From 46021b95ab6c10ab64ed360de62d3094adef5bb3 Mon Sep 17 00:00:00 2001 From: Oluwafemi Adadayo Date: Thu, 24 Sep 2026 16:09:56 +0100 Subject: [PATCH 1/2] docs(readme): note ragas optional extra install for --evaluator ragas The RAGAS backend is not installed by default. The evaluator package declares `ragas` as an optional extra, so readers following the peer comparison section would hit an import error when running `rag-forge audit --evaluator ragas` without first installing `rag-forge-evaluator[ragas]`. Spell out the install step inline. --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 5892060..17ec08a 100644 --- a/README.md +++ b/README.md @@ -129,7 +129,7 @@ There are great tools in this space. Here's an honest look at where each fits. **Peer strengths worth knowing:** -- **RAGAS** has deeper metric research and a large community. RAG-Forge's evaluator supports RAGAS as a backend — run `rag-forge audit --evaluator ragas` to use it directly. +- **RAGAS** has deeper metric research and a large community. RAG-Forge's evaluator supports RAGAS as a backend — install the optional extra (`pip install rag-forge-evaluator[ragas]`) and run `rag-forge audit --evaluator ragas` to use it directly. - **LangChain Eval** has the broadest ecosystem of integrations if you're already invested in LangChain. - **Giskard** has a strong general-purpose ML testing story beyond RAG. From a1854cda0f517a5fc4c6356b1de82324b823a65a Mon Sep 17 00:00:00 2001 From: Oluwafemi Adadayo Date: Thu, 24 Sep 2026 17:02:40 +0100 Subject: [PATCH 2/2] docs(readme): quote ragas extra specifier for zsh In zsh, an unquoted `[ragas]` is treated as a filename glob. When it matches no file, zsh aborts with "no matches found" before pip runs. Quoting the specifier makes the documented install command work in bash, zsh, and fish alike. --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 17ec08a..a245d3c 100644 --- a/README.md +++ b/README.md @@ -129,7 +129,7 @@ There are great tools in this space. Here's an honest look at where each fits. **Peer strengths worth knowing:** -- **RAGAS** has deeper metric research and a large community. RAG-Forge's evaluator supports RAGAS as a backend — install the optional extra (`pip install rag-forge-evaluator[ragas]`) and run `rag-forge audit --evaluator ragas` to use it directly. +- **RAGAS** has deeper metric research and a large community. RAG-Forge's evaluator supports RAGAS as a backend — install the optional extra (`pip install 'rag-forge-evaluator[ragas]'`) and run `rag-forge audit --evaluator ragas` to use it directly. - **LangChain Eval** has the broadest ecosystem of integrations if you're already invested in LangChain. - **Giskard** has a strong general-purpose ML testing story beyond RAG.