Reprocess Source

The reprocess method (same name as the API endpoint) re-runs the ingestion pipeline on an existing source using a different partition method. Processing is asynchronous: the method returns a build_id immediately; poll Get build status until the job completes.

Method overview

Python
TypeScript

Sync

client.sources.reprocess()

Async

await client.sources.reprocess()

Method signature

Python
TypeScript

client.sources.reprocess(
    file_id: str,                           # Required
    method: str | None = None,             # Optional: auto, fast, balanced, accurate, agentic
    timeout: float | None = None
) -> SourceReprocessResponse

Returns SourceReprocessResponse with .build_id.

await client.sources.reprocess({
  file_id: string,                                   // Required
  method?: 'auto' | 'fast' | 'balanced' | 'accurate' | 'agentic',
}): Promise<SourceReprocessResponse>

Returns SourceReprocessResponse with .build_id.

Parameters

Python
TypeScript

Parameter	Type	Description	Required
`file_id`	`str`	Unique identifier of the source to re-process	Yes
`method`	`str \| None`	One of: `auto`, `fast`, `balanced`, `accurate`, `agentic`. Default: `fast`	No
`timeout`	`float`	Request timeout in seconds	No

Parameter	Type	Description	Required
`file_id`	`string`	Unique identifier of the source to re-process	Yes
`method`	`string`	One of: `auto`, `fast`, `balanced`, `accurate`, `agentic`	No

Partition method values (v2)

Value	Name	Description
`auto`	Auto	Per-page routing: classifies each page and runs the cheapest parser that fits. Best for mixed PDFs (body + tables + scans in one document). PDF-only.
`fast`	Fast	Fast processing with heuristic classification. No OCR.
`balanced`	Balanced	OCR-based extraction with structure classification.
`accurate`	Accurate	Fine-tuned model for highest accuracy (Premium).
`agentic`	Agentic	Highest accuracy for complex layouts, tables, and diagrams.

Method comparison

Method	Speed	Text parsing	Element classification	Best use cases	OCR
Auto	Mixed (per page)	Best for the page	Best for the page	Mixed PDFs with body + tables + scans	When needed
Fast	High	Good	Good	Simple text files, testing	No
Balanced	Medium	Very good	Very good	Complex layouts, mixed content	Yes
Accurate	Medium	Excellent	Excellent	Premium accuracy needed	Yes
Agentic	Medium	Excellent	Excellent	Complex layouts, multi-page tables, diagrams	Yes

Return value

The method returns a build_id (string). Use it with Get build status to poll until processing completes (Completed or failure). The file_id does not change.

Code examples

Basic usage

Python
TypeScript

from graphor import Graphor

client = Graphor()
file_id = "a1b2c3d4-e5f6-7890-abcd-ef1234567890"  # from list() or get_build_status

response = client.sources.reprocess(
    file_id=file_id,
    method="balanced"
)
print(f"Build ID: {response.build_id}")

const client = new Graphor();
const fileId = 'a1b2c3d4-e5f6-7890-abcd-ef1234567890';

const { build_id: buildId } = await client.sources.reprocess({
  file_id: fileId,
  method: 'balanced',
});
console.log('Build ID:', buildId);

Reprocess and poll until complete

Python
TypeScript

import time
from graphor import Graphor

client = Graphor()
file_id = "a1b2c3d4-e5f6-7890-abcd-ef1234567890"

response = client.sources.reprocess(file_id=file_id, method="balanced")
build_id = response.build_id

while True:
    status = client.sources.get_build_status(build_id)
    if status.status == "Completed":
        print("Done. file_id:", status.file_id)
        break
    if status.error and status.status != "not_found":
        raise RuntimeError(status.error)
    time.sleep(2)

const client = new Graphor();
const fileId = 'a1b2c3d4-e5f6-7890-abcd-ef1234567890';
const { build_id: buildId } = await client.sources.reprocess({ file_id: fileId, method: 'balanced' });

while (true) {
  const status = await client.sources.getBuildStatus(buildId);
  if (status.status === 'Completed') {
    console.log('Done. file_id:', status.file_id);
    break;
  }
  if (status.error && status.status !== 'not_found') throw new Error(status.error);
  await new Promise((r) => setTimeout(r, 2000));
}

With partition method

Python
TypeScript

response = client.sources.reprocess(file_id=file_id, method="agentic")
build_id = response.build_id

const { build_id: buildId } = await client.sources.reprocess({
  file_id: fileId,
  method: 'agentic',
});

Reprocessing runs in the background and can take several minutes. Use Get build status to poll until completion.

Error handling

Python
TypeScript

import graphor
from graphor import Graphor

client = Graphor()
try:
    response = client.sources.reprocess(file_id=file_id, method="balanced")
    print("Scheduled. Build ID:", response.build_id)
except graphor.NotFoundError as e:
    print("Source not found:", e)
except graphor.BadRequestError as e:
    print("Invalid request:", e)
except graphor.APIStatusError as e:
    print("API error:", e)

try {
  const { build_id: buildId } = await client.sources.reprocess({ file_id: fileId, method: 'balanced' });
  console.log('Scheduled. Build ID:', buildId);
} catch (err) {
  if (err instanceof Graphor.NotFoundError) {
    console.log('Source not found:', err.message);
  } else if (err instanceof Graphor.APIError) {
    console.log('API error:', err.message);
  } else {
    throw err;
  }
}

Batch reprocess

Reprocess multiple sources by file_id; each call returns a build_id. Poll Get build status for each until complete.

