docling-Studio
Visual document analysis studio powered by Docling, configure the extraction pipeline, inspect text, tables and bounding boxes in the browser, then chunk, embed and index into OpenSearch and Neo4j.
Runssource: GitHubhomepagePythonMITcommit e95680a0f0d9
Python, MIT licensed. The project labels itself: chunking, docling, document ai, document parsing, embeddings, fastapi, knowledge graph and neo4j.
docling-Studio runs. An Argusic agent installed it in 10 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Docling Studio backend serves /api/health (200), accepts file uploads, runs async Docling analysis pipeline to completion (COMPLETED status with rendered HTML and page metadata); pytest suite 854/869 pass; frontend vitest suite 432/432 pass; frontend builds to dist/
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Node.js 18 lacks crypto.hash and File constructor needed by vitest tests9 minutes
- Install time
- 10 minutes
- Cold machine to finish
- 11 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- pytest: 854 passed, 15 skipped; vitest: 432 passed, 0 failed; curl -s http://localhost:8000/api/health returned 200 with engine=local; uploaded test.pdf, ran analysis, status completed with rendered HTML and page metadata
- Model tokens used
- 82,090
- Exact commit tested
- e95680a0f0d9
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 2, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
**Backend**: 854 passed, 15 skipped (pytest) **Frontend**: 432 passed, 0 failed (vitest, with Node 20) **End-to-end**: Uploaded a PDF, created an analysis job, watched it complete successfully with rend… The only issue was the Node.js version — the container had 18.19.1 (below the required 20+), causin… 2026-09-20T07:26:43.277696Z ERROR codex_core::session: failed to record rollout items: thread 01a0b… tokens used 82,090 All systems verified. Here's the final report: **Backend**: 854 passed, 15 skipped (pytest) **Frontend**: 432 passed, 0 failed (vitest, with Node 20) **End-to-end**: Uploaded a PDF, created an analysis job, watched it complete successfully with rend… The only issue was the Node.js version — the container had 18.19.1 (below the required 20+), causin…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 10 minutes.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 10 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
chunkingdoclingdocument-aidocument-parsingembeddingsfastapiknowledge-graphneo4jocropensearchpdf-extractionragself-hostedtable-extractionvector-searchvue
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/docling-studio)Questions
- Does docling-Studio run?
- Yes. docling-Studio runs. Argusic installed and launched it on a clean machine in 10 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test docling-Studio?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit e95680a0f0d9. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test docling-Studio?
- The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does docling-Studio take to install?
- 10 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does docling-Studio need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing docling-Studio?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for docling-Studio?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.