diff --git a/chains.py b/chains.py
index 9ad10f40..cc3c00b9 100644
--- a/chains.py
+++ b/chains.py
@@ -29,7 +29,7 @@
 def load_embedding_model(embedding_model_name: str, logger=BaseLogger(), config={}):
     if embedding_model_name == "ollama":
         embeddings = OllamaEmbeddings(
-            base_url=config["ollama_base_url"], model="llama2"
+            base_url=config["ollama_base_url"], model="llama3"
         )
         dimension = 4096
         logger.info("Embedding: Using Ollama")
diff --git a/docker-compose.yml b/docker-compose.yml
index 7faafe52..6148c20f 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -24,7 +24,7 @@ services:
       dockerfile: pull_model.Dockerfile
     environment:
       - OLLAMA_BASE_URL=${OLLAMA_BASE_URL-http://host.docker.internal:11434}
-      - LLM=${LLM-llama2}
+      - LLM=${LLM-llama3}
     networks:
       - net
     tty: true
@@ -105,7 +105,7 @@ services:
       - OPENAI_API_KEY=${OPENAI_API_KEY-}      
       - GOOGLE_API_KEY=${GOOGLE_API_KEY-}
       - OLLAMA_BASE_URL=${OLLAMA_BASE_URL-http://host.docker.internal:11434}
-      - LLM=${LLM-llama2}
+      - LLM=${LLM-llama3}
       - EMBEDDING_MODEL=${EMBEDDING_MODEL-sentence_transformer}
       - LANGCHAIN_ENDPOINT=${LANGCHAIN_ENDPOINT-"https://api.smith.langchain.com"}
       - LANGCHAIN_TRACING_V2=${LANGCHAIN_TRACING_V2-false}
@@ -144,7 +144,7 @@ services:
       - OPENAI_API_KEY=${OPENAI_API_KEY-}
       - GOOGLE_API_KEY=${GOOGLE_API_KEY-}
       - OLLAMA_BASE_URL=${OLLAMA_BASE_URL-http://host.docker.internal:11434}
-      - LLM=${LLM-llama2}
+      - LLM=${LLM-llama3}
       - EMBEDDING_MODEL=${EMBEDDING_MODEL-sentence_transformer}
       - LANGCHAIN_ENDPOINT=${LANGCHAIN_ENDPOINT-"https://api.smith.langchain.com"}
       - LANGCHAIN_TRACING_V2=${LANGCHAIN_TRACING_V2-false}
@@ -185,7 +185,7 @@ services:
       - OPENAI_API_KEY=${OPENAI_API_KEY}
       - GOOGLE_API_KEY=${GOOGLE_API_KEY}  
       - OLLAMA_BASE_URL=${OLLAMA_BASE_URL-http://host.docker.internal:11434}
-      - LLM=${LLM-llama2}
+      - LLM=${LLM-llama3}
       - EMBEDDING_MODEL=${EMBEDDING_MODEL-sentence_transformer}
       - LANGCHAIN_ENDPOINT=${LANGCHAIN_ENDPOINT-"https://api.smith.langchain.com"}
       - LANGCHAIN_TRACING_V2=${LANGCHAIN_TRACING_V2-false}
diff --git a/env.example b/env.example
index 88e33cc3..a7953ed7 100644
--- a/env.example
+++ b/env.example
@@ -1,15 +1,15 @@
 #*****************************************************************
 # LLM and Embedding Model
 #*****************************************************************
-LLM=llama2 #or any Ollama model tag, gpt-4, gpt-3.5, or claudev2
+LLM=llama3 #or any Ollama model tag, gpt-4, gpt-3.5, or claudev2
 EMBEDDING_MODEL=sentence_transformer #or google-genai-embedding-001 openai, ollama, or aws
 
 #*****************************************************************
 # Neo4j
 #*****************************************************************
-#NEO4J_URI=neo4j://database:7687
-#NEO4J_USERNAME=neo4j
-#NEO4J_PASSWORD=password
+NEO4J_URI=neo4j://database:7687
+NEO4J_USERNAME=neo4j
+NEO4J_PASSWORD=password
 
 #*****************************************************************
 # Langchain
diff --git a/readme.md b/readme.md
index 28fba3d4..6d2cbdc5 100644
--- a/readme.md
+++ b/readme.md
@@ -14,7 +14,7 @@ Available variables:
 | NEO4J_URI              | neo4j://database:7687              | REQUIRED - URL to Neo4j database                                        |
 | NEO4J_USERNAME         | neo4j                              | REQUIRED - Username for Neo4j database                                  |
 | NEO4J_PASSWORD         | password                           | REQUIRED - Password for Neo4j database                                  |
-| LLM                    | llama2                             | REQUIRED - Can be any Ollama model tag, or gpt-4 or gpt-3.5 or claudev2 |
+| LLM                    | llama3                             | REQUIRED - Can be any Ollama model tag, or gpt-4 or gpt-3.5 or claudev2 |
 | EMBEDDING_MODEL        | sentence_transformer               | REQUIRED - Can be sentence_transformer, openai, aws, ollama or google-genai-embedding-001|
 | AWS_ACCESS_KEY_ID      |                                    | REQUIRED - Only if LLM=claudev2 or embedding_model=aws                  |
 | AWS_SECRET_ACCESS_KEY  |                                    | REQUIRED - Only if LLM=claudev2 or embedding_model=aws                  |
diff --git a/running_on_wsl.md b/running_on_wsl.md
index 473ec50e..439df724 100644
--- a/running_on_wsl.md
+++ b/running_on_wsl.md
@@ -29,10 +29,10 @@ After the activation enter into the WSL with the command `wsl` and type `docker`
     - To list the downloaded model: `ollama list`. This command could lead to:
     ```sh
     NAME            ID              SIZE    MODIFIED       
-    llama2:latest   7da22eda89ac    3.8 GB  22 minutes ago
+    llama3:latest   7da22eda89ac    3.8 GB  22 minutes ago
     ```
-    - (OPTIONAL) To remove model: `ollama rm llama2`
-    - To run the ollama on WSL: `ollama run llama2`
+    - (OPTIONAL) To remove model: `ollama rm llama3`
+    - To run the ollama on WSL: `ollama run llama3`
 
 3. clone the repo
 4. cd into the repo and enter wsl
@@ -40,4 +40,4 @@ After the activation enter into the WSL with the command `wsl` and type `docker`
 
 # Run the stack on MAC:
 
-On MAC you can follow this tutorial: https://collabnix.com/getting-started-with-genai-stack-powered-with-docker-langchain-neo4j-and-ollama/
\ No newline at end of file
+On MAC you can follow this tutorial: https://collabnix.com/getting-started-with-genai-stack-powered-with-docker-langchain-neo4j-and-ollama/