A package to interact with vectors DB
Project description
pdf2vectors
Description
This package provides a convenient way to interact with a vectors database using Pinecone, allowing you to upload data in the form of vectors to your Pinecone index.
Installation
You can install the package via pip:
pip install pdf2vectors
Usage
from pdf2vectors import PineconeUploader, read_pdf, upsert_files
PineconeUploader(api_key="YOUR_PINECONE_API_KEY", host="YOUR_PINECONE_HOST")
directory = "YOUR_PDF_FILE_PATH"
texts = read_pdf(directory)
response = upsert_files(texts)
print(response)
Features
Simplified Interaction: Easily upload vectorized data to your Pinecone index with just a few lines of code. Automatic Vectorization: The package automatically vectorizes text content extracted from PDF files. Flexible Configuration: Customize the package by providing your Pinecone API key and host.
Contributing
Contributions are welcome! Feel free to submit issues or pull requests to enhance the functionality or fix any bugs in the package. Your contributions help improve the overall quality of the package and make it more valuable for the community.
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
Built Distribution
Hashes for pdf2vectors-0.1.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 1bbdb33c406d171fa69baaaef7ae49b60dc2dbaf0c78988ac880530539834662 |
|
MD5 | fdf20c86f812592433cef115b6f8894f |
|
BLAKE2b-256 | f3aa1c5cb484413e7aca2332b48cf4077039db8be926aa1c3e3f0399a09b15df |