# cmem-plugin-pgvector
[![poetry][poetry-shield]][poetry-link] [![ruff][ruff-shield]][ruff-link] [![mypy][mypy-shield]][mypy-link] [![copier][copier-shield]][copier]
Store embedding vectors into a Postgres vector store.
This plugin consumes the costumable entity's paths ```embedding```, ```text``` and ```metadata``` as following:
- The text path contain the text used to generate the embeddings, default ```text```.
- The embedding path contain the embedding representation of the text, default ```embedding```.
- The metadata path contain the information that will be associated with the embedding, default all paths.
[![eccenca Corporate Memory][cmem-shield]][cmem-link]
## Use
Interact with Large Language Models.
This is a plugin for [eccenca](https://eccenca.com) [Corporate Memory](https://documentation.eccenca.com).
You can install it with the [cmemc](https://eccenca.com/go/cmemc) command line
clients like this:
```
cmemc admin workspace python install cmem-plugin-llm
```
### Parameters
- ```collection_name```: The name of the collection where the embeddings are going to be stored, default ```my_collection```
- ```user```:the database user
- ```password```: the database password
- ```host```: the databse host, i.e. locahost
- ```port```: the database port, default ```5432```
- ```database```: the name of the database
- ```pre_delete_collection```: boolean parameter indicating if the collection should be cleanse before insertion, default ```false```
- ```embedding_path```: output path that will contain the generated embedding, default ```embedding```
- ```text_path```: path containing the text used for genereting the embedding, default ```text```
- ```metadata_paths```: paths from the entity that will be stored along with the embedding, default all paths
[cmem-link]: https://documentation.eccenca.com
[cmem-shield]: https://img.shields.io/endpoint?url=https://dev.documentation.eccenca.com/badge.json
[poetry-link]: https://python-poetry.org/
[poetry-shield]: https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json
[ruff-link]: https://docs.astral.sh/ruff/
[ruff-shield]: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json&label=Code%20Style
[mypy-link]: https://mypy-lang.org/
[mypy-shield]: https://www.mypy-lang.org/static/mypy_badge.svg
[copier]: https://copier.readthedocs.io/
[copier-shield]: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/copier-org/copier/master/img/badge/badge-grayscale-inverted-border-purple.json
Raw data
{
"_id": null,
"home_page": null,
"name": "cmem-plugin-pgvector",
"maintainer": "Edgard Marx",
"docs_url": null,
"requires_python": "<4.0,>=3.11",
"maintainer_email": "edgard.marx@eccenca.com",
"keywords": "eccenca Corporate Memory, plugin",
"author": "eccenca GmbH",
"author_email": "cmempy-developer@eccenca.com",
"download_url": "https://files.pythonhosted.org/packages/77/61/49b9f6719b630ce4e20502bcc16ba05b36640150eedfc941d4436d86fd41/cmem_plugin_pgvector-0.5.0.tar.gz",
"platform": null,
"description": "# cmem-plugin-pgvector\n\n[![poetry][poetry-shield]][poetry-link] [![ruff][ruff-shield]][ruff-link] [![mypy][mypy-shield]][mypy-link] [![copier][copier-shield]][copier] \n\nStore embedding vectors into a Postgres vector store.\n\nThis plugin consumes the costumable entity's paths ```embedding```, ```text``` and ```metadata``` as following:\n\n - The text path contain the text used to generate the embeddings, default ```text```.\n - The embedding path contain the embedding representation of the text, default ```embedding```.\n - The metadata path contain the information that will be associated with the embedding, default all paths.\n\n[![eccenca Corporate Memory][cmem-shield]][cmem-link]\n\n## Use\n\nInteract with Large Language Models.\n\nThis is a plugin for [eccenca](https://eccenca.com) [Corporate Memory](https://documentation.eccenca.com).\n\nYou can install it with the [cmemc](https://eccenca.com/go/cmemc) command line\nclients like this:\n\n```\ncmemc admin workspace python install cmem-plugin-llm\n```\n\n### Parameters\n\n- ```collection_name```: The name of the collection where the embeddings are going to be stored, default ```my_collection```\n- ```user```:the database user\n- ```password```: the database password\n- ```host```: the databse host, i.e. locahost\n- ```port```: the database port, default ```5432```\n- ```database```: the name of the database\n- ```pre_delete_collection```: boolean parameter indicating if the collection should be cleanse before insertion, default ```false```\n- ```embedding_path```: output path that will contain the generated embedding, default ```embedding```\n- ```text_path```: path containing the text used for genereting the embedding, default ```text```\n- ```metadata_paths```: paths from the entity that will be stored along with the embedding, default all paths\n\n[cmem-link]: https://documentation.eccenca.com\n[cmem-shield]: https://img.shields.io/endpoint?url=https://dev.documentation.eccenca.com/badge.json\n[poetry-link]: https://python-poetry.org/\n[poetry-shield]: https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json\n[ruff-link]: https://docs.astral.sh/ruff/\n[ruff-shield]: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json&label=Code%20Style\n[mypy-link]: https://mypy-lang.org/\n[mypy-shield]: https://www.mypy-lang.org/static/mypy_badge.svg\n[copier]: https://copier.readthedocs.io/\n[copier-shield]: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/copier-org/copier/master/img/badge/badge-grayscale-inverted-border-purple.json\n\n",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "Store embedding vectors into a Postgres vector store.",
"version": "0.5.0",
"project_urls": null,
"split_keywords": [
"eccenca corporate memory",
" plugin"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "2e41c4df88774ce737be2350a002f78a6e33fbe0028c875f96f6e78c1c427f23",
"md5": "3b0d40c9036dbc62a937c06fbbbfabc6",
"sha256": "8d8c189a7f90074ff4baea19886d9a03e577fe82a4db2e45d5b0b1632d975603"
},
"downloads": -1,
"filename": "cmem_plugin_pgvector-0.5.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "3b0d40c9036dbc62a937c06fbbbfabc6",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.11",
"size": 13782,
"upload_time": "2025-02-20T15:53:18",
"upload_time_iso_8601": "2025-02-20T15:53:18.917598Z",
"url": "https://files.pythonhosted.org/packages/2e/41/c4df88774ce737be2350a002f78a6e33fbe0028c875f96f6e78c1c427f23/cmem_plugin_pgvector-0.5.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "776149b9f6719b630ce4e20502bcc16ba05b36640150eedfc941d4436d86fd41",
"md5": "4ecad23ec2606805418b03c1ca1801c2",
"sha256": "76ba3dd28c2053327a0dbb8469ca36d970fd5eef6ed994807bc8b4f9bed82e48"
},
"downloads": -1,
"filename": "cmem_plugin_pgvector-0.5.0.tar.gz",
"has_sig": false,
"md5_digest": "4ecad23ec2606805418b03c1ca1801c2",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.11",
"size": 13865,
"upload_time": "2025-02-20T15:53:20",
"upload_time_iso_8601": "2025-02-20T15:53:20.866747Z",
"url": "https://files.pythonhosted.org/packages/77/61/49b9f6719b630ce4e20502bcc16ba05b36640150eedfc941d4436d86fd41/cmem_plugin_pgvector-0.5.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-02-20 15:53:20",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "cmem-plugin-pgvector"
}
JSON