Ask your filing cabinet

The Knowledge node is in alpha and appears in the palette once the feature is switched on for your organization. Ask us to enable it.

Extraction answers “what is on this document”. This answers “what do these documents say about X”, across every document the workflow has ever parsed. Add a Knowledge node and the corpus builds itself; then ask it questions over the API. Every answer comes back with the quotes it rests on, each resolved to a page and a region of the original PDF.

You ask

→

It answers

NodesCredits27 per pageYou get

The workflow

The node has no options. Its presence is the switch: every document this workflow parses is folded into one corpus.

{
  "name": "Ask the supplier file",
  "description": "Index every document the workflow parses, then ask it questions",
  "nodes": [
    { "id": "parse_1", "type": "parse" },
    { "id": "knowledge_1", "type": "knowledge" }
  ],
  "edges": [{ "source": "parse_1", "target": "knowledge_1" }]
}

import os

from anyformat.sdk import Client

client = Client(api_key=os.environ["ANYFORMAT_API_KEY"])

workflow = (
    client.workflow("Ask the supplier file", "Index every document the workflow parses")
    .parse()
    .knowledge()
    .create()
)

The corpus is workflow-scoped, not version-scoped. It accumulates the latest parse of every live file across every run and every version, so a document parsed months ago under an older version is still answerable.

Ask it

Upload and run documents as you would with any workflow. Then ask.

curl -X POST "https://api.anyformat.ai/v3/workflows/$WORKFLOW_ID/knowledge/ask" \
  -H "Authorization: Bearer $ANYFORMAT_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"question": "Which invoices are in this file, who issued each one, and what is the total of each?"}'

answer = workflow.ask("Which invoices are in this file, who issued each one, and what is the total of each?")

print(answer.answer)
for citation in answer.citations:
    print(citation.quote, "page", citation.page)

Response

The answer is markdown, written to be shown to a person. The citations are the point: each one carries the exact quote, the page, and a bbox in normalized page coordinates, so you can draw the box on the PDF instead of asking anyone to trust the answer. path shows which tools the agent used to get there, and steps_used how many it took.

{
  "answer": "The document `2026-08/mixed_partition.md` contains three invoices:\n\n*   **INV-2026-1000**, issued by **Acme Industries**, with a total of **$1,810.50**.\n*   **INV-2026-1001**, issued by **Globex Corporation**, with a total of **$932.45**.\n*   **INV-2026-1002**, issued by **Initech LLC**, with a total of **$5,648.15**.\n\nThe file also includes a shipping label and a boarding pass.",
  "citations": [
    {
      "path": "2026-08/mixed_partition.md",
      "quote": "Invoice #: INV-2026-1000",
      "file_id": "06a95794-11f6-77e1-8000-f49fa028d98e",
      "block_id": "p1_b1",
      "page": 1,
      "bbox": { "x0": 0.113, "x1": 0.325, "y0": 0.132, "y1": 0.21 }
    },
    {
      "path": "2026-08/mixed_partition.md",
      "quote": "**TOTAL: $1,810.50**",
      "file_id": "06a95794-11f6-77e1-8000-f49fa028d98e",
      "block_id": "p1_b9",
      "page": 1,
      "bbox": { "x0": 0.584, "x1": 0.756, "y0": 0.431, "y1": 0.483 }
    }
  ],
  "path": [
    { "tool": "kb_ls",   "args": { "folder": "." } },
    { "tool": "kb_read", "args": { "path": ["INDEX.md", "2026-08/mixed_partition.md"] } }
  ],
  "steps_used": 2,
  "thread_id": null
}

Follow-up questions

Mint a thread_id yourself, starting with kb-, and pass it to ask in the context of what came before. Reuse the same id to continue the conversation; omit it and every question stands alone.

{ "question": "Which of those is the largest?", "thread_id": "kb-invoices-review-1" }

When it goes wrong

409 KNOWLEDGE_NOT_ENABLED. The workflow has no Knowledge node. This is permanent until you add one: do not retry. 409 KNOWLEDGE_NOT_READY. The first index is still building after your first run. Retry in a few seconds. Expect this on the very first question against a new workflow. The answer is right but you cannot prove it. Read the citations, not the prose. Each bbox is normalized to the page, so multiply by the rendered page size to draw it. An answer whose citations do not support it is the one to escalate. It answers about the wrong document. The corpus holds every file the workflow ever ran, which is the feature and occasionally the surprise. Give the question the scope you mean: name the supplier, the month or the file. The bill is bigger than you expected. Questions are metered on the text the agent actually reads, so a broad sweep over a large corpus costs more than a narrow question. Ask narrowly.

Examples

Read the page

Messy piles

Money and compliance

At scale

Ask your filing cabinet

The workflow

Ask it

Response

Follow-up questions

When it goes wrong

Next steps

Knowledge

Ask

​The workflow

​Ask it

​Response

​Follow-up questions

​When it goes wrong

​Next steps

Knowledge

Ask

The workflow

Ask it

Response

Follow-up questions

When it goes wrong

Next steps