Python package + class names are provisional.pip install anyformat-sdk and from anyformat.sdk import Client work today, but both are expected to change before the official launch — pin the version you ship with.
A parse-only workflow has one parse node and no edges. For documents with mixed content (tables, figures, dense text), use agentic mode by flipping mode to "agentic" — each block is routed through a typed strategy (text / table / figure) instead of a single batched call.
import { Anyformat } from "@anyformat/sdk";const af = new Anyformat({ apiKey: process.env.ANYFORMAT_API_KEY! });const file: File = /* a File with .name set */;// Standard mode. For agentic, pass { mode: "agentic" } to parse().const workflow = await af .workflow("Document Parser", "Parse documents to markdown without extraction") .parse() .create();const run = await workflow.run(file);const result = await run.wait();const markdown = result.parse?.markdown ?? "";// parseConfidence may be null in some parse modes — fall back to layoutConfidence.const confidence = result.parse?.parseConfidence ?? result.parse?.layoutConfidence;console.log(`confidence: ${confidence}`);console.log(markdown.slice(0, 500));
import osfrom anyformat.sdk import Clientclient = Client(api_key=os.environ["ANYFORMAT_API_KEY"])# Standard mode. For agentic, pass mode="agentic" to .parse().workflow = ( client.workflow("Document Parser") .parse() .create())result = workflow.run("document.pdf").wait()# parse_confidence may be None in some parse modes — fall back to layout_confidence.# Explicit `is not None` check (not `or`) so a real 0.0 confidence still wins.confidence = ( result.parse.parse_confidence if result.parse.parse_confidence is not None else result.parse.layout_confidence)print(f"confidence: {confidence}")print((result.parse.markdown or "")[:500])
For a parse-only workflow, the extractions array is empty in the response — only the parse section is populated:
The response carries two document-level confidence rollups plus a per-block attribute inside the rendered markdown.
Field
Source
Range
Use for
parse.parse_confidence
Char-weighted mean of per-block LLM logprobs. null when no blocks have logprob-based confidence.
80–99 typical
Triage — “is this doc trustworthy enough to extract from?”
parse.layout_confidence
Char-weighted mean of YOLO layout-segmentation scores. Present whenever blocks exist.
30–60 typical
Fallback when parse_confidence is null. Measures “is this region a table?”, not “is the parsed content accurate?”
data-confidence attribute on each <section>
Per-block — calibrated logprobs when available, YOLO fallback otherwise
0–100
UI highlight — “dim low-confidence regions”
Agentic mode caveat: agentic strategies don’t always populate per-block logprobs (e.g. text-bytes-first never calls an LLM), so parse_confidence is often null and callers fall back to layout_confidence. For calibrated parser confidence (apples-to-apples with extraction confidence), use mode="standard".
Reuse one workflow. Create a single parse-only workflow and submit all documents to it — no need for separate workflows per document type.
Tables are preserved — output as HTML <table> with cell IDs.
Multi-page — each page gets its own <DOCUMENT> block with a page attribute. All pages processed automatically.
Use parse.parse_confidence for triage — filter low-confidence documents into a manual-review queue before downstream processing. Fall back to parse.layout_confidence when parse_confidence is null (e.g. agentic mode).
