dummy-ollama

serve.py

import json
import time

app = Flask(__name__)


@app.route("/api/generate", methods=["POST"])
def generate_response():
    assert request.json
    model = request.json["model"]
    prompt = request.json["prompt"]

    def generate_messages():
        for word in prompt.split():
            response_message = {
                "model": model,
                "created_at": time.strftime("%Y-%m-%dT%H:%M:%S.%fZ"),
                "response": f"{word} ",
                "done": False,
            }
            yield json.dumps(response_message) + "\n"
            time.sleep(1)  # Simulate some processing time

        # Final message with some no-sense additional information
        final_message = {
            "model": model,
            "created_at": time.strftime("%Y-%m-%dT%H:%M:%S.%fZ"),
            "context": [1, 2, 3],
            "done": True,
            "total_duration": 5589157167,
            "load_duration": 3013701500,
            "sample_count": 114,
            "sample_duration": 81442000,
            "prompt_eval_count": 46,
            "prompt_eval_duration": 1160282000,
            "eval_count": 113,
            "eval_duration": 1325948000,
        }
        yield json.dumps(final_message) + "\n"

    return Response(generate_messages(), content_type="application/json", status=200)


if __name__ == "__main__":
    app.run(host="localhost", port=11434, debug=True)

• Run server with

python serve.py

• Send HTTP request with curl

curl \
-X POST  \
-H "Content-Type: application/json" \
-d '{
  "model": "dummy-model",
  "prompt":"Why is the sky blue?"
}' \
http://localhost:11434/api/generate

-H "Content-Type: application/json" header is required for this Flask server but is not required in standard ollama API calls.