-
I am trying to integrate LigthRag in AutoGen, but I am not sucessfull. I can get it answer the RAG question, but either it gets into an infinit loop, or if I add max_consecutive_auto_reply=1 it only …
-
1. Model Setup (LegalBERT for Retrieval, T5 for Generation)
-
Good Day. Adjusting chunk size is an existing feature, but other than that... what are some methodologies that can optimize RAG? I think it would be good to have various such methodologies in the dial…
-
The current illustration of RAG in the README.md is not sophisticated enough for audiences to understand correctly.
Draw a figure just like component diagram using draw.io.
-
As a user I can run a sample which shows how to perform RAG against a PDF document (SK learn document).
- See citations for any answers provided
- I can click on citation links and be brought to t…
-
首先是要介绍 vx: cartman-ca 发起的
## Multi-stack RAG项目
- 通过Naive RAG/Memo RAG/Graph RAG，建立的一套具备案例循症能力建议，以及科普性知识能力的RAG系统，突破了AI能否给出诊疗意见及合理性的边界，虽然还需时日，但是期待这个项目为AI技术普惠，带来全新的能力阶段。xyb也跟上。
---
然后是这个
## 针…
-
### Proposal for PDF Injection Feature to Address RAG Vulnerabilities
- **Tool**: Garak
- **Issue Reference**: [Indirect injection probes focused on RAG vulnerabilities #888](https://github.com/leon…
-
### Is there an existing issue for the same bug?
- [X] I have checked the existing issues.
### RAGFlow workspace code commit ID
000000
### RAGFlow image version
0.13
### Other environment inform…
-
**Is your feature request related to a problem? Please describe.**
If you are building a RAG pipeline, then the indexing pipeline is of course an essential part of it.
You usually don't run the ind…
-
### Documentation Issue Description
This page made it seem easy to go create a RAG CLI with a local model (e.g., Llama)
https://docs.llamaindex.ai/en/stable/getting_started/starter_tools/rag_cli/
…