feat(docs): add support for reusable snippets (#1414)

- Replaced LLM selection blocks with `choose_evaluvator_llm.md` snippet.
- Simplifies updates and reuse across documentation.

Author: zodwick

docs/extra/components/choose_evaluvator_llm.md

@@ -0,0 +1,39 @@
+
+=== "OpenAI"
+    This guide utilizes OpenAI for running some metrics, so ensure you have your OpenAI key ready and available in your environment.
+    
+    ```python
+    import os
+    os.environ["OPENAI_API_KEY"] = "your-openai-key"
+    ```
+    Wrapp the LLMs in `LangchainLLMWrapper`
+    ```python
+    from ragas.llms import LangchainLLMWrapper
+    from langchain_openai import ChatOpenAI
+    evaluator_llm = LangchainLLMWrapper(ChatOpenAI(model="gpt-4o"))
+    ```
+
+
+=== "AWS Bedrock"
+    First you have to set your AWS credentials and configurations
+
+    ```python
+    config = {
+        "credentials_profile_name": "your-profile-name",  # E.g "default"
+        "region_name": "your-region-name",  # E.g. "us-east-1"
+        "model_id": "your-model-id",  # E.g "anthropic.claude-v2"
+        "model_kwargs": {"temperature": 0.4},
+    }
+    ```
+    define you LLMs
+    ```python
+    from langchain_aws.chat_models import BedrockChat
+    from ragas.llms import LangchainLLMWrapper
+    evaluator_llm = LangchainLLMWrapper(BedrockChat(
+        credentials_profile_name=config["credentials_profile_name"],
+        region_name=config["region_name"],
+        endpoint_url=f"https://bedrock-runtime.{config['region_name']}.amazonaws.com",
+        model_id=config["model_id"],
+        model_kwargs=config["model_kwargs"],
+    ))
+    ```

docs/getstarted/rag_evaluation.md

@@ -41,42 +41,10 @@ Since all of the metrics we have chosen are LLM-based metrics, we need to choose
 
 ### Choosing evaluator LLM
 
-=== "OpenAI"
-    This guide utilizes OpenAI for running some metrics, so ensure you have your OpenAI key ready and available in your environment.
-    ```python
-    import os
-    os.environ["OPENAI_API_KEY"] = "your-openai-key"
-    ```
-    Wrapp the LLMs in `LangchainLLMWrapper`
-    ```python
-    from ragas.llms import LangchainLLMWrapper
-    from langchain_openai import ChatOpenAI
-    evaluator_llm = LangchainLLMWrapper(ChatOpenAI(model="gpt-4o"))
-    ```
-
-
-=== "AWS Bedrock"
-    First you have to set your AWS credentials and configurations
-    ```python
-    config = {
-        "credentials_profile_name": "your-profile-name",  # E.g "default"
-        "region_name": "your-region-name",  # E.g. "us-east-1"
-        "model_id": "your-model-id",  # E.g "anthropic.claude-v2"
-        "model_kwargs": {"temperature": 0.4},
-    }
-    ```
-    define you LLMs
-    ```python
-    from langchain_aws.chat_models import BedrockChat
-    from ragas.llms import LangchainLLMWrapper
-    evaluator_llm = LangchainLLMWrapper(BedrockChat(
-        credentials_profile_name=config["credentials_profile_name"],
-        region_name=config["region_name"],
-        endpoint_url=f"https://bedrock-runtime.{config['region_name']}.amazonaws.com",
-        model_id=config["model_id"],
-        model_kwargs=config["model_kwargs"],
-    ))
-    ```
+--8<--
+choose_evaluvator_llm.md
+--8<--
+
 
 ### Running Evaluation
 

docs/getstarted/rag_testset_generation.md

@@ -10,8 +10,8 @@ For the sake of this tutorial we will use sample documents from this [repository
 git clone https://huggingface.co/datasets/explodinggradients/Sample_Docs_Markdown
 ```
 
-
 ### Load documents
+
 Now we will load the documents from the sample dataset using `DirectoryLoader`, which is one of document loaders from [langchain_community](https://python.langchain.com/v0.1/docs/modules/data_connection/document_loaders/). You may also use any loaders from [llama_index](https://docs.llamaindex.ai/en/stable/understanding/loading/llamahub/)
 
 ```python
@@ -22,52 +22,12 @@ loader = DirectoryLoader(path, glob="**/*.md")
 docs = loader.load()
 ```
 
-
 ### Choose your LLM
 
 You may choose to use any [LLM of your choice]()
-
-=== "OpenAI"
-    This guide utilizes OpenAI for running some metrics, so ensure you have your OpenAI key ready and available in your environment.
-    
-    ```python
-    import os
-    os.environ["OPENAI_API_KEY"] = "your-openai-key"
-    ```
-    Wrapp the LLMs in `LangchainLLMWrapper`
-    ```python
-    from ragas.llms import LangchainLLMWrapper
-    from langchain_openai import ChatOpenAI
-    generator_llm = LangchainLLMWrapper(ChatOpenAI(model="gpt-4o"))
-    ```
-
-
-
-
-=== "AWS Bedrock"
-    First you have to set your AWS credentials and configurations
-    
-    ```python
-    config = {
-        "credentials_profile_name": "your-profile-name",  # E.g "default"
-        "region_name": "your-region-name",  # E.g. "us-east-1"
-        "model_id": "your-model-id",  # E.g "anthropic.claude-v2"
-        "model_kwargs": {"temperature": 0.4},
-    }
-    ```
-    define you LLMs
-    ```python
-    from langchain_aws.chat_models import BedrockChat
-    from ragas.llms import LangchainLLMWrapper
-    generator_llm = LangchainLLMWrapper(BedrockChat(
-        credentials_profile_name=config["credentials_profile_name"],
-        region_name=config["region_name"],
-        endpoint_url=f"https://bedrock-runtime.{config['region_name']}.amazonaws.com",
-        model_id=config["model_id"],
-        model_kwargs=config["model_kwargs"],
-    ))
-    ```
-
+--8<--
+choose_evaluvator_llm.md
+--8<--
 
 ### Generate Testset
 
@@ -83,7 +43,7 @@ dataset = generator.generate_with_langchain_docs(docs, test_size=10)
 ### Export
 
 You may now export and inspect the generated testset.
-    
+
 ```python
 dataset.to_pandas()
-```
+```

mkdocs.yml

@@ -102,7 +102,6 @@ markdown_extensions:
       pygments_lang_class: true
   - admonition
   - pymdownx.inlinehilite
-  - pymdownx.snippets
   - pymdownx.details
   - pymdownx.tabbed:
       alternate_style: true
@@ -118,6 +117,8 @@ markdown_extensions:
         - name: mermaid
           class: mermaid
           format: !!python/name:pymdownx.superfences.fence_code_format
+  - pymdownx.snippets:
+      base_path: ['./docs/extra/components/']
 
 # Extra CSS
 extra_css: