Skip to main content

r3con

arXiv Python License

Context representation for large-scale reasoning.

Ask a question whose evidence is scattered across many documents. r3con builds a task-specific representation of that context, then reasons over it to produce an answer.

How r3con works

Install

pip install r3context

Set the API key(s) for the provider(s) you use:

export OPENAI_API_KEY=sk-...
export ANTHROPIC_API_KEY=sk-ant-...

You can also put them in a .env file in your working directory.

Usage

Command line

Pass a directory, glob, or list of files:

r3con run "Which supplier missed the most delivery windows?" ./reports \
  --model openai/gpt-6-luna

--model accepts any LiteLLM model string, for example:

anthropic/claude-sonnet-5-5
gemini/gemini-3.8-flash
hosted_vllm/Qwen/Qwen3.5-35B-A3B

The default is openai/gpt-6-luna.

Directories are searched recursively. You can also use glob patterns or pass files directly:

r3con run "Who approved the Q3 overspend?" "./reports/*.pdf"
r3con run "Who approved the Q3 overspend?" "./reports/**/*.pdf"
r3con run "Who approved the Q3 overspend?" q1.md q2.md q3.md

Quote glob patterns so your shell passes them to r3con unchanged.

Python

Load documents from a directory, glob, or list of files:

from r3con import r3con

docs = r3con.read_documents("./reports")
result = r3con.run(
    "Which supplier missed the most delivery windows?",
    docs,
)
print(result)  # "Ardent Logistics missed the most delivery windows: 8 in total."

read_documents supports .txt, .md, .csv, .json, .html, .xml, .pdf, and other common text formats.

If you already have the documents in memory, pass them directly:

result = r3con.run(
    "Which supplier missed the most delivery windows?",
    [doc_a, doc_b, doc_c],
)

documents is simply a list of strings, one per document.

Notebooks

The examples use five short memos arranged so that no single document contains the full answer:

Output

r3con.run(...) returns a result object containing the final answer and the representation built during the run:

result.answer  # str       — final answer
result.relevant_context  # list[str] — final relevance snippets
result.structured_context  # dict      — structured representation
result.run_dir  # Path      — directory containing run artifacts

str(result) returns the same value as result.answer.

Run artifacts

Every run writes its intermediate artifacts to a directory under ./logs. This includes the relevance snippet produced for each document at every round, the generated schema, parsed records, model calls, and the final reasoning transcript.

logs/<timestamp>_<hex>/          <- result.run_dir
├── splits.json                  <- only when a document was read in parts
├── relevance/
│   ├── result.json
│   └── calls.json
├── structuring/
│   ├── schema/
│   │   ├── result.json
│   │   ├── calls.json
│   │   └── transcript.yaml
│   └── parsing/
│       ├── result.json
│       └── calls.json
└── reasoning/
    ├── result.json
    ├── calls.json
    └── transcript.yaml

Evaluation

Paper: for benchmark results, baselines, and evaluation code, see r3con-evaluation.

License

MIT — see LICENSE.

src/r3con/runtime/python_executor.py contains a modified version of the sandboxed interpreter from smolagents, licensed under Apache-2.0 and © HuggingFace Inc. See NOTICE and LICENSE-APACHE-2.0.

Metadata

Release files for r3context 0.4.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for r3context 0.4.0
File Size Uploaded Provenance Actions
r3context-0.4.0.tar.gz 97.1 kB With provenance Details for r3context-0.4.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for r3context 0.4.0
File Interpreter ABI Platform Actions
r3context-0.4.0-py3-none-any.whl Python 3 none any Details for r3context-0.4.0-py3-none-any.whl

Total release size: 210.6 kB

Release files / r3context-0.4.0.tar.gz

Download URL r3context-0.4.0.tar.gz
Size 97.1 kB
Tags Source
SHA-256 checksum
How to use checksums
65b34c26e07d57d1b3d7c3a88c9f6aaa7aa68787ca3e1beedabe38693eef35b7
BLAKE2b-256 checksum
How to use checksums
c72de8be54c1a0b22276744d8d534d0ed3f1ac02f66475ba61e1091fd0b1ae20
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 28, 2026.

Transparency log

Release files / r3context-0.4.0-py3-none-any.whl

Download URL r3context-0.4.0-py3-none-any.whl
Size 113.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
df68ba43bfe517b2e24aa92353b2b1ca159ae6eebaa5da9c5489e8906c700d85
BLAKE2b-256 checksum
How to use checksums
d7299687392858fc4d72710ca7ada371eb05679fe3af7c6353f1e4ccec0dc216
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 28, 2026.

Transparency log

Security for r3context 0.4.0

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.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for r3context-0.4.0.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 28, 2026.

Transparency log

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.

Release history Release notifications | RSS feed

This release

0.4.0 This release

2 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page