diff --git a/docs/concepts/prompt_adaptation.md b/docs/concepts/prompt_adaptation.md
index 790f54104..68b90dc1b 100644
--- a/docs/concepts/prompt_adaptation.md
+++ b/docs/concepts/prompt_adaptation.md
@@ -39,7 +39,6 @@ Create a sample prompt using `Prompt` class.
 ```{code-block} python
 
 from langchain.chat_models import ChatOpenAI
-from ragas.llms import LangchainLLMWrapper
 from ragas.llms.prompt import Prompt
 
 noun_extractor = Prompt(
@@ -55,7 +54,6 @@ examples=[{
 )
 
 openai_model = ChatOpenAI(model_name="gpt-4")
-openai_model = LangchainLLMWrapper(llm=openai_model)
 ```
 
 Prompt adaption is done using the `.adapt` method: 
diff --git a/docs/howtos/customisations/gcp-vertexai.ipynb b/docs/howtos/customisations/gcp-vertexai.ipynb
index 70722c34a..55fab1c5a 100644
--- a/docs/howtos/customisations/gcp-vertexai.ipynb
+++ b/docs/howtos/customisations/gcp-vertexai.ipynb
@@ -111,9 +111,7 @@
     "]\n",
     "```\n",
     "\n",
-    "By default Ragas uses `ChatOpenAI` for evaluations, lets swap that out with `ChatVertextAI`. We also need to change the embeddings used for evaluations for `OpenAIEmbeddings` to `VertextAIEmbeddings` for metrices that need it, which in our case is `answer_relevancy`.\n",
-    "\n",
-    "Now in order to use the new `ChatVertextAI` llm instance with Ragas metrics, you have to create a new instance of `RagasLLM` using the `ragas.llms.LangchainLLM` wrapper. Its a simple wrapper around langchain that make Langchain LLM/Chat instances compatible with how Ragas metrics will use them."
+    "By default Ragas uses `ChatOpenAI` for evaluations, lets swap that out with `ChatVertextAI`. We also need to change the embeddings used for evaluations for `OpenAIEmbeddings` to `VertextAIEmbeddings` for metrices that need it, which in our case is `answer_relevancy`."
    ]
   },
   {
@@ -125,7 +123,6 @@
    "source": [
     "import google.auth\n",
     "from langchain.chat_models import ChatVertexAI\n",
-    "from ragas.llms import LangchainLLM\n",
     "from langchain.embeddings import VertexAIEmbeddings\n",
     "\n",
     "\n",
@@ -136,11 +133,8 @@
     "# authenticate to GCP\n",
     "creds, _ = google.auth.default(quota_project_id=\"tmp-project-404003\")\n",
     "# create Langchain LLM and Embeddings\n",
-    "chat = ChatVertexAI(credentials=creds)\n",
-    "vertextai_embeddings = VertexAIEmbeddings(credentials=creds)\n",
-    "\n",
-    "# create a wrapper around it\n",
-    "ragas_vertexai_llm = LangchainLLM(chat)"
+    "ragas_vertexai_llm = ChatVertexAI(credentials=creds)\n",
+    "vertextai_embeddings = VertexAIEmbeddings(credentials=creds)"
    ]
   },
   {
diff --git a/docs/howtos/customisations/llms.ipynb b/docs/howtos/customisations/llms.ipynb
index d1f34504e..7f96d1a78 100644
--- a/docs/howtos/customisations/llms.ipynb
+++ b/docs/howtos/customisations/llms.ipynb
@@ -188,7 +188,7 @@
    "id": "c9ddf74a-9830-4e1a-a4dd-7e5ec17a71e4",
    "metadata": {},
    "source": [
-    "Now lets create an Langchain llm instance and wrap it with `LangchainLLMWrapper` class. Because vLLM can run in OpenAI compatibilitiy mode, we can use the `ChatOpenAI` class as it is with small tweaks."
+    "Now lets create an Langchain llm instance. Because vLLM can run in OpenAI compatibilitiy mode, we can use the `ChatOpenAI` class as it is with small tweaks."
    ]
   },
   {
@@ -199,7 +199,6 @@
    "outputs": [],
    "source": [
     "from langchain_openai.chat_models import ChatOpenAI\n",
-    "from ragas.llms.base import LangchainLLMWrapper\n",
     "\n",
     "inference_server_url = \"http://localhost:8080/v1\"\n",
     "\n",