Update README.md

README.md

@@ -7,11 +7,22 @@ sdk: docker
 pinned: false
 license: apache-2.0
 short_description: using public LLM to create own Gen AI app
-
-app_port: 7860  # This MUST match the port your FastAPI app listens on inside the container
-image: dharmendrarathore/first-py-app:latest # Points to your Docker Hub image
-hf_token_secret: HUGGINGFACEHUB_API_TOKEN # This tells Spaces to mount the secret as an env var
+app_port: 7860
+image: dharmendrarathore/first-py-app:latest
+hf_token_secret: HUGGINGFACEHUB_API_TOKEN
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# PY LLM DEMO
+
+This Hugging Face Space hosts a FastAPI application serving a Qwen language model via a Docker container.
+The Docker image is pulled from Docker Hub.
+
+## API Endpoint Usage:
+
+To interact with the API, send a POST request with a JSON body with a "question" field to the `/api/generate` endpoint.
+
+**Example using `curl`:**
+
+```bash
+curl -X POST -H "Content-Type: application/json" -d '{"question": "How do large language models work?"}' [https://rathore11-py-llm-demo.hf.space/api/generate](https://rathore11-py-llm-demo.hf.space/api/generate)