thinkpdf
Extract text, tables, and structure from PDFs. Built for RAG pipelines, AI training, and LLM context.
Read directly into memory or save as Markdown. Supports OCR.
Install
pip install thinkpdf # Python (PyPI)
npx thinkpdf # npm (run directly)
brew install thinkpdf # macOS (Homebrew)
choco install thinkpdf # Windows (Chocolatey)
snap install thinkpdf # Linux (Snap Store)
conda install -c conda-forge thinkpdf # Anaconda (pending)
For better table extraction (but slower):
pip install thinkpdf[docling]
Quick Start
thinkpdf document.pdf # outputs document.md
thinkpdf document.pdf -o output.md # custom output
thinkpdf folder/ --batch # convert all PDFs
from thinkpdf import convert
convert("document.pdf") # returns markdown
GUI
pip install thinkpdf[gui]
thinkpdf-gui
MCP Server
Add to your MCP config:
{
"mcpServers": {
"thinkpdf": {
"command": "python",
"args": ["-m", "thinkpdf.mcp_server"]
}
}
}
| Tool | Description |
|---|---|
read_pdf |
Read PDF content into context |
convert_pdf |
Convert and save to file |
get_document_info |
Get PDF metadata |
License
AGPL-3.0
Metadata
Release files for thinkpdf 1.0.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| thinkpdf-1.0.5.tar.gz | 57.2 kB | Without provenance | Details for thinkpdf-1.0.5.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| thinkpdf-1.0.5-py3-none-any.whl | Python 3 | none | any | Details for thinkpdf-1.0.5-py3-none-any.whl |
Total release size: 116.2 kB
Release files / thinkpdf-1.0.5.tar.gz
| Download URL | thinkpdf-1.0.5.tar.gz |
|---|---|
| Size | 57.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
6db7ed075f214f3c11e3d64be0d4f5fcf0a3e2623026dabe8500e70aa0ab2fe9
|
|
BLAKE2b-256 checksum How to use checksums |
ff57c7931becfc6effc739bd18e270285ee296cc58aec3243b44f87d20fa42fc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.3
|
Release files / thinkpdf-1.0.5-py3-none-any.whl
| Download URL | thinkpdf-1.0.5-py3-none-any.whl |
|---|---|
| Size | 59.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
2ae3327984d51d8c0b4c3beab6a308879862e4da35dd8af8063b1969715bab40
|
|
BLAKE2b-256 checksum How to use checksums |
7e7e91c3a4053a657e7383fe516131889105118400f94823b76820b80d1060f2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.3
|
Security for thinkpdf 1.0.5
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.