fix the embedding models

Author: garman

samples/js/azure_ai_inference/embeddings.js

@@ -3,7 +3,7 @@ import { isUnexpected } from "@azure-rest/ai-inference";
 import { AzureKeyCredential } from "@azure/core-auth";
 
 const token = process.env["GITHUB_TOKEN"];
-const endpoint = "https://models.github.ai";
+const endpoint = "https://models.github.ai/inference";
 
 /* By using the Azure AI Inference SDK, you can easily experiment with different models
    by modifying the value of `modelName` in the code below. For this code sample

samples/js/openai/embeddings.js

@@ -1,7 +1,7 @@
 import OpenAI from "openai";
 
 const token = process.env["GITHUB_TOKEN"];
-const endpoint = "https://models.github.ai";
+const endpoint = "https://models.github.ai/inference";
 
 /* Pick one of the OpenAI embeddings models from the GitHub Models service */
 const modelName = "text-embedding-3-small";

samples/python/azure_ai_inference/embeddings.py

@@ -4,7 +4,7 @@
 from azure.core.credentials import AzureKeyCredential
 
 token = os.environ["GITHUB_TOKEN"]
-endpoint = "https://models.github.ai"
+endpoint = "https://models.github.ai/inference"
 
 # By using the Azure AI Inference SDK, you can easily experiment with different models
 # by modifying the value of `modelName` in the code below. For this code sample

samples/python/azure_ai_inference/getting_started.ipynb

@@ -58,7 +58,7 @@
     "    raise ValueError(\"GITHUB_TOKEN is not set\")\n",
     "\n",
     "github_token = os.environ[\"GITHUB_TOKEN\"]\n",
-    "endpoint = \"https://models.github.ai\"\n",
+    "endpoint = \"https://models.github.ai/inference\"\n",
     "\n",
     "\n",
     "# Create a client\n",

samples/python/mistralai/getting_started.ipynb

@@ -58,7 +58,7 @@
     "    raise ValueError(\"GITHUB_TOKEN is not set\")\n",
     "\n",
     "github_token = os.environ[\"GITHUB_TOKEN\"]\n",
-    "endpoint = \"https://models.github.ai\"\n",
+    "endpoint = \"https://models.github.ai/inference\"\n",
     "\n",
     "# Pick one of the Mistral models from the GitHub Models service\n",
     "model_name = \"Mistral-large\"\n",

samples/python/openai/embeddings.py

@@ -2,7 +2,7 @@
 from openai import OpenAI
 
 token = os.environ["GITHUB_TOKEN"]
-endpoint = "https://models.github.ai"
+endpoint = "https://models.github.ai/inference"
 
 # Pick one of the OpenAI embeddings models from the GitHub Models service
 model_name = "text-embedding-3-small"

samples/python/openai/embeddings_getting_started.ipynb

@@ -55,7 +55,7 @@
     "    raise ValueError(\"GITHUB_TOKEN is not set\")\n",
     "\n",
     "os.environ[\"OPENAI_API_KEY\"] = os.getenv(\"GITHUB_TOKEN\")\n",
-    "os.environ[\"OPENAI_BASE_URL\"] = \"https://models.github.ai/\"\n",
+    "os.environ[\"OPENAI_BASE_URL\"] = \"https://models.github.ai/inference\"\n",
     "\n",
     "client = OpenAI()\n"
    ]

samples/python/openai/multi_turn.py

@@ -16,6 +16,9 @@
 client = OpenAI(
     base_url=endpoint,
     api_key=token,
+    default_headers={
+        "x-ms-useragent": "github-models-sample",
+    }
 )
 
 # Call the chat completion API
@@ -42,4 +45,4 @@
 )
 
 # Print the response
-print(response.choices[0].message.content)
+print(response.choices[0].message.content)