docling-project/docling
What It Calls
Calls external APIs · local option
Partial check
Without a key: Runs locally (LM Studio): runs locally (LM Studio). Runs locally (MLX): runs locally (MLX). Local model file: runs locally (model file). The other rows are in the table below.
| Feature | Provider | Use | Default | Alternative |
|---|---|---|---|---|
| Text generation · Image generation · Speech-to-text · Text-to-speech · Embeddings | OpenAI
1 call sites |
Optional | api.openai.com |
Local runtime (Ollama), Local runtime (LM Studio) |
| Runs locally (LM Studio) | Local (LM Studio) | Local | - | - |
| Runs locally (MLX) | Local (MLX)
1 call sites |
Local | - | - |
| Local model file | Local (model file)
1 call sites |
Local | - | - |
| Runs locally (Ollama) | Local (Ollama) | Local | - | - |
| Runs locally (ONNX Runtime) | Local (ONNX Runtime) | Local | - | - |
| Runs locally (PyTorch) | Local (PyTorch)
1 call sites |
Local | - | - |
| Runs locally (Hugging Face Transformers) | Local (Hugging Face Transformers)
1 call sites |
Local | - | - |
Show 4 more rows
| Feature | Provider | Use | Default | Alternative |
|---|---|---|---|---|
| Runs locally (vLLM) | Local (vLLM) | Local | - | - |
| Runs locally (Whisper (local)) | Local (Whisper (local)) | Local | - | - |
| models command — Runs locally (PyTorch)Subcommand: models | Local (PyTorch)
1 call sites |
Local | - | - |
| models command — Runs locally (Hugging Face Transformers)Subcommand: models | Local (Hugging Face Transformers) | Local | - | - |
| API | Credential | Code evidence | Pricing | Pricing page | Checked |
|---|---|---|---|---|---|
| OpenAI | Your API key | docling/datamodel/vlm_engine_options.py:256OpenAI can be optionally used for text/image generation, speech-to-text/text-to-speech, and embeddings; local paths for Ollama and LM Studio are also available. |
Paid | Pricing | 2026-10-05 |
Data sent out: prompt text
Checked scope: Partial check — 400/1,843 files · tree not truncated · no submodules · 22 unresolved import path(s)
Next
Badge preview
[](https://whatitcalls.reactiveworks.dev/en/docling-project/docling)
Shows as “external API · used · local option” in a README.
Was this analysis helpful?
Freshness details
- Checked commit
dd7c03577d60867ed345037d51a358c00d6dbed4- Committed
- 2026-10-07 10:52 UTC
- Checked
- 2026-10-07 11:51 UTC
- HEAD last seen
- 2026-10-07 11:51 UTC ·
dd7c035(same as the checked commit) - Read depth
- Basic (up to 400 files · 8 MB)
- Scanner · rules
scan-5+verdict-4- Pricing catalog
- version 2
- Correction revision
- 0
- Summary
- Model ollama-cloud/gemma4:31b-cloud
What is sent out
- Confirmed Sends prompt text to OpenAI.
docling/datamodel/vlm_engine_options.py:256
README claims ↔ code
No README claim contradicts the code.
Code quotes
Checked scope details
Files
- In the repository
- 1,843
- Checked
- 400 (21%)
Manifests
All priority files read
pyproject.tomlpackages/docling/pyproject.toml
Unresolved import paths (22)
docx.documentdocling/backend/docx/drawingml/utils.py:21xml.sax.saxutilsdocling/backend/iwork/chart_image.py:34xml.etree.ElementTreedocling/backend/iwork/keynote_xml.py:19xml.etree.ElementTreedocling/backend/iwork/legacy.py:18xml.etree.ElementTreedocling/backend/iwork/numbers_xml.py:20
missing file 21 · plugin discovery 1
Excluded files
.md368.json294.itxt136.pdf79.txt73.html45
+63 more
- External code not checked
- None
- Limits hit
- file count limit
- Symbolic links not followed
- 8
Correction history
No corrections yet.