diff --git a/README.md b/README.md
index 7c6b445..964a1df 100644
--- a/README.md
+++ b/README.md
@@ -1 +1,6 @@
-# township-small-business-bot
\ No newline at end of file
+## API Usage
+
+To test the API locally, ensure your server is running and use the following `curl` command:
+
+```sh
+curl -d '{ "model": "llama3", "prompt": "Why is the sky blue?" }' -H "Content-Type: application/json" http://localhost:11434/api/generate
diff --git a/api_server.py b/api_server.py
new file mode 100644
index 0000000..9c880fc
--- /dev/null
+++ b/api_server.py
@@ -0,0 +1,22 @@
+from flask import Flask, request, jsonify
+
+app = Flask(__name__)
+
+@app.route('/api/generate', methods=['POST'])
+def generate_response():
+    data = request.json
+    model = data.get('model')
+    prompt = data.get('prompt')
+    if model and prompt:
+        # Mock response for demonstration
+        response = {
+            "model": model,
+            "prompt": prompt,
+            "response": "The sky is blue due to the scattering of sunlight by the atmosphere."
+        }
+        return jsonify(response), 200
+    else:
+        return jsonify({"error": "Invalid input"}), 400
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=11434)
diff --git a/app.py b/app.py
new file mode 100644
index 0000000..40b21aa
--- /dev/null
+++ b/app.py
@@ -0,0 +1,14 @@
+from flask import Flask, request, jsonify
+
+app = Flask(__name__)
+
+@app.route('/api/generate', methods=['POST'])
+def generate():
+    data = request.json
+    model = data.get('model')
+    prompt = data.get('prompt')
+    response = f"This is a mock response for the model {model} with prompt: {prompt}"
+    return jsonify({"response": response})
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=11434)
diff --git a/ollama_api.py b/ollama_api.py
new file mode 100644
index 0000000..80f1571
--- /dev/null
+++ b/ollama_api.py
@@ -0,0 +1,9 @@
+from fastapi import FastAPI
+
+app = FastAPI()
+
+@app.post("/ollama")
+def generate_response(prompt: str):
+    # Replace with your actual Llama 2 model invocation
+    model_response = ollama.generate(prompt, model="llama3", temperature=0.8)
+    return {"response": model_response}