UTCP In-Memory Embeddings Search Plugin
This plugin registers the in-memory embedding-based semantic search strategy with UTCP 1.0 via entry points.
Installation
pip install utcp-in-mem-embeddings
Optionally, for high-quality embeddings:
pip install "utcp-in-mem-embeddings[embedding]"
Or install the required dependencies directly:
pip install "sentence-transformers>=2.2.0" "torch>=1.9.0"
Why are sentence-transformers and torch needed?
While the plugin works without these packages (using a simple character frequency-based fallback), installing them provides significant benefits:
-
Enhanced Semantic Understanding: The
sentence-transformerspackage provides pre-trained models that convert text into high-quality vector embeddings, capturing the semantic meaning of text rather than just keywords. -
Better Search Results: With these packages installed, the search can understand conceptual similarity between queries and tools, even when they don't share exact keywords.
-
Performance: The default model (all-MiniLM-L6-v2) offers a good balance between quality and performance for semantic search applications.
-
Fallback Mechanism: Without these packages, the plugin automatically falls back to a simpler text similarity method, which works but with reduced accuracy.
How it works
When installed, this package exposes an entry point under utcp.plugins so the UTCP core can auto-discover and register the in_mem_embeddings strategy.
The embeddings are cached in memory for improved performance during repeated searches.
Metadata
Release files for utcp-in-mem-embeddings 1.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| utcp_in_mem_embeddings-1.0.0.tar.gz | 10.5 kB | Without provenance | Details for utcp_in_mem_embeddings-1.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| utcp_in_mem_embeddings-1.0.0-py3-none-any.whl | Python 3 | none | any | Details for utcp_in_mem_embeddings-1.0.0-py3-none-any.whl |
Total release size: 16.5 kB
Release files / utcp_in_mem_embeddings-1.0.0.tar.gz
| Download URL | utcp_in_mem_embeddings-1.0.0.tar.gz |
|---|---|
| Size | 10.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
257153929a1dcc91499f3a4747f6e42796a7f0f691afa0376827a353500f4213
|
|
BLAKE2b-256 checksum How to use checksums |
7f864e80638aa6fee1a3ca6dd3ad8ace1cd99ff3cf4ffec55e621d467cd2991b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.5
|
Release files / utcp_in_mem_embeddings-1.0.0-py3-none-any.whl
| Download URL | utcp_in_mem_embeddings-1.0.0-py3-none-any.whl |
|---|---|
| Size | 6.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f6df81736df8810bacd3b0d602583b3ab14c3e549e6477f8be77ab071d16da73
|
|
BLAKE2b-256 checksum How to use checksums |
ed329684260b0023bcdce1a542423103ccbae2f196a6bf30b01c865af30dc063
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.5
|
Security for utcp-in-mem-embeddings 1.0.0
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.