deepset-ai
diff --git a/‎tutorials/35_Evaluating_RAG_Pipelines.ipynb
+1-1 b/‎tutorials/35_Evaluating_RAG_Pipelines.ipynb
+1-1
diff --git a/‎tutorials/img/tutorial35_rag.png
25.3 KB b/‎tutorials/img/tutorial35_rag.png
25.3 KB
@@ -48,7 +48,7 @@
         "\n",
         "To evaluate a full RAG pipeline, we have to evaluate each of these steps in isolation, as well as a full unit. While retrieval can in some cases be evaluated with some statistical metrics that require labels, it's not a straight-forward task to do the same for the generation step. Instead, we often rely on model-based metrics to evaluate the generation step, where an LLM is used as the 'evaluator'.\n",
         "\n",
-        "![Steps or RAG](img/tutorial35_rag.png)"
+        "![Steps or RAG](https://raw.githubusercontent.com/deepset-ai/haystack-tutorials/main/tutorials/img/tutorial35_rag.png)"
       ]
     },
     {
Original file line number	Diff line number	Diff line change
`@@ -48,7 +48,7 @@`
`48`	`48`	`"\n",`
`49`	`49`	`"To evaluate a full RAG pipeline, we have to evaluate each of these steps in isolation, as well as a full unit. While retrieval can in some cases be evaluated with some statistical metrics that require labels, it's not a straight-forward task to do the same for the generation step. Instead, we often rely on model-based metrics to evaluate the generation step, where an LLM is used as the 'evaluator'.\n",`
`50`	`50`	`"\n",`
`51`		`- "![Steps or RAG](img/tutorial35_rag.png)"`
	`51`	`+ "![Steps or RAG](https://raw.githubusercontent.com/deepset-ai/haystack-tutorials/main/tutorials/img/tutorial35_rag.png)"`
`52`	`52`	`]`
`53`	`53`	`},`
`54`	`54`	`{`