A local vector search engine built for speed and scalability
Project description
Eric Search
A local vector search engine built for speed and scalability.
- Fast: we use two-level IVF to effectively scale to millions of documents.
- EricRanker(): powered by a cross-encoder model that extracts relevant information from the top documents.
- Accelerated compute: compatible with both MPS and CUDA.
- Easy to use: only a few lines of code are needed to train new datasets
- Lightweight: simple to install and run with a single Python script.
- Integrated with Hugging Face's Hub.
- Transferable: zip a single folder to move an entire dataset.
Install
pip install ericsearch
Maintainers
- Eric Fillion Lead Maintainer
- Ted Brownlow Maintainer
Contributing
We are currently not accepting contributions.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
ericsearch-0.0.1.tar.gz
(23.8 kB
view details)
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 ericsearch-0.0.1.tar.gz.
File metadata
- Download URL: ericsearch-0.0.1.tar.gz
- Upload date:
- Size: 23.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
31d03163be264a3bcef4840bbb51f84a2cb7d081210c84f7d83e31d54ea3960f
|
|
| MD5 |
1a1a5442ca8cb3e7bb6c63f7e1583bcb
|
|
| BLAKE2b-256 |
0237e0b27e92aeb3598f363831b403799d0074a56aa869303683db1da2e2e27e
|
File details
Details for the file ericsearch-0.0.1-py3-none-any.whl.
File metadata
- Download URL: ericsearch-0.0.1-py3-none-any.whl
- Upload date:
- Size: 29.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
8e69468aa318be0e97cf4427edef8a5ab59dd126490f8ee4eca49a3f7e314e28
|
|
| MD5 |
7b7f05e94785b4280d1edcbfd07fb727
|
|
| BLAKE2b-256 |
3edb9a946ded81e7d665395ca0f131a75acd76c2e38b170d21f10e66118529f2
|
