OneContext
The fastest way to ship enterprise-grade RAG pipelines to millions of users.
Ingest any file format
OneContext provides support for a broad range of file formats, handling ingestion and, OCR and pre-processing. Whether you have data stored as PDFs, Word documents, PowerPoint presentations, or image files, OneContext can easily parse it.
1from onecontext import OneContext
2
3oc = OneContext()
4context = oc.Context("my_context")
5
6context.add_files(["deck.pptx", "agreement.pdf", "draft.docx"])Hybrid Search out of the box
Leverage hybrid semantic and keyword search with flexible metadata filters to get the most relevant results.
1from onecontext import OneContext
2
3oc = OneContext()
4
5context = oc.Context("my_context")
6
7chunks = context.search(
8 "my query",
9 semantic_weight=0.7,
10 full_text_weight=0.3,
11 metadata_filters={
12 "tag": {"$eq": "file_1_tag"},
13 "author": {"$in": ["author1", "author2"]}
14 }
15)
16Let us focus on RAG so that you dont have to
Focus on your domain expertise and app development; let us handle the rest.
Don't just take our word for it
OneContext is like the Vercel of RAG pipelines. Super easy iteration and deployment. No other product makes it this easy to deploy RAG in production!
Wow, this is fantastic. This makes deployment so much simpler. This is going to save our devops team so much time and frustration.
Integrate directly into your stack.
OneContext integrates with you choice of language models
