAL_FILE_INPUT_DIR,
    process.env.LOCAL_FILE_OUTPUT_DIR
);