R2R
R2R copied to clipboard
The all-in-one solution for RAG. Build, scale, and deploy state of the art Retrieval-Augmented Generation applications
There is a `logging.logging_path` setting for the `local` logging provider: https://github.com/SciPhi-AI/R2R/blob/210e11249c2695993be4ddf8433b30f42894d02c/r2r/base/logging/kv_logger.py#L29 However, it is not documented at . It should be added to the documentation. On a related note, are...
can you explain what in backend you are using
When using search_file_knowledge or get_file_content ragTools in rag agent, the results contains answers from documents and collections outside the specified collections and documents in searchSettings config filters. Doesn't this completely...
Iam using R2R version 3.6.1 with ollama - llama3.1 model. I have added a pdf document to the R2R using the custom ingestion_mode. When iam using the rag stream iam...
**Describe the bug** ``` R2R git:(main) sudo docker compose -f docker/compose.full.yaml --profile postgres up -d [+] Running 13/13 ✔ unstructured Pulled 3.8s ✔ af302e5c37e9 Already exists 0.0s ✔ 499051ac08b3 Already...
We want the RAG response to include the rectangle coordinates (top, left, width, and height in the 0–1 range) of the relevant chunk of a citation, so we can highlight...
Steps to Reproduce: 1. Set the task prompt with variables {date}, {max_tool_context_length}, and {document_context} (likely unrelated). 2. Set mode to rag. 3. Provide the agent access to the following tools:...
**Is your feature request related to a problem? Please describe.** There's no easy way to ingest an HTML page, e.g. a blog post on a highly relevant topic. **Describe the...