Local retriever search for your use
Project description
Retriever
To setup your own local search you can now use this repo.
Install
Recommended to use a virtual environment using venv -
$ python -m venv new_env
$ source new_env/bin/activate
For installing from the github repo -
$ pip install -e .
For installing from the pip -
$ pip install retriever-search
Search server and frontend run
>>> from retriever_search import search_server
>>> from retriever_search import frontend_app as fp
>>> fp.run_frontend()
>>> search_server.run_search_server('path_to_folder', 'save_json_path', device='cpu')
Vizualisation run
Currently run from the git repo
$ cd retriever
>>> from retriever_search import viz_server as vs
>>> vs.run_viz_server()
Where to access the frontend
Access via the following URL - http://127.0.0.1:7860 This URL would work for your local setup only
Tickets
1.0.0
- Add lightweight embedding model support as flag in launcher
- Remove HTML requirement for plotly visualization
- Make LDA visualization update
- Add model quantized
Project details
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
retriever_search-0.2.7.tar.gz
(10.5 kB
view hashes)
Built Distribution
Close
Hashes for retriever_search-0.2.7-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 9864e869fa97e2fa2c65c475b14d939f1ade98054ac6af1f0a36ed2e6f45fb1c |
|
MD5 | bceea7c9ca533c053ab0a07e0fb7117a |
|
BLAKE2b-256 | 7316800dccadc589ed3c6af651e912dc092774b98a9c2b81bb83b0a97c221ae8 |