-
Would be awesome to embed a vector DB like something like open-webui does that indexes all of the documents in the Obsidian vault so you can talk with the model about any document.
-
**Description**
Add a simple vectorDB rag to enhance memory.
**Use Case**
It would be possible to retrieve information from outside of the context window
sotwi updated
2 weeks ago
-
/kind feature
Ref https://arxiv.org/pdf/2404.01037.pdf
> Auto-RAG: The idea of automatically optimizing RAG systems, akin to Auto-ML’s approach
in traditional machine learning, presents a signi…
-
-
I knew about hybrid retrieval. Recently I've heard BM25 mentioned a lot, let's try to use that. The question is how well ObjectBox will support that.
-
I really don't want to promote llm/genai approaches, but if I have to, it may be interesting to use notebooks as the corpus in a RAG system.
As well as interestingness in the RAG chunking strategie…
-
# Feature Request
**Problem Description:**
When integrating Open-webui with agents or assistants (such as [Assistants Code Interpreter](https://platform.openai.com/docs/assistants/tools/code-inter…
-
-
This came to my mind while attending https://cloudonair.withgoogle.com/events/key-prompt-engineering-techniques-with-anthropics-claude-on-vertex-ai
In an agentic AI setup when RAGs are implemented …
-
We should implement a RAG use case taking an imaginary company as an example and include it as a tool for our agent setup. The following RAG components should be setup on an OpenShift cluster:
- [x…