llama-index-vector-stores-mnestic
A LlamaIndex vector store backed by mnestic — an embedded graph + vector + full-text database (a maintained fork of CozoDB). Retrieval is hybrid: dense (HNSW) + keyword (full-text) fused with Reciprocal Rank Fusion, in one call.
mnestic is a maintained fork of CozoDB; it is not the official CozoDB. Original design credit belongs to Ziyang Hu and the Cozo Project Authors.
pip install llama-index-vector-stores-mnestic
Use 0.2.1 or newer. It validates relation, column, index, distance, and dtype identifiers and coerces numeric HNSW settings before constructing CozoScript; earlier releases interpolated those configuration values directly.
from llama_index.core import VectorStoreIndex, StorageContext, Document
from llama_index.vector_stores.mnestic import MnesticVectorStore
vector_store = MnesticVectorStore(dim=1536, engine="sqlite", path="mydocs.db")
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
[Document(text="the cat sat on the mat")],
storage_context=storage_context,
)
nodes = index.as_retriever(similarity_top_k=4).retrieve("feline")
dim must match your embedding model's dimension. query runs hybrid search when
the query carries text (the usual index path), otherwise vector-only.
Engine pass-through: graph legs and more
Extra keyword arguments flow from the retriever to the engine's hybrid query via
vector_store_kwargs. That includes graph_legs — fuse graph proximity into
the ranking alongside the dense and keyword legs, in the same single call:
retriever = index.as_retriever(
similarity_top_k=4,
vector_store_kwargs={"graph_legs": [{
"edge_relation": "links", "from_col": "src", "to_col": "dst",
"seeds": ["doc-1"], "max_hops": 2, "label": "graph",
}]},
)
MnesticRetriever(..., search_kwargs={...}) forwards the same way, and so do
extra_lists, vector_k, fts_k, rrf_k, and future engine keys — no adapter
release needed when the engine grows new knobs.
License
Mozilla Public License 2.0.
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file llama_index_vector_stores_mnestic-0.2.1.tar.gz.
File metadata
- Download URL: llama_index_vector_stores_mnestic-0.2.1.tar.gz
- Upload date:
- Size: 7.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/7.0.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ab192be1f85abe3b04f841ca53e4291927477d5910ae27d1a642100c07df8890
|
|
| MD5 |
1887e0e94c52e90e3402ea0511c65db6
|
|
| BLAKE2b-256 |
3fa0660769de332debd2809bed218be645abcf50805fa7bf93f8ad2cf445c5ec
|
Provenance
The following attestation bundles were made for llama_index_vector_stores_mnestic-0.2.1.tar.gz:
Publisher:
python-publish.yml on shuruheel/mnestic
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
llama_index_vector_stores_mnestic-0.2.1.tar.gz -
Subject digest:
ab192be1f85abe3b04f841ca53e4291927477d5910ae27d1a642100c07df8890 - Sigstore transparency entry: 2387283808
- Sigstore integration time:
-
Permalink:
shuruheel/mnestic@5ef1aa44c99b34aef31a159a907b7b53d2c81c2a -
Branch / Tag:
refs/tags/py-v0.14.0 - Owner: https://github.com/shuruheel
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
python-publish.yml@5ef1aa44c99b34aef31a159a907b7b53d2c81c2a -
Trigger Event:
push
-
Statement type:
File details
Details for the file llama_index_vector_stores_mnestic-0.2.1-py3-none-any.whl.
File metadata
- Download URL: llama_index_vector_stores_mnestic-0.2.1-py3-none-any.whl
- Upload date:
- Size: 7.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/7.0.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
38c881cfd063bd6ae5b8eb87fcc569af1506b45e05fc413e7bae08e3ba3756f4
|
|
| MD5 |
5245f4ab95bf0ea8e0c0f262c2af8285
|
|
| BLAKE2b-256 |
e44231d59653addab6f617c4c55694a6a9b99c847d4bca2ac26707e1038cc239
|
Provenance
The following attestation bundles were made for llama_index_vector_stores_mnestic-0.2.1-py3-none-any.whl:
Publisher:
python-publish.yml on shuruheel/mnestic
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
llama_index_vector_stores_mnestic-0.2.1-py3-none-any.whl -
Subject digest:
38c881cfd063bd6ae5b8eb87fcc569af1506b45e05fc413e7bae08e3ba3756f4 - Sigstore transparency entry: 2387283901
- Sigstore integration time:
-
Permalink:
shuruheel/mnestic@5ef1aa44c99b34aef31a159a907b7b53d2c81c2a -
Branch / Tag:
refs/tags/py-v0.14.0 - Owner: https://github.com/shuruheel
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
python-publish.yml@5ef1aa44c99b34aef31a159a907b7b53d2c81c2a -
Trigger Event:
push
-
Statement type:
