Add /inference to the end

pamelafox · web-flow · commit 828c656751fe · 2025-07-23T16:46:15.000Z
diff --git a/chained_calls.py b/chained_calls.py
@@ -24,7 +24,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/chat.py b/chat.py
@@ -24,7 +24,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/chat_async.py b/chat_async.py
@@ -23,7 +23,7 @@
     client = openai.AsyncOpenAI(base_url=os.environ["OLLAMA_ENDPOINT"], api_key="nokeyneeded")
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 elif API_HOST == "github":
-    client = openai.AsyncOpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.AsyncOpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 else:
     client = openai.AsyncOpenAI(api_key=os.environ["OPENAI_KEY"])
diff --git a/chat_history.py b/chat_history.py
@@ -22,7 +22,7 @@
     client = openai.OpenAI(base_url=os.environ["OLLAMA_ENDPOINT"], api_key="nokeyneeded")
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 else:
     client = openai.OpenAI(api_key=os.environ["OPENAI_KEY"])
diff --git a/chat_history_stream.py b/chat_history_stream.py
@@ -22,7 +22,7 @@
     client = openai.OpenAI(base_url=os.environ["OLLAMA_ENDPOINT"], api_key="nokeyneeded")
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 else:
     client = openai.OpenAI(api_key=os.environ["OPENAI_KEY"])
diff --git a/chat_langchain.py b/chat_langchain.py
@@ -28,7 +28,7 @@
 elif API_HOST == "github":
     llm = ChatOpenAI(
         model_name=os.getenv("GITHUB_MODEL", "gpt-4o"),
-        openai_api_base="https://models.github.ai",
+        openai_api_base="https://models.github.ai/inference",
         openai_api_key=os.environ["GITHUB_TOKEN"],
     )
 else:
diff --git a/chat_llamaindex.py b/chat_llamaindex.py
@@ -30,7 +30,7 @@
 elif API_HOST == "github":
     llm = