diff --git a/README.md b/README.md
index e72686a24..a09e30636 100644
--- a/README.md
+++ b/README.md
@@ -98,7 +98,7 @@ import asyncio
 from neo4j import GraphDatabase
 from neo4j_graphrag.embeddings import OpenAIEmbeddings
 from neo4j_graphrag.experimental.pipeline.kg_builder import SimpleKGPipeline
-from neo4j_graphrag.llm.openai_llm import OpenAILLM
+from neo4j_graphrag.llm import OpenAILLM
 
 NEO4J_URI = "neo4j://localhost:7687"
 NEO4J_USERNAME = "neo4j"
@@ -149,6 +149,9 @@ asyncio.run(kg_builder.run_async(text=text))
 driver.close()
 ```
 
+> Warning: In order to run this code, the `openai` Python package needs to be installed: `pip install "neo4j_graphrag[openai]"`
+
+
 Example knowledge graph created using the above script:
 
 ![Example knowledge graph](https://raw.githubusercontent.com/neo4j/neo4j-graphrag-python/fd276af0069e4dd1769255d358793cc96e299bf3/images/kg_construction.svg)
diff --git a/docs/source/user_guide_kg_builder.rst b/docs/source/user_guide_kg_builder.rst
index ea91ec2cc..edc89f609 100644
--- a/docs/source/user_guide_kg_builder.rst
+++ b/docs/source/user_guide_kg_builder.rst
@@ -357,6 +357,11 @@ can be omitted (the parser will automatically import from `neo4j_graphrag.llm`).
 For custom implementations, the full path must be explicitly specified,
 for example: `my_package.my_llm.MyLLM`.
 
+.. warning::
+
+    Check the :ref:`installation` section to make sure you have the required dependencies installed when using an LLM.
+
+
 Defining an Embedder
 --------------------
 
@@ -800,7 +805,7 @@ It can be used in this way:
     from neo4j_graphrag.experimental.components.entity_relation_extractor import (
         LLMEntityRelationExtractor,
     )
-    from neo4j_graphrag.llm.openai import OpenAILLM
+    from neo4j_graphrag.llm import OpenAILLM
 
     extractor = LLMEntityRelationExtractor(
         llm=OpenAILLM(
@@ -814,6 +819,10 @@ It can be used in this way:
     await extractor.run(chunks=TextChunks(chunks=[TextChunk(text="some text")]))
 
 
+.. warning::
+
+    Using `OpenAILLM` requires the `openai` Python client. You can install it with `pip install "neo4j_graphrag[openai]"`.
+
 .. warning::
 
     The `LLMEntityRelationExtractor` works better if `"response_format": {"type": "json_object"}` is in the model parameters.
@@ -834,13 +843,7 @@ This behaviour can be changed by using the `on_error` flag in the `LLMEntityRela
     )
 
     extractor = LLMEntityRelationExtractor(
-        llm=OpenAILLM(
-            model_name="gpt-4o",
-            model_params={
-                "max_tokens": 1000,
-                "response_format": {"type": "json_object"},
-            },
-        ),
+        # ...
         on_error=OnError.RAISE,
     )
 
diff --git a/docs/source/user_guide_rag.rst b/docs/source/user_guide_rag.rst
index 8074eef77..f569505ec 100644
--- a/docs/source/user_guide_rag.rst
+++ b/docs/source/user_guide_rag.rst
@@ -56,10 +56,9 @@ In practice, it's done with only a few lines of code:
     print(response.answer)
 
 
-.. note::
+.. warning::
 
-    In order to run this code, the `openai` Python package needs to be installed:
-    `pip install openai`
+    Using `OpenAILLM` requires the `openai` Python client. You can install it with `pip install "neo4j_graphrag[openai]"`.
 
 
 The following sections provide more details about how to customize this code.
@@ -108,7 +107,7 @@ to learn more about the configuration.
 .. note::
 
     In order to run this code, the `openai` Python package needs to be installed:
-    `pip install openai`
+    `pip install "neo4j_graphrag[openai]"`
 
 
 See :ref:`azureopenaillm`.
@@ -134,7 +133,7 @@ To use VertexAI, instantiate the `VertexAILLM` class:
 .. note::
 
     In order to run this code, the `google-cloud-aiplatform` Python package needs to be installed:
-    `pip install google-cloud-aiplatform`
+    `pip install "neo4j_grpahrag[vertexai]"`
 
 
 See :ref:`vertexaillm`.
