axio-tui-rag
RAG (Retrieval-Augmented Generation) plugin for axio-tui.
Index your local files into a vector store and let the agent search them semantically. Point the agent at a codebase, documentation, or notes — it retrieves relevant chunks without reading every file.
Features
- File indexing — chunk and embed files into a LanceDB vector store
- Semantic search — retrieve the most relevant chunks for a query using embedding similarity
- Incremental updates — re-indexing a file replaces its old chunks; unchanged files are skipped
- Two axio tools —
index_filesandsemantic_searchregistered via entry points
Installation
pip install axio-tui-rag
Or install as part of the TUI bundle:
pip install "axio-tui[rag]"
Usage
Via axio-tui (recommended)
Launch the TUI with RAG enabled — the agent gains two new tools automatically:
pip install "axio-tui[rag,openai]"
axio
Then ask the agent:
- "Index all Python files in ./src"
- "Search for how authentication is implemented"
Standalone
from axio.agent import Agent
from axio.context import MemoryContextStore
from axio_transport_openai import OpenAITransport, OPENAI_MODELS
from axio_tui_rag import IndexFiles, SemanticSearch
from axio.tool import Tool
tools = [
Tool(name="index_files", description=IndexFiles.__doc__ or "", handler=IndexFiles),
Tool(name="semantic_search", description=SemanticSearch.__doc__ or "", handler=SemanticSearch),
]
agent = Agent(
system="You are a code assistant. Index files before searching.",
tools=tools,
transport=OpenAITransport(api_key="sk-...", model=OPENAI_MODELS["gpt-4o"]),
)
Tools
index_files
Index one or more files into the vector store for later semantic search. Files are chunked and embedded. Re-indexing a file replaces its old chunks.
Parameters:
paths: list[str]— file paths to index (relative to cwd)
semantic_search
Search the vector store for chunks semantically similar to a query. Returns ranked excerpts with file paths and line numbers.
Parameters:
query: str— natural-language search querylimit: int(default: 5) — number of results to return
Plugin registration
[project.entry-points."axio.tools"]
index_files = "axio_tui_rag:IndexFiles"
semantic_search = "axio_tui_rag:SemanticSearch"
Part of the axio ecosystem
axio · axio-tui · axio-tui-guards
License
MIT
Metadata
Release files for axio-tui-rag 0.6.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| axio_tui_rag-0.6.1.tar.gz | 100.7 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| axio_tui_rag-0.6.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 109.8 kB
Release files / axio_tui_rag-0.6.1.tar.gz
| Download URL | axio_tui_rag-0.6.1.tar.gz |
|---|---|
| Size | 100.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
84a1fc4f860091e383fe8bb804f1cb9c7f12b85457ab481eda29d7074ab2ae0c
|
|
BLAKE2b-256 checksum How to use checksums |
7be86df52ea3fdd6300d9cafc42f274c4767c2ffdee1fb83cf2c9432d7dec84e
|
| 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 16, 2026.
Transparency logRelease files / axio_tui_rag-0.6.1-py3-none-any.whl
| Download URL | axio_tui_rag-0.6.1-py3-none-any.whl |
|---|---|
| Size | 9.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
2a17651bdfc69da5fe6ba250fee37598e05c1afed563f596c9dc4253ab5e4b86
|
|
BLAKE2b-256 checksum How to use checksums |
e9fe875b96a3b04ebadd8dee2f59fb7ce3f0449f8e7e0171d6e0289c7ab338a1
|
| 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 16, 2026.
Transparency log