Skip to main content

Cached Sentence Transformer

PostgreSQL-backed embedding cache for SentenceTransformers.

This package provides a small wrapper that caches computed sentence embeddings in a Postgres table keyed by a stable hash of (model, normalize flag, text), so repeated runs can reuse stored vectors instead of recomputing them.

Installation

pip install cached-sentence-transformer

Quickstart

from cached_sentence_transformer import CachedSentenceTransformer

st = CachedSentenceTransformer(
    model_name_or_path="sentence-transformers/all-MiniLM-L6-v2",
    pg_dsn="host=localhost port=5432 dbname=mydb user=myuser password=mypassword",
)

emb = st.encode(["hello", "world"], normalize_embeddings=True)
st.close()

Environment-based DSN

If you do not pass pg_dsn, the wrapper will attempt to build it from environment variables (auto loads environment variables in the .env file in the current working directory) and will fail fast if any are missing:

  • PSQL_HOST_NAME
  • PSQL_PORT
  • PSQL_DBNAME
  • PSQL_USER
  • PSQL_PASSWORD

Release files for cached-sentence-transformer 0.1.0

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

Source distribution (sdist)

Source distribution for cached-sentence-transformer 0.1.0
File Size Uploaded
cached_sentence_transformer-0.1.0.tar.gz 15.2 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for cached-sentence-transformer 0.1.0
File Interpreter ABI Platform
cached_sentence_transformer-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 27.0 kB

Release files / cached_sentence_transformer-0.1.0.tar.gz

Download URL cached_sentence_transformer-0.1.0.tar.gz
Size 15.2 kB
Tags Source
SHA-256 checksum
How to use checksums
cbd742fb1a4dc3d13df30c1267580d5f29b4ccb861ea018666fdc1eddff24962
BLAKE2b-256 checksum
How to use checksums
52e8d622bbe4eac5d126418036d45cadde60f59e253483cf4acf6f2dd59f91cf
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.0

Release files / cached_sentence_transformer-0.1.0-py3-none-any.whl

Download URL cached_sentence_transformer-0.1.0-py3-none-any.whl
Size 11.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
9aeb67dadc5aecd8432cb5903f7ff84bb26161ae6c20c97c7109807b48e9e80c
BLAKE2b-256 checksum
How to use checksums
8dec9f88a46f551c2f56e3b22026bfab60304afd8bfeac6b981bea187f86eb40
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.0

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files

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