Merge pull request #384 from DefangLabs/jordan/refactor-managed-llm-samples

jordanstephens · web-flow · commit 9a0d42a38499 · 2025-05-23T07:35:33.000-07:00
Refactor managed llm samples
diff --git a/README.md b/README.md
@@ -36,7 +36,7 @@ The `x-defang-llm` property on the `llm` service must be set to `true` in order
 To run the application locally, you can use the following command:
 
 ```bash
-docker compose -f compose.dev.yaml up --build
+docker compose -f compose.local.yaml up --build
 ```
 
 ## Deployment
diff --git a/app/app.py b/app/app.py
@@ -3,10 +3,11 @@
 import os
 
 import requests
-from fastapi import FastAPI, Form, Request
+from fastapi import FastAPI, Form
 from fastapi.responses import HTMLResponse
 from fastapi.staticfiles import StaticFiles
 from fastapi.responses import JSONResponse
+from fastapi.responses import FileResponse
 
 app = FastAPI()
 app.mount("/static", StaticFiles(directory="static"), name="static")
@@ -22,33 +23,14 @@
 MODEL_ID = os.getenv("LLM_MODEL", "gpt-4-turbo")
 
 # Get the API key for the LLM
-# For development, you can use your local API key. In production, the LLM gateway service will override the need for it.
+# For development, you have the option to use your local API key. In production, the LLM gateway service will override the need for it.
 def get_api_key():
     return os.getenv("OPENAI_API_KEY", "")
 
 # Home page form
 @app.get("/", response_class=HTMLResponse)
 async def home():
-    return """
-    <html>
-        <head>
-            <title>Ask the AI Model</title>
-            <script type="text/javascript" src="./static/app.js"></script>
-        </head>
-        <body>
-            <h1>Ask the AI Model</h1>
-            <form method="post" id="askForm" onsubmit="event.preventDefault(); submitForm(event);">
-                <textarea id="prompt" name="prompt" autofocus="autofocus" rows="5" cols="60" placeholder="Enter your question here..."
-                  onkeydown="if(event.key==='Enter'&&!event.shiftKey){event.preventDefault();this.form.dispatchEvent(new Event('submit', {cancelable:true}));}"></textarea>
-                <br><br>
-                <input type="submit" value="Ask">
-            </form>
-            <hr>
-            <h2>Model's Reply:</h2>
-            <p id="reply"></p>
-        </body>
-    </html>
-    """
+    return FileResponse("static/index.html", media_type="text/html")
 
 # Handle form submission
 @app.post("/ask", response_class=JSONResponse)
diff --git a/app/static/index.html b/app/static/index.html
@@ -0,0 +1,18 @@
+<html>
+    <head>
+        <title>Ask the AI Model</title>
+        <script type="text/javascript" src="./static/app.js"></script>
+    </head>
+    <body>
+        <h1>Ask the AI Model</h1>
+        <form method="post" id="askForm" onsubmit="event.preventDefault(); submitForm(event);">
+            <textarea id="prompt" name="prompt" autofocus="autofocus" rows="5" cols="60" placeholder="Enter your question here..."
+              onkeydown="if(event.key==='Enter'&&!event.shiftKey){event.preventDefault();this.form.dispatchEvent(new Event('submit', {cancelable:true}));}"></textarea>
+            <br><br>
+            <input type="submit" value="Ask">
+        </form>
+        <hr>
+        <h2>Model's Reply:</h2>
+        <p id="reply"></p>
+    </body>
+</html>
diff --git a/compose.yaml b/compose.yaml
@@ -7,7 +7,7 @@ services:
       - "8000:8000"
     restart: always
     environment:
-      - LLM_MODEL # LLM model ID used
+      - LLM_MODEL=default
       # For other models, see https://docs.defang.io/docs/concepts/managed-llms/openai-access-gateway#model-mapping
     healthcheck:
       test: ["CMD", "python3", "-c", "import sys, urllib.request; urllib.request.urlopen(sys.argv[1]).read()", "http://localhost:8000/"]
