Hey everyone,
I’ve been working on a side project called Bilgecan — a self-hosted, local-first AI platform that uses Ollama as the LLM runtime.
What can you do with Bilgecan?
- Use local LLM models via Ollama to run privacy-friendly AI prompts and chat without sending your data to third parties.
- With RAG (Retrieval-Augmented Generation), you can feed your own files into a knowledge base and enrich AI outputs with your private data.
- Define asynchronous AI tasks to run long operations (document analysis, report generation, large text processing, image analysis, etc.) in the background.
- Use the file processing pipeline to run asynchronous AI tasks over many files automatically.
- With the Workspace structure, you can share AI prompts and tasks with your team in a collaborative environment.
I’d really appreciate feedback from the community.
Repo: https://github.com/mokszr/bilgecan
YouTube demo video:
Kayıtlar
){kind=link}
0 Yorumlar