| Name | vectrix JSON |
| Version |
0.0.75
JSON |
| download |
| home_page | None |
| Summary | An assistant helping you to index webpages into structured datasets. |
| upload_time | 2024-08-30 17:19:58 |
| maintainer | None |
| docs_url | None |
| author | Ben Selleslagh |
| requires_python | <3.13,>=3.11 |
| license | MIT |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# PAGINX
  
Paginx is an innovative Python-based project that leverages the power of Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) to provide intelligent question-answering capabilities for any given website. By simply entering a website URL, users can interact with an AI assistant that can answer questions and provide insights based on the content of the website.
## Setting Up a PostgreSQL instance with the pgvector Extension
To store the uploaded data for later retrieval (for example during RAG), you need to set up a PostgreSQL database with the pgvector extension enabled. This chapter guides you through the steps to install PostgreSQL, enable the pgvector extension, create a new database, and store the connection string as a URL. Alternatively, you can use hosted PostgreSQL instances provided by many cloud providers.
### 1. Install PostgreSQL and pgvector Extension
**Using Docker**
1. Pull the PostgreSQL image with pgvector:
```sh
docker pull ankane/pgvector
```
2. Run the PostgreSQL container with the pgvector extension enabled:
```sh
docker run -d --name paginx -e POSTGRES_PASSWORD=mysecretpassword -p 5432:5432 -e PG_EXTENSIONS="pgvector" ankane/pgvector
```
**Manual Installation**
If you prefer to install PostgreSQL and pgvector manually, please follow the instructions provided in the official documentation:
- [PostgreSQL Installation](https://www.postgresql.org/download/)
- [pgvector Installation](https://github.com/ankane/pgvector)
### 2. Create a New Database
Once you have PostgreSQL running with pgvector enabled, you need to create a new database for our application. You can do this by connecting to your PostgreSQL instance and executing the following SQL commands
Create a new database named `paginx` (you can choose a different name if you prefer):
```sql
CREATE DATABASE paginx;
```
Connect to the `paginx` database:
```sql
\c paginx;
```
Enable the pgvector extension for the `paginx` database:
```sql
CREATE EXTENSION IF NOT EXISTS vector;
```
### 3. Store the Connection String
After creating the database, you need to store the connection string as an enviroment variable named ```database_url```. This connection string will be used by paginx to connect to the database.
The envrioment variable can be set using the following command:
```sh
export database_url="postgresql://postgres:mysecretpassword@localhost/paginx"
```
### 4. Using a Hosted PostgreSQL Instance
If you prefer to use a hosted PostgreSQL instance, you can create a new database and store the connection string as a URL. Make sure to enable the pgvector extension for the hosted database.
Raw data
{
"_id": null,
"home_page": null,
"name": "vectrix",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.13,>=3.11",
"maintainer_email": null,
"keywords": null,
"author": "Ben Selleslagh",
"author_email": "ben@dataframe.be",
"download_url": "https://files.pythonhosted.org/packages/25/26/52b07db1b3548d7e767670eb413b861836e0c84a8e6b63ec387309fdb79f/vectrix-0.0.75.tar.gz",
"platform": null,
"description": "# PAGINX\n\n  \n\n Paginx is an innovative Python-based project that leverages the power of Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) to provide intelligent question-answering capabilities for any given website. By simply entering a website URL, users can interact with an AI assistant that can answer questions and provide insights based on the content of the website.\n\n## Setting Up a PostgreSQL instance with the pgvector Extension\nTo store the uploaded data for later retrieval (for example during RAG), you need to set up a PostgreSQL database with the pgvector extension enabled. This chapter guides you through the steps to install PostgreSQL, enable the pgvector extension, create a new database, and store the connection string as a URL. Alternatively, you can use hosted PostgreSQL instances provided by many cloud providers.\n\n### 1. Install PostgreSQL and pgvector Extension\n**Using Docker**\n1.\tPull the PostgreSQL image with pgvector:\n```sh\ndocker pull ankane/pgvector\n```\n\n2.\tRun the PostgreSQL container with the pgvector extension enabled:\n```sh\ndocker run -d --name paginx -e POSTGRES_PASSWORD=mysecretpassword -p 5432:5432 -e PG_EXTENSIONS=\"pgvector\" ankane/pgvector\n```\n\n**Manual Installation**\n\nIf you prefer to install PostgreSQL and pgvector manually, please follow the instructions provided in the official documentation:\n\n- [PostgreSQL Installation](https://www.postgresql.org/download/)\n- [pgvector Installation](https://github.com/ankane/pgvector)\n\n### 2. Create a New Database\nOnce you have PostgreSQL running with pgvector enabled, you need to create a new database for our application. You can do this by connecting to your PostgreSQL instance and executing the following SQL commands\n\n\nCreate a new database named `paginx` (you can choose a different name if you prefer):\n```sql\nCREATE DATABASE paginx;\n```\n\nConnect to the `paginx` database:\n```sql\n\\c paginx;\n```\n\nEnable the pgvector extension for the `paginx` database:\n```sql\nCREATE EXTENSION IF NOT EXISTS vector;\n```\n\n### 3. Store the Connection String\nAfter creating the database, you need to store the connection string as an enviroment variable named ```database_url```. This connection string will be used by paginx to connect to the database.\n\n\nThe envrioment variable can be set using the following command:\n```sh\nexport database_url=\"postgresql://postgres:mysecretpassword@localhost/paginx\"\n```\n\n### 4. Using a Hosted PostgreSQL Instance\nIf you prefer to use a hosted PostgreSQL instance, you can create a new database and store the connection string as a URL. Make sure to enable the pgvector extension for the hosted database.\n\n\n\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "An assistant helping you to index webpages into structured datasets.",
"version": "0.0.75",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "3afbc9a30ec964056a9933a97dec6fd93d9169b4fbf86ebdfe184d967076a2d0",
"md5": "93eedb70b216e9d03978c6acf0f3c389",
"sha256": "eed0a73e2228285abd628ff2f8989c30f5f3c54b4eaa54dd24d919e6035b7c4c"
},
"downloads": -1,
"filename": "vectrix-0.0.75-py3-none-any.whl",
"has_sig": false,
"md5_digest": "93eedb70b216e9d03978c6acf0f3c389",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.13,>=3.11",
"size": 36412,
"upload_time": "2024-08-30T17:19:57",
"upload_time_iso_8601": "2024-08-30T17:19:57.195508Z",
"url": "https://files.pythonhosted.org/packages/3a/fb/c9a30ec964056a9933a97dec6fd93d9169b4fbf86ebdfe184d967076a2d0/vectrix-0.0.75-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "252652b07db1b3548d7e767670eb413b861836e0c84a8e6b63ec387309fdb79f",
"md5": "8faddd29852411b6509c2c02a6d5e6d8",
"sha256": "af26be1e6705f5f5c210ff8c0aec9f7ea408fc6567cfe92576763aa67e8685c9"
},
"downloads": -1,
"filename": "vectrix-0.0.75.tar.gz",
"has_sig": false,
"md5_digest": "8faddd29852411b6509c2c02a6d5e6d8",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.13,>=3.11",
"size": 29081,
"upload_time": "2024-08-30T17:19:58",
"upload_time_iso_8601": "2024-08-30T17:19:58.134571Z",
"url": "https://files.pythonhosted.org/packages/25/26/52b07db1b3548d7e767670eb413b861836e0c84a8e6b63ec387309fdb79f/vectrix-0.0.75.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-08-30 17:19:58",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "vectrix"
}
