Swarmauri Vectorstore FS
A Swarmauri community vector store that indexes filesystem trees for BM25F retrieval over file paths, file names, extensions, chunk identity, and file content.
Features
- Filesystem-aware retrieval with weighted BM25F fields
- Chunk, file, and chunk-plus-file indexing modes
- Stable chunk identity metadata for global, path-level, and file-level chunk numbering
- CLI for ad hoc lexical search over source trees and document corpora
- No embedding vocabulary dependency for query handling
Installation
pip install swarmauri_vectorstore_fs
Usage
from swarmauri_vectorstore_fs import FsVectorStore
store = FsVectorStore(root_path=".", mode="chunk")
store.build_index()
results = store.retrieve("vector store registration", top_k=3)
for document in results:
print(document.id, document.metadata["relative_path"])
CLI
fsvs --root . query --query "vector store registration" --top-k 5
To inspect a specific retrieved document:
fsvs --root . show --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_fs 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| swarmauri_vectorstore_fs-0.1.0.tar.gz | 9.4 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| swarmauri_vectorstore_fs-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 19.5 kB
Release files / swarmauri_vectorstore_fs-0.1.0.tar.gz
| Download URL | swarmauri_vectorstore_fs-0.1.0.tar.gz |
|---|---|
| Size | 9.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
05c4c485a5d70e85251dc6c6ac5be1b9c8d2de0121f590dcbb85a32fd83d5955
|
|
BLAKE2b-256 checksum How to use checksums |
59b8a1699f58d70a52e684fd0c99bba5385419dfd2c366b02b3035d34a9cd55d
|
| 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_fs-0.1.0-py3-none-any.whl
| Download URL | swarmauri_vectorstore_fs-0.1.0-py3-none-any.whl |
|---|---|
| Size | 10.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
3f60c6b294a38fad6547975360bcefb95deced177d75b79daf7d14843500fcc3
|
|
BLAKE2b-256 checksum How to use checksums |
ec2526811c1071ebc974c314460fc50a562556ea26a08502e679f8ad3ecb4c96
|
| 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}
|