1
Create the job
Replace
EXTRACTION_PROMPT with your extraction prompt, and INPUT_DIR with the path to your local directory of files to process. The response includes the job ID.Each local-file processing job can include up to 10 files, and each file can be up to 50 MB.These local-file processing jobs are on-demand jobs. A job enters the queue if the Workspace is running its allowed number of on-demand jobs or an earlier job is queued.
By default, send at most one queued submission per second per Workspace.
Another queued submission within that second returns HTTP 429. Jobs that start without entering the queue do not count toward this limit.For Unstructured SaaS accounts, up to five on-demand jobs can run at once per Workspace.
Accepted queued jobs remain scheduled until capacity is available.
Your deployment settings can change both this capacity and the queued-submission rate.For other Pipelines API limits, see Pipelines API rate limits.
- curl
- Python
Save and run this script:This script requires jq to parse the JSON response.
#!/usr/bin/env bash
EXTRACTION_PROMPT="Represent dates such as May-12-24 as 2024-05-12 and June-12-25 as 2025-06-12."
INPUT_DIR="/full/path/to/your/directory"
form_args=()
for filepath in "$INPUT_DIR"/*; do
[ -f "$filepath" ] || continue
filename=$(basename "$filepath")
mimetype=$(file --mime-type -b "$filepath")
form_args+=(--form "input_files=@${filepath};filename=${filename};type=${mimetype}")
done
json_schema='{"type":"object","properties":{"invoice_number":{"type":"number"},"invoice_date":{"type":"string"},"payment_due":{"type":"string"},"bill_to":{"type":"string"}},"additionalProperties":false,"required":["invoice_number","invoice_date","payment_due","bill_to"]}'
request_data=$(jq -n --arg prompt "$EXTRACTION_PROMPT" --arg schema "$json_schema" '{
"job_nodes": [
{"name":"Partitioner","type":"partition","subtype":"vlm","settings":{"is_dynamic":true,"allow_fast":true}},
{"name":"Extractor","type":"structured_data_extractor","subtype":"llm","settings":{"schema_to_extract":{"json_schema":$schema,"extraction_guidance":$prompt},"provider":"openai","model":"gpt-5-mini","output_mode":"extracted_data_only"}}
]
}')
response=$(curl --request POST --location \
"$UNSTRUCTURED_API_URL/jobs/" \
--header "accept: application/json" \
--header "unstructured-api-key: $UNSTRUCTURED_API_KEY" \
--form "request_data=$request_data" \
"${form_args[@]}")
JOB_ID=$(echo "$response" | jq -r '.id')
echo "Job ID: $JOB_ID"
import mimetypes
import os
import json
from unstructured_client import UnstructuredClient
from unstructured_client.models.operations import CreateJobRequest
from unstructured_client.models.shared import BodyCreateJob, InputFiles
EXTRACTION_PROMPT = "<your-extraction-prompt>"
INPUT_DIR = "/full/path/to/your/directory"
client = UnstructuredClient(
api_key_auth=os.getenv("UNSTRUCTURED_API_KEY"),
server_url=os.getenv("UNSTRUCTURED_API_URL")
)
input_files = []
for filename in os.listdir(INPUT_DIR):
full_path = os.path.join(INPUT_DIR, filename)
if not os.path.isfile(full_path):
continue
content_type, _ = mimetypes.guess_type(full_path)
input_files.append(
InputFiles(
content=open(full_path, "rb"),
file_name=filename,
content_type=content_type or "application/octet-stream"
)
)
response = client.jobs.create_job(
request=CreateJobRequest(
body_create_job=BodyCreateJob(
request_data=json.dumps({
"job_nodes": [
{
"name": "Partitioner",
"type": "partition",
"subtype": "vlm",
"settings": {
"is_dynamic": True,
"allow_fast": True
}
},
{
"name": "Extractor",
"type": "structured_data_extractor",
"subtype": "llm",
"settings": {
"schema_to_extract": {
"json_schema": json.dumps({
"type": "object",
"properties": {
"invoice_number": { "type": "number" },
"invoice_date": { "type": "string" },
"payment_due": { "type": "string" },
"bill_to": { "type": "string" }
},
"additionalProperties": False,
"required": [
"invoice_number",
"invoice_date",
"payment_due",
"bill_to"
]
}),
"extraction_guidance": EXTRACTION_PROMPT
},
"provider": "openai",
"model": "gpt-5-mini",
"output_mode": "extracted_data_only"
}
}
]
}),
input_files=input_files
)
)
)
job_info = response.job_information
print(f"Job ID: {job_info.id}")
2
Poll for job status
Replace
JOB_ID with the job ID from the previous step. This script polls every 10 seconds and stops when the job completes.- curl
- Python
Save and run this script:This script requires jq to parse the JSON response.