Python
TypeScript

from graphor import Graphor

client = Graphor()
file_ids = ["id1", "id2", "id3"]
build_ids = []
for fid in file_ids:
    try:
        resp = client.sources.reprocess(file_id=fid, method="balanced")
        build_ids.append(resp.build_id)
        print(f"Scheduled: {fid} -> {resp.build_id}")
    except Exception as e:
        print(f"FAIL - {fid}: {e}")

const client = new Graphor();
const fileIds = ['id1', 'id2', 'id3'];
const buildIds: string[] = [];
for (const fid of fileIds) {
  try {
    const { build_id: bid } = await client.sources.reprocess({ file_id: fid, method: 'balanced' });
    buildIds.push(bid);
    console.log(`Scheduled: ${fid} -> ${bid}`);
  } catch (err) {
    console.log(`FAIL - ${fid}:`, err);
  }
}

When to reprocess

Poor text extraction

Symptoms: Missing text, garbled characters, incomplete content
Recommended: balanced or accurate for complex layouts.

Table detection issues

Symptoms: Tables not recognized, merged cells, structure lost
Recommended: balanced, accurate, or agentic for multi-page tables.

Image and figure handling

Symptoms: Missing captions, poor figure recognition
Recommended: balanced, accurate, or agentic for rich image annotations.

Document structure problems

Symptoms: Headers/footers mixed with content, poor section detection
Recommended: balanced, accurate, or agentic for better structure and semantics.

Best practices

Use file_id: Always use the source’s file_id (from list sources or build status).
Poll build status: After calling reprocess, poll Get build status with a reasonable interval (e.g. 2–5 seconds) and timeout.
Choose method by need: Start with fast for testing; use balanced or accurate for better quality; use agentic for complex layouts and tables.

Error Reference

Error Type	Status Code	Description
`BadRequestError`	400	Invalid request format or partition method
`AuthenticationError`	401	Invalid or missing API key
`PermissionDeniedError`	403	Access denied to the specified project
`NotFoundError`	404	Source not found for the given file_id
`RateLimitError`	429	Too many requests, please retry after waiting
`InternalServerError`	≥500	Processing failure or server error
`APIConnectionError`	N/A	Network connectivity issues
`APITimeoutError`	N/A	Request timed out

Troubleshooting

Processing timeouts

Causes: Large files, complex documents, or heavy server loadSolutions:

Increase request timeout (5+ minutes recommended)
Try a simpler processing method first
Process during off-peak hours

Python
TypeScript

client = Graphor(timeout=600.0)  # 10 minutes

const client = new Graphor({ timeout: 600 * 1000 }); // 10 minutes

Source not found (404)

Causes: Invalid file_id, source deleted, or wrong projectSolutions:

Use client.sources.list() to get valid file_ids
Ensure you’re using the correct API key for the project

Python
TypeScript

sources = client.sources.list()
for s in sources:
    print(s.file_id, s.file_name)

const sources = await client.sources.list();
for (const s of sources) {
  console.log(s.file_id, s.file_name);
}

Processing failures

Causes: Corrupted file, unsupported content, or method incompatibilitySolutions:

Try a different method (e.g. balanced, agentic)
Check file integrity; re-ingest if necessary using client.sources.ingest_file()

Poor processing quality

Solutions:

Use balanced or accurate for complex layouts
Use agentic for complex layouts with tables and diagrams

Next steps

After reprocessing, poll Get build status until complete, then:

Get build status

Poll status and get parsed elements for a build

List sources

View all sources and their status

Upload

Ingest new files, URLs, GitHub repos, or YouTube videos

Get elements

Retrieve parsed elements from a source

Delete source

Remove a source by file_id

Get Started

Data SDK Options

Method overview

Sync

Async

Method signature

Parameters

Partition method values (v2)

Method comparison

Return value

Code examples

Basic usage

Reprocess and poll until complete

With partition method

Error handling

Batch reprocess

When to reprocess

Best practices

Error Reference

Troubleshooting

Next steps

Get build status

List sources

Upload

Get elements

Delete source

​Method overview

Sync

Async

​Method signature

​Parameters

​Partition method values (v2)

​Method comparison

​Return value

​Code examples

​Basic usage

​Reprocess and poll until complete

​With partition method

​Error handling

​Batch reprocess

​When to reprocess

​Best practices

​Error Reference

​Troubleshooting

​Next steps

Get build status

List sources

Upload

Get elements

Delete source

Method overview

Method signature

Parameters

Partition method values (v2)

Method comparison

Return value

Code examples

Basic usage

Reprocess and poll until complete

With partition method

Error handling

Batch reprocess

When to reprocess

Best practices

Error Reference

Troubleshooting

Next steps