Kitconc 3.4.3
Kitconc is a package for Corpus Linguistics and text analysis with Python. It contains, among other things, tools for creating:
Corpora;
Frequency wordlists;
Keywords (Log-Likelihood, Chi-Square, TF-IDF);
Concordance lines;
Collocates;
N-gram lists;
Dispersion plots;
Excel data files;
Semantic search with sentence embeddings.
The package is built on top of platforms and packages for scientific research: numpy, pandas, NLTK, XlsxWriter and matplotlib.
Requirements
Kitconc requires Python 3.10 or later.
Package dependencies (pip install kitconc):
numpy>=1.26.4,<2.0.0 pandas>=2.2.0,<3.0.0 matplotlib>=3.7.0,<4.0.0 xlsxwriter>=3.2.3,<4.0.0 ttkbootstrap>=1.12.0,<2.0.0 pillow>=11.2.0,<12.0.0 requests>=2.31.0,<3.0.0 nltk>=3.9.1,<4.0.0 chardet>=5.2.0,<6.0.0 pypdf>=4.0.0,<7.0.0 cryptography>=3.1,<47.0.0 mcp>=1.0.0,<2.0.0 setuptools>=70.0.0
Additional dependencies listed in requirements.txt (full local environment):
torch>=2.6,<2.10 (CPU wheels via –extra-index-url https://download.pytorch.org/whl/cpu) transformers>=4.45,<6.0.0 sentence-transformers>=3.0,<6.0.0 sqlite-vec>=0.1.7,<1.0.0 fastapi>=0.110,<1.0.0 uvicorn[standard]>=0.27,<1.0.0 python-dotenv>=1.0.0,<2.0.0
Installation
pip install kitconc
Kitconc App (graphical interface)
kitconc-app
Agent Layer (internal actions)
Kitconc now includes an internal action layer for agent/tool orchestration:
kitconc.agent.actions.KitconcActions
Full parity with shell commands from kit_cmd.py (do_*)
Typed schemas in kitconc.agent.schemas
Contract documentation in kitconc/agent/CONTRACT.md
Semantic retrieval action: semantic_search(…)
Basic usage:
from kitconc.agent import KitconcActions actions = KitconcActions(“kitconc_workspace”) actions.create(“ads”, “kitconc_corpora/ads”, “english”) actions.use(“ads”) rows = actions.keywords(limit=10)
MCP Server (for agent integrations)
kitconc-mcp –transport stdio
For HTTP clients (recommended):
kitconc-mcp –transport streamable-http –host 127.0.0.1 –port 8001
or (legacy SSE):
kitconc-mcp –transport sse –host 127.0.0.1 –port 8001
Includes semantic retrieval tool: semantic_search (query, top_k, db_path, model_name)
MCP runtime is included in package dependencies (pip install kitconc is enough).
What’s new in 3.2.0
Tkinter launcher command – start GUI with kitconc-app
Agent action layer – kitconc.agent.actions.KitconcActions with command parity from kit_cmd.py
Typed schemas – available in kitconc.agent.schemas
MCP server entrypoint – run with kitconc-mcp
Semantic search MCP tool – semantic_search for sqlite-vec indexes
Embedding index hardening – transactional writes and thread-safe SQLite access
Progress flag rename – use verbose=True (replacing show_progress=True)
What’s new in 3.1.0
TF-IDF keywords – third keyword extraction method alongside Log-Likelihood and Chi-Square
Keyword filters – ignore numbers, ignore words with strange characters, minimum word length
PDF support – add PDF files directly to a corpus
Embeddings module – semantic search with sentence-transformers and SQLite vector storage
Dialog improvements – dialog boxes now center correctly in fullscreen and large-window mode
Language resources
Kitconc comes with built-in language resources for Portuguese and English corpora. It also provides functions for adding your own language resources.
Usage example
See how easy it is to use Kitconc:
1 maintainer
Release files for kitconc 3.4.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| kitconc-3.4.4.tar.gz | 6.4 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| kitconc-3.4.4-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 12.9 MB
Release files / kitconc-3.4.4.tar.gz
| Download URL | kitconc-3.4.4.tar.gz |
|---|---|
| Size | 6.4 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
102506d6ae34e4582df698e6ff0ab06fd9f2e3d274c5b649427bcd46a0f0204a
|
|
BLAKE2b-256 checksum How to use checksums |
3ead6923404f54e9728ed5be6c5d058cea6e9741fb5ca2b00f3f8cb49fd2d2ba
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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 Apr 11, 2026.
Transparency logRelease files / kitconc-3.4.4-py3-none-any.whl
| Download URL | kitconc-3.4.4-py3-none-any.whl |
|---|---|
| Size | 6.5 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0ee86c1cb3c14695137214abad069904860bd1af992f6825356ed97eb1500614
|
|
BLAKE2b-256 checksum How to use checksums |
36e13f4c641e7b89825dc5887aad5ac08edcc03affc4d937054eee0713588b03
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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 Apr 11, 2026.
Transparency log