#!/usr/bin/env bash
JOB_ID="<job-id>"
while true; do
job=$(curl --request GET --silent --location \
"$UNSTRUCTURED_API_URL/jobs/$JOB_ID" \
--header "accept: application/json" \
--header "unstructured-api-key: $UNSTRUCTURED_API_KEY")
status=$(echo "$job" | jq -r '.status')
echo "Job status: $status"
if [ "$status" = "COMPLETED" ]; then
echo "Job completed."
echo "Output node file IDs: $(echo "$job" | jq -c '[.output_node_files[].file_id]')"
break
elif [ "$status" = "FAILED" ] || [ "$status" = "STOPPED" ]; then
echo "Job did not complete successfully: $status"
exit 1
fi
sleep 10
done
import os
import time
from unstructured_client import UnstructuredClient
JOB_ID = "<job-id>"
client = UnstructuredClient(
api_key_auth=os.getenv("UNSTRUCTURED_API_KEY"),
server_url=os.getenv("UNSTRUCTURED_API_URL")
)
while True:
response = client.jobs.get_job(request={"job_id": JOB_ID})
job_info = response.job_information
status = job_info.status
print(f"Job status: {status.value}")
if status == "COMPLETED":
print("Job completed.")
print(f"Output node file IDs: {[f.file_id for f in (job_info.output_node_files or [])]}")
break
elif status in ("FAILED", "STOPPED"):
raise RuntimeError(f"Job did not complete successfully: {status}")
time.sleep(10)
3
Download the job output
Replace
JOB_ID, OUTPUT_FILE_IDS, and OUTPUT_DIR with your values from the previous steps.- curl
- Python
Save and run this script:
#!/usr/bin/env bash
JOB_ID="<job-id>"
OUTPUT_FILE_IDS=("<output-file-id>" "<output-file-id>") # From Step 1
OUTPUT_DIR="/full/path/to/your/output/directory"
mkdir -p "$OUTPUT_DIR"
for file_id in "${OUTPUT_FILE_IDS[@]}"; do
curl --request GET --silent --location \
"$UNSTRUCTURED_API_URL/jobs/$JOB_ID/download?file_id=$file_id" \
--header "unstructured-api-key: $UNSTRUCTURED_API_KEY" \
--output "$OUTPUT_DIR/$file_id.json"
echo "Saved: $OUTPUT_DIR/$file_id.json"
done
import json
import os
from unstructured_client import UnstructuredClient
from unstructured_client.models.operations import DownloadJobOutputRequest
JOB_ID = "<job-id>"
OUTPUT_FILE_IDS = ["<output-file-id>", "<output-file-id>"] # From Step 1
OUTPUT_DIR = "/full/path/to/your/output/directory"
client = UnstructuredClient(
api_key_auth=os.getenv("UNSTRUCTURED_API_KEY"),
server_url=os.getenv("UNSTRUCTURED_API_URL")
)
os.makedirs(OUTPUT_DIR, exist_ok=True)
for file_id in OUTPUT_FILE_IDS:
response = client.jobs.download_job_output(
request=DownloadJobOutputRequest(job_id=JOB_ID, file_id=file_id)
)
output_path = os.path.join(OUTPUT_DIR, f"{file_id}.json")
with open(output_path, "w") as f:
json.dump(response.any, f, indent=4)
print(f"Saved: {output_path}")
Complete end-to-end script
ReplaceEXTRACTION_PROMPT, INPUT_DIR, and OUTPUT_DIR with your values, then save and run this script.
- curl
- Python
This script requires jq to parse JSON responses.
#!/usr/bin/env bash
EXTRACTION_PROMPT="Represent dates such as May-12-24 as 2024-05-12 and June-12-25 as 2025-06-12."
INPUT_DIR="/full/path/to/your/input/directory"
OUTPUT_DIR="/full/path/to/your/output/directory"
# Step 1: Create the job.
form_args=()
for filepath in "$INPUT_DIR"/*; do
[ -f "$filepath" ] || continue
filename=$(basename "$filepath")
mimetype=$(file --mime-type -b "$filepath")
form_args+=(--form "input_files=@${filepath};filename=${filename};type=${mimetype}")
done
json_schema='{"type":"object","properties":{"invoice_number":{"type":"number"},"invoice_date":{"type":"string"},"payment_due":{"type":"string"},"bill_to":{"type":"string"}},"additionalProperties":false,"required":["invoice_number","invoice_date","payment_due","bill_to"]}'
request_data=$(jq -n --arg prompt "$EXTRACTION_PROMPT" --arg schema "$json_schema" '{
"job_nodes": [
{"name":"Partitioner","type":"partition","subtype":"vlm","settings":{"is_dynamic":true,"allow_fast":true}},
{"name":"Extractor","type":"structured_data_extractor","subtype":"llm","settings":{"schema_to_extract":{"json_schema":$schema,"extraction_guidance":$prompt},"provider":"openai","model":"gpt-5-mini","output_mode":"extracted_data_only"}}
]
}')
response=$(curl --request POST --location \
"$UNSTRUCTURED_API_URL/jobs/" \
--header "accept: application/json" \
--header "unstructured-api-key: $UNSTRUCTURED_API_KEY" \
--form "request_data=$request_data" \
"${form_args[@]}")
JOB_ID=$(echo "$response" | jq -r '.id')
echo "Job ID: $JOB_ID"
