Skip to main content

Swarmauri Logo

PyPI - Python Version PyPI - License PyPI - swarmauri_vectorstore_git


Swarmauri Vectorstore Git

A Swarmauri community vector store that indexes Git repositories for semantic retrieval over commits and git log style records.

Features

  • Index scopes:
    • head: commits reachable from HEAD
    • ref: commits reachable from a specific branch, tag, or revision
    • all_refs: commits reachable from every ref in the repository
  • Document kinds:
    • commit: normalized commit metadata and changed-path text
    • log: rendered git log --stat style text
  • Pure git CLI backend, so there is no hard dependency on pygit2
  • Convenience CLI with colored logs for ad hoc retrieval
  • Default CLI behavior targets the current repo (.) and indexes all refs via --ref all

Installation

pip install swarmauri_vectorstore_git

Usage

from swarmauri_standard.documents.Document import Document
from swarmauri_vectorstore_git import GitVectorStore

store = GitVectorStore(
    repo_path=".",
    scope="all_refs",
    document_kinds=("commit", "log"),
)

store.build_index()
results = store.retrieve("oauth token bug", top_k=3)

for document in results:
    print(document.metadata["oid"], document.metadata["kind"])
    print(document.content[:200])

CLI

gitvs query --query "memory leak fix" --top-k 5

To inspect a specific retrieved document:

gitvs show --ref feature/my-branch --document-id <document-id>

Want to help?

If you want to contribute to swarmauri-sdk, read up on our guidelines for contributing.

Metadata

Release files for swarmauri_vectorstore_git 0.10.0

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

Source distribution (sdist)

Source distribution for swarmauri_vectorstore_git 0.10.0
File Size Uploaded
swarmauri_vectorstore_git-0.10.0.tar.gz 6.8 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for swarmauri_vectorstore_git 0.10.0
File Interpreter ABI Platform
swarmauri_vectorstore_git-0.10.0-py3-none-any.whl Python 3 none any Details

Total release size: 14.8 kB

Release files / swarmauri_vectorstore_git-0.10.0.tar.gz

Download URL swarmauri_vectorstore_git-0.10.0.tar.gz
Size 6.8 kB
Tags Source
SHA-256 checksum
How to use checksums
f68b4420f1b5b6d39e8f138a7866fc42ced1c6c5a283527510955777a826fba4
BLAKE2b-256 checksum
How to use checksums
0ae465808b83d1d6883298d8a53e77b8bc6bfaf5c9abbf247bc3f61cf458770c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.11.8 {"installer":{"name":"uv","version":"0.11.8","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / swarmauri_vectorstore_git-0.10.0-py3-none-any.whl

Download URL swarmauri_vectorstore_git-0.10.0-py3-none-any.whl
Size 7.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
f6fa0a6c0c92e9ca9c02ea31bc2cb108c235f3eff595b44456bed6fd5fa09386
BLAKE2b-256 checksum
How to use checksums
cecf7505c6d99267394db572bb0a24ca8d842893fe4097e9a7639161b48b18f2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.11.8 {"installer":{"name":"uv","version":"0.11.8","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
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