ColiVara is a State of the Art Retrieval API - with a delightful developer experience.
Make your RAG application
10x Smarter
ColiVara has
state of the art retrieval performance
on both
text and
visual documents.
Whether it's complex
financial reports,technical diagrams, or data-rich tables, our
advanced vision models
see and understand your documents just like a human would.
Say goodbye to broken layouts, missed context, and OCR limitations.
colivara.com
pip install colivara_py
# Import and initialize ColiVara
from colivara_py import ColiVara
rag_client = ColiVara()
# Upload a document to the default collection
document = rag_client.upsert_document(
name="sample_document",
url="https://example.com/sample.pdf",
metadata={"author": "John Doe"}
)
results = rag_client.search(query="machine learning")
print(results) # top 3 pages with the most relevant information
Colivara is a state of the art retrieval API that allows you to store, search, and retrieve documents based on their visual embeddings.
Documents are visually rich structures that convey information through text, as well as tables, figures, page layouts, and charts. While legacy document retrieval systems exhibit good performance on query-to-text matching, they struggle to pass visual cues efficiently to large language models, hindering their performance on practical document retrieval applications such as Retrieval Augmented Generation.
It is a web-first implementation of the ColPali paper using ColQwen2 as the LLM model. It works exactly like RAG from the end-user standpoint - but using vision models instead of chunking and text-processing for documents.
State of the Art Retrieval. Delightful developer experience
Plans that match your needs
No matter
how many documents you have - our pricing is simple, transparent and adapts to
the size of your usage.
Create your next project with ColiVara
