docs: add notebook external-evaluation-pipelines

Author: marcklingen

cookbook/_routes.json

@@ -118,5 +118,9 @@
   {
     "notebook": "integration_ollama.ipynb",
     "docsPath": "docs/integrations/ollama"
+  },
+  {
+    "notebook": "example_external_evaluation_pipelines.ipynb",
+    "docsPath": "docs/scores/external-evaluation-pipelines"
   }
 ]

cookbook/example_external_evaluation_pipelines.ipynb

@@ -4,5 +4,6 @@
   "annotation": "Annotation in UI",
   "user-feedback": "User Feedback",
   "model-based-evals": "Model-based Evaluation",
+  "external-evaluation-pipelines": "External Evaluation Pipelines",
   "custom": "Custom via SDKs/API"
 }

pages/docs/scores/_meta.json

@@ -104,10 +104,14 @@ Langfuse ->> User: Analyze evaluation scores via UI & API
 
 You can run your own model-based evals on data in Langfuse by fetching traces from Langfuse (e.g. via the Python SDK) and then adding evaluation results as [`scores`](/docs/scores) back to the traces in Langfuse. This gives you full flexibility to run various eval libraries on your production data and discover which work well for your use case.
 
-Popular evaluation packages:
+The example notebook is a good template to get started with building your own evaluation pipeline.
 
-- OpenAI Evals
-- Langchain Evaluators ([Example notebook](/guides/cookbook/evaluation_with_langchain))
-- RAGAS for RAG applications ([Example notebook](/guides/cookbook/evaluation_of_rag_with_ragas))
-- UpTrain evals ([Example notebook](/guides/cookbook/evaluation_with_uptrain))
-- Whylabs Langkit
+import { FileCode, BookOpen } from "lucide-react";
+
+<Cards num={2}>
+  <Card
+    title="Example: External Evaluation Pipeline"
+    href="/docs/scores/external-evaluation-pipelines"
+    icon={<FileCode />}
+  />
+</Cards>

pages/docs/scores/custom.mdx

@@ -27,8 +27,8 @@ Langfuse supports all forms of evaluation methods due to its open architecture a
 
 There are two ways to run model-based evaluations in Langfuse:
 
-- [Via the Langfuse UI (beta)](/docs/scores/model-based-evals#ui)
-- [Via external evaluation pipelines](/docs/scores/model-based-evals#evaluation-pipeline)
+- [Via the Langfuse UI (beta)](/docs/scores/model-based-evals)
+- [Via external evaluation pipelines](/docs/scores/external-evaluation-pipelines)
 
 ### 2. Manual Annotation (in UI)
 
@@ -48,9 +48,9 @@ Learn how to configure and utilize `scores` in Langfuse to assess quality, accur
 
 import { FileCode, BookOpen } from "lucide-react";
 
-<Cards num={3}>
+<Cards num={2}>
   <Card
-    title="Getting Started with Langfuse Scoring"
+    title="Getting Started with Langfuse Evaluation"
     href="/docs/scores/getting-started"
     icon={<FileCode />}
   />