@@ -160,7 +159,7 @@ To use Anthropic, instantiate the `AnthropicLLM` class:
 .. note::
 
     In order to run this code, the `anthropic` Python package needs to be installed:
-    `pip install anthropic`
+    `pip install "neo4j_graphrag[anthropic]"`
 
 See :ref:`anthropicllm`.
 
@@ -184,7 +183,7 @@ To use MistralAI, instantiate the `MistralAILLM` class:
 .. note::
 
     In order to run this code, the `mistralai` Python package needs to be installed:
-    `pip install mistralai`
+    `pip install "neo4j_graphrag[mistralai]"`
 
 See :ref:`mistralaillm`.
 
@@ -209,7 +208,7 @@ To use Cohere, instantiate the `CohereLLM` class:
 .. note::
 
     In order to run this code, the `cohere` Python package needs to be installed:
-    `pip install cohere`
+    `pip install "neo4j_graphrag[cohere]"`
 
 
 See :ref:`coherellm`.
@@ -630,7 +629,7 @@ Weaviate Retrievers
 .. note::
 
     In order to import this retriever, the Weaviate Python client must be installed:
-    `pip install weaviate-client`
+    `pip install "neo4j_graphrag[weaviate]"`
 
 
 .. code:: python
@@ -663,7 +662,7 @@ Pinecone Retrievers
 .. note::
 
     In order to import this retriever, the Pinecone Python client must be installed:
-    `pip install pinecone-client`
+    `pip install "neo4j_graphrag[pinecone]"`
 
 
 .. code:: python
@@ -691,7 +690,7 @@ Qdrant Retrievers
 .. note::
 
     In order to import this retriever, the Qdrant Python client must be installed:
-    `pip install qdrant-client`
+    `pip install "neo4j_graphrag[qdrant]"`
 
 
 .. code:: python
@@ -787,7 +786,7 @@ LLMs can be different.
 
     from neo4j import GraphDatabase
     from neo4j_graphrag.retrievers import Text2CypherRetriever
-    from neo4j_graphrag.llm.openai import OpenAILLM
+    from neo4j_graphrag.llm import OpenAILLM
 
     URI = "neo4j://localhost:7687"
     AUTH = ("neo4j", "password")
@@ -796,7 +795,7 @@ LLMs can be different.
     driver = GraphDatabase.driver(URI, auth=AUTH)
 
     # Create LLM object
-    llm = OpenAILLM(model_name="gpt-3.5-turbo")
+    llm = OpenAILLM(model_name="gpt-4o")
 
     # (Optional) Specify your own Neo4j schema
     neo4j_schema = """
@@ -833,6 +832,10 @@ LLMs can be different.
     print(retriever.search(query_text=query_text))
 
 
+.. warning::
+
+    Using `OpenAILLM` requires the `openai` Python client. You can install it with `pip install "neo4j_graphrag[openai]"`.
+
 .. note::
 
     Since we are not performing any similarity search (vector index), the Text2Cypher
diff --git a/examples/build_graph/simple_kg_builder_from_pdf.py b/examples/build_graph/simple_kg_builder_from_pdf.py
index 05ac69892..f7ad683da 100644
--- a/examples/build_graph/simple_kg_builder_from_pdf.py
+++ b/examples/build_graph/simple_kg_builder_from_pdf.py
@@ -15,7 +15,7 @@
 from neo4j_graphrag.experimental.pipeline.kg_builder import SimpleKGPipeline
 from neo4j_graphrag.experimental.pipeline.pipeline import PipelineResult
 from neo4j_graphrag.llm import LLMInterface
-from neo4j_graphrag.llm.openai_llm import OpenAILLM
+from neo4j_graphrag.llm import OpenAILLM
 
 # Neo4j db infos
 URI = "neo4j://localhost:7687"
diff --git a/examples/build_graph/simple_kg_builder_from_text.py b/examples/build_graph/simple_kg_builder_from_text.py
index 288a21ab5..29a5cfc5b 100644
--- a/examples/build_graph/simple_kg_builder_from_text.py
+++ b/examples/build_graph/simple_kg_builder_from_text.py
@@ -19,7 +19,7 @@
     RelationInputType,
 )
 from neo4j_graphrag.llm import LLMInterface
-from neo4j_graphrag.llm.openai_llm import OpenAILLM
+from neo4j_graphrag.llm import OpenAILLM
 
 logging.basicConfig()
 logging.getLogger("neo4j_graphrag").setLevel(logging.DEBUG)