add llama cpp example

README.md

@@ -71,6 +71,45 @@ Note that you'll still need to code the server-side handling of making the funct
 **Run on your laptop**
 Run on your laptop [video and juypter notebook](https://youtu.be/nDJMHFsBU7M)
 
+After running llama.cpp server, you can call the server with this command, with thanks to @jdo300:
+```
+import requests
+import json
+
+# Define the roles and markers
+B_INST, E_INST = "[INST]", "[/INST]"
+B_FUNC, E_FUNC = "<FUNCTIONS>", "</FUNCTIONS>\n\n"
+
+# Define the function metadata
+function_metadata = {
+    "function": "search_bing",
+    "description": "Search the web for content on Bing. This allows users to search online/the internet/the web for content.",
+    "arguments": [
+        {
+            "name": "query",
+            "type": "string",
+            "description": "The search query string"
+        }
+    ]
+}
+
+# Define the user prompt
+user_prompt = 'Search for the latest news on AI.'
+
+# Format the function list and prompt
+function_list = json.dumps(function_metadata, indent=4)
+prompt = f"{B_FUNC}{function_list.strip()}{E_FUNC}{B_INST} {user_prompt.strip()} {E_INST}\n\n"
+
+# Define the API endpoint
+url = "http:/localhost:8080/completion"
+
+# Send the POST request to the API server
+response = requests.post(url, json={"prompt": prompt})
+
+# Print the response
+print(response.json())
+```
+
 ## Syntax
 
 ### Prompt Templates