Documents and Processing
How do I return the whole document as plain Markdown?
Set chunking to disabled (the default). The entire document will be returned as a single chunk with all content in the content field as Markdown.
result = client.parse.run(
input=upload.file_id,
retrieval={"chunking": {"chunk_mode": "disabled"}},
settings={"model": "r-1"},
)
# Full document as markdown
markdown = result.result.chunks[0].contentTables will be formatted according to your table_output_format setting (default: dynamic, which uses Markdown for simple tables).
What's the difference between content and embed fields?
Both fields contain the chunk’s text, but optimized for different purposes:
content: Raw extraction with original formatting. Tables appear as HTML or Markdown. Use for display.embed: Optimized for vector embeddings. Same text ascontent. Whenretrieval.embedding_optimizedis on, tables become natural language summaries like “This table shows quarterly revenue…” which embed better.
For RAG: Use embed for your vector database, content for displaying results to users.
See Understanding Chunks for details.
How do I use Reducto for RAG?
- Parse with variable chunking to get semantically meaningful segments
- Enable embedding optimization so tables become natural language
- Filter noise like headers and footers
- Store chunks in your vector database
result = client.parse.run(
input=upload.file_id,
retrieval={
"chunking": {"chunk_mode": "variable", "chunk_size": 1000},
"embedding_optimized": True,
"filter_blocks": ["Header", "Footer", "Page Number"]
},
settings={"model": "r-1"},
)
for chunk in result.result.chunks:
your_vector_db.insert(
embedding=your_embedding_function(chunk.embed),
metadata={"content": chunk.content, "blocks": chunk.blocks}
)See Parse Best Practices for more.
Which configurations increase latency?
Adds significant latency:
- Customized agentic processing with
enhance.agenticand custom prompts enhance.agentic[].advanced_chart_agent: true(advanced chart extraction)- On legacy Parse, promptless agentic scopes and
enhance.summarize_figures - Large documents with
embedding_optimized: true
Moderate impact:
settings.return_images(generates cropped images)settings.embed_pdf_metadata(modifies PDF)
Minimal impact:
- Chunking mode changes
- Table output format changes
- Block filtering
r-1 handles general parsing accuracy natively, so promptless agentic scopes are not needed. For latency-sensitive applications, use customized agentic processing only when needed and use async with priority.
Can I choose which LLM or model Reducto uses?
No. Reducto manages model selection internally to optimize for accuracy, cost, and latency. The models used may change as we improve the system.
For on-premise deployments, you can configure which LLM providers are available. See LLM Configuration.
URLs and Retention
How long are result URLs valid?
- Image URLs (
image_urlfromreturn_images): Valid for 12 hours - PDF URLs (
pdf_url): Valid for 12 hours - Result URLs (when
type: "url"): Valid for 12 hours
Reducto signs image and PDF URLs when the job completes, and fetching the job again returns the same URLs. Reducto signs a new result URL each time you fetch the job. Download or process any URLs promptly after receiving them.
How long are job results retained?
By default, job results are generally available for 12 hours. Under Reducto’s zero data retention (ZDR) policy, all API processing artifacts for API-submitted jobs are typically purged within 24 hours for Growth and Enterprise tiers.
To keep results longer:
result = client.parse.run(
input=upload.file_id,
settings={"model": "r-1", "persist_results": True}
)With persist_results: true, results are stored indefinitely and can be retrieved anytime using the job ID. This requires opting in to Reducto Studio.
Why am I getting a URL instead of inline results?
When the response exceeds approximately 6MB, Reducto returns result.type: "url" instead of result.type: "full". Fetch the content from result.url:
if result.result.type == "url":
import requests
chunks = requests.get(result.result.url).json()
else:
chunks = result.result.chunksTo always get URL responses (for consistent handling):
result = client.parse.run(
input=upload.file_id,
settings={"model": "r-1", "force_url_result": True}
)Job ID not found error
Job IDs generally expire after 12 hours. Under Reducto’s zero data retention (ZDR) policy, all API processing artifacts for API-submitted jobs are typically purged within 24 hours for Growth and Enterprise tiers. Jobs can also be explicitly deleted via DELETE /job/{job_id}.
A 410 response means the job was permanently deleted. A 409 response means deletion is in progress.
To prevent data loss:
- Process results immediately when you receive them
- Store results in your own database
- Use
persist_results: trueto keep results indefinitely
See Deleting Jobs & Uploads for more on manual deletion.
API and Integration
What's the maximum file size?
- Direct upload (
/upload): 100MB - Presigned URL upload: 5GB
- URL passthrough: No limit (Reducto fetches the file)
For files over 100MB, use the presigned URL method. For files over 5GB, host them on S3 or another storage service and pass the URL directly.
How do I check system status?
Visit status.reducto.ai for real-time status of all Reducto services, uptime history, and incident reports.
Subscribe to updates to get notified of any service disruptions.
How do I contact support?
- Email: support@reducto.ai
- Slack: Available for Growth and Enterprise customers
- Teams: Available for Growth and Enterprise customers
- Studio: Use the feedback button in Reducto Studio