add ollama http endpoint example

Author: niftycode

CHANGELOG.rst

@@ -1,6 +1,12 @@
 CHANGELOG
 =========
 
+[0.1.9]-2026-04-30
+-------------------
+
+Add first Ollama example:
+Use Ollama's HTTP API to generate a response from a local LLM model and print the response.
+
 [0.1.8]-2025-10-25
 -------------------
 

ai/README.md

@@ -3,3 +3,5 @@
 This directory contains examples of using [Ollama](https://ollama.com) with Python. Some of you might be wondering: What is Ollama? It's a tool that allows you to use LLMs locally. Once Ollama is installed and a large language model (LLM) has been downloaded, you can use that model in the terminal. Ollama also has a simple graphical interface (similar to ChatGPT).
 
 [This blog post](https://niftycode.eu/using-large-language-models-with-ollama-locally-on-mac/) describes how to install Ollama on a Mac. The procedure shown should be very similar under Linux and Windows.
+
+The first example (ollama-api.py) demonstrates how to access Ollama's HTTP endpoint. A request is sent to a local model via this endpoint. The response is displayed in the terminal and saved to the file `generated_output.md` (Markdown format).

ai/ollama-api.py

@@ -0,0 +1,69 @@
+#!/usr/bin/env python3
+
+"""
+This script interacts with the Ollama API to generate text based on a given prompt.
+The output will be printed to the console and saved to a Markdown file named `generated_output.md`.
+Version: 1.1
+Python 3.13+
+Date created: April 30th, 2026
+Date modified: -
+"""
+
+import json
+import sys
+
+import requests  # type: ignore
+from requests.exceptions import RequestException  # type: ignore
+
+# Endpoint of Ollama API
+URL = "http://localhost:11434/api/generate"
+
+data = {
+    "model": "qwen2.5-coder",
+    "prompt": "Write a Python class called `Cameras` with the field `manufacturer`.",
+    "max_tokens": 1000,
+    "temperature": 0.6,
+    "top_p": 0.9,
+    "n": 1,
+    "stream": False,
+}
+
+
+def fetch_generated_text() -> str:
+    """
+    Fetch generated text from the Ollama API.
+    """
+
+    generated_text = ""
+
+    try:
+        # Make a POST request to the Ollama API
+        response: requests.Response = requests.post(URL, json=data, stream=True)
+    except RequestException as e:
+        print(f"Error message:\n{e}")
+        sys.exit("No connection to Ollama API. Exit program!")
+
+    for line in response.iter_lines():
+        if line:
+            decoded_line = line.decode("utf-8")
+            result = json.loads(decoded_line)
+            # Get the generated text from the response
+            generated_text = result.get("response", "")
+
+    return generated_text
+
+
+def main() -> None:
+    """Main function to execute the script."""
+
+    answer: str = fetch_generated_text()
+
+    print(answer, end="", flush=True)
+
+    # Save the generated text to a Markdown file
+    with open("generated_output.md", "a", encoding="utf-8") as md_file:
+        md_file.write(answer)
+
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -4,4 +4,5 @@ black
 mypy
 pytest
 rich
+requests
 pycryptodome