# Step 2: Poll until the job completes.
output_file_ids=()
while true; do
job=$(curl --request GET --silent --location \
"$UNSTRUCTURED_API_URL/jobs/$JOB_ID" \
--header "accept: application/json" \
--header "unstructured-api-key: $UNSTRUCTURED_API_KEY")
status=$(echo "$job" | jq -r '.status')
echo "Job status: $status"
if [ "$status" = "COMPLETED" ]; then
echo "Job completed."
while IFS= read -r id; do
output_file_ids+=("$id")
done < <(echo "$job" | jq -r '.output_node_files[].file_id')
break
elif [ "$status" = "FAILED" ] || [ "$status" = "STOPPED" ]; then
echo "Job did not complete successfully: $status"
exit 1
fi
sleep 10
done
# Step 3: Download the job output.
mkdir -p "$OUTPUT_DIR"
for file_id in "${output_file_ids[@]}"; do
curl --request GET --silent --location \
"$UNSTRUCTURED_API_URL/jobs/$JOB_ID/download?file_id=$file_id" \
--header "unstructured-api-key: $UNSTRUCTURED_API_KEY" \
--output "$OUTPUT_DIR/$file_id.json"
echo "Saved: $OUTPUT_DIR/$file_id.json"
done
import json
import mimetypes
import os
import time
from unstructured_client import UnstructuredClient
from unstructured_client.models.operations import CreateJobRequest, DownloadJobOutputRequest
from unstructured_client.models.shared import BodyCreateJob, InputFiles
EXTRACTION_PROMPT = "<your-extraction-prompt>"
INPUT_DIR = "/full/path/to/your/input/directory"
OUTPUT_DIR = "/full/path/to/your/output/directory"
client = UnstructuredClient(
api_key_auth=os.getenv("UNSTRUCTURED_API_KEY"),
server_url=os.getenv("UNSTRUCTURED_API_URL")
)
# Step 1: Create the job.
input_files = []
for filename in os.listdir(INPUT_DIR):
full_path = os.path.join(INPUT_DIR, filename)
if not os.path.isfile(full_path):
continue
content_type, _ = mimetypes.guess_type(full_path)
input_files.append(
InputFiles(
content=open(full_path, "rb"),
file_name=filename,
content_type=content_type or "application/octet-stream"
)
)
response = client.jobs.create_job(
request=CreateJobRequest(
body_create_job=BodyCreateJob(
request_data=json.dumps({
"job_nodes": [
{
"name": "Partitioner",
"type": "partition",
"subtype": "vlm",
"settings": {
"is_dynamic": True,
"allow_fast": True
}
},
{
"name": "Extractor",
"type": "structured_data_extractor",
"subtype": "llm",
"settings": {
"schema_to_extract": {
"json_schema": json.dumps({
"type": "object",
"properties": {
"invoice_number": { "type": "number" },
"invoice_date": { "type": "string" },
"payment_due": { "type": "string" },
"bill_to": { "type": "string" }
},
"additionalProperties": False,
"required": [
"invoice_number",
"invoice_date",
"payment_due",
"bill_to"
]
}),
"extraction_guidance": EXTRACTION_PROMPT
},
"provider": "openai",
"model": "gpt-5-mini",
"output_mode": "extracted_data_only"
}
}
]
}),
input_files=input_files
)
)
)
job_id = response.job_information.id
print(f"Job ID: {job_id}")
# Step 2: Poll until the job completes.
while True:
response = client.jobs.get_job(request={"job_id": job_id})
job_info = response.job_information
status = job_info.status
print(f"Job status: {status.value}")
if status == "COMPLETED":
print("Job completed.")
break
elif status in ("FAILED", "STOPPED"):
raise RuntimeError(f"Job did not complete successfully: {status}")
time.sleep(10)
output_node_file_ids = [f.file_id for f in (job_info.output_node_files or [])]
# Step 3: Download the job output.
os.makedirs(OUTPUT_DIR, exist_ok=True)
for file_id in output_node_file_ids:
response = client.jobs.download_job_output(
request=DownloadJobOutputRequest(job_id=job_id, file_id=file_id)
)
output_path = os.path.join(OUTPUT_DIR, f"{file_id}.json")
with open(output_path, "w") as f:
json.dump(response.any, f, indent=4)
print(f"Saved: {output_path}")
What’s next?
- Create local-file processing jobs that only partition, add enrichments, or add embeddings.
- Learn about the Unstructured API.