diff --git a/README.md b/README.md
index 1b723da45..f1e092da3 100644
--- a/README.md
+++ b/README.md
@@ -46,6 +46,7 @@ Each layer has a certain strength of communication inbuilt
 ✅ `GitHub actions` configured\
 ✅ `Vale.sh` configured at PR level\
 ✅ `Pre-commit hooks` configured for code linting/formatting\
+✨ [LangChain](https://python.langchain.com/) Basics & workflows\
 ✅ Environment management via [pixi](https://prefix.dev/)\
 ✅ Reading data from online sources using [intake](https://github.com/intake/intake)\
 ✅ Sample pipeline built using [Dagster](https://github.com/dagster-io/dagster)\
@@ -54,7 +55,6 @@ Each layer has a certain strength of communication inbuilt
 ✅ Web UI build on [Flask](https://flask.palletsprojects.com/en/3.0.x/) \
 ✅ Web UI re-done and expanded with [FastHTML](https://docs.fastht.ml/)\
 ✅ Leverage AI models to analyse data [GitHub AI models Beta](https://docs.github.com/en/github-models/prototyping-with-ai-models)
-✨ LangChain integration
 
 ### ☕️ Quickly getting started with DataJourney
 
diff --git a/analytics_framework/langchain/hello_world_lc.py b/analytics_framework/langchain/hello_world_lc.py
new file mode 100644
index 000000000..dae16fe52
--- /dev/null
+++ b/analytics_framework/langchain/hello_world_lc.py
@@ -0,0 +1,39 @@
+import os
+from langchain.prompts import PromptTemplate
+from langchain.llms import OpenAI
+
+# NOTE: Using GitHub models here (add your preferred token attribute)
+
+token = os.environ["GITHUB_TOKEN"]
+endpoint = "https://models.inference.ai.azure.com"
+model_name = "gpt-4o-mini"
+
+llm = OpenAI(
+    base_url=endpoint,
+    api_key=token,
+    model=model_name,
+    temperature=0.7
+)
+
+# Step 2: Define a Prompt Template
+prompt = PromptTemplate(
+    input_variables=["question"],
+    template="You are a helpful assistant. Answer the following question in a clear and concise way: {question}"
+)
+
+
+# Step 3: Create a Function to Get AI Responses
+def get_answer(question):
+    # Format the prompt with the input question
+    formatted_prompt = prompt.format(question=question)
+
+    # Use the LLM to generate a response
+    response = llm(formatted_prompt)
+    return response
+
+
+# Example Usage
+if __name__ == "__main__":
+    question = "What is LangChain and why is it useful?"
+    answer = get_answer(question)
+    print("AI Speaks:", answer)
diff --git a/pixi.toml b/pixi.toml
index 46b390496..cbc28910d 100644
--- a/pixi.toml
+++ b/pixi.toml
@@ -55,5 +55,6 @@ DJ_panel_app = { cmd = "python stock_price_twilio_app.py", depends-on = "DJ_pack
 DJ_flask_app = { cmd = "python app.py", depends-on = "DJ_package", cwd = "analytics_framework/intake/web_ui_flask" }
 DJ_fasthtml_app = { cmd = "python app.py", depends-on = "DJ_package", cwd = "analytics_framework/intake/web_ui_fasthtml" }
 DJ_mito_app = { cmd = "jupyter notebook mito_exp.ipynb", depends-on = "DJ_package", cwd = "usage_guide"}
-DJ_llm_analysis_gpt_4o = {cmd = "python analyse_my_data__gpt_4o_mini.py", cwd= "analytics_framework/ai_modeling"}
-DJ_advance_llm_analysis = {cmd = "python advance_analysis_coral_bleeching.py", cwd= "analytics_framework/ai_modeling"}
+DJ_llm_analysis_gpt_4o = {cmd = "python analyse_my_data__gpt_4o_mini.py", cwd = "analytics_framework/ai_modeling"}
+DJ_advance_llm_analysis = {cmd = "python advance_analysis_coral_bleeching.py", cwd = "analytics_framework/ai_modeling"}
+DJ_hello_world_langchain = {cmd = "python hello_world_lc.py", cwd = "analytics_framework/langchain"}