contextF
Efficient context builder. Build relevant context from documents using configurable search patterns and token-aware windowing.
Installation
pip install contextF
For PDF parsing:
pip install contextF[pdf]
Parameters
Search Parameters
docs_path: Directory containing documents (default: "./docs")file_patterns: File types to search (default: [".md", ".txt"])max_patterns_per_query: Max search patterns to use (default: 3)max_matches_per_file: Max matches per file (default: 3)case_sensitive: Case sensitive search (default: false)
Token Parameters
max_context_tokens: Maximum total context tokens (default: 500000)context_window_tokens: Context window size around matches (default: 10000)max_file_tokens: Max tokens per file before windowing (default: 200000)encoding: Tokenizer encoding (default: "cl100k_base")
LLM Parameters (Optional)
enabled: Enable LLM pattern generation (default: true)model: OpenAI model (default: "gpt-4.1-mini")temperature: LLM temperature (default: 0.3)
Documentation
For detailed documentation and code examples, please refer to the README.md file.
1 maintainer
Metadata
1 maintainer
Release files for contextF 0.0.6
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 | |
|---|---|---|---|---|
| contextf-0.0.6.tar.gz | 14.6 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| contextf-0.0.6-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 30.6 kB
Release files / contextf-0.0.6.tar.gz
| Download URL | contextf-0.0.6.tar.gz |
|---|---|
| Size | 14.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
8b9b2341573e25cf416e335d1c9f1cc371a2e47204ab16338abef43b413faeaf
|
|
BLAKE2b-256 checksum How to use checksums |
833764a56a96d2d8b678da1eadadad559cacf32a47804c84e4f0596cbd034f3d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.23
|
Release files / contextf-0.0.6-py3-none-any.whl
| Download URL | contextf-0.0.6-py3-none-any.whl |
|---|---|
| Size | 16.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
753ae917222e2ea3702dd09722d0eddd78f9002eeb705f1ff5d3ff1bbb13fe7d
|
|
BLAKE2b-256 checksum How to use checksums |
08e0d1c0cfd9b48082b1b95247716c8a52d1aced599d0e8d77eb5ad74072c320
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.23
|
Security for contextF 0.0.6
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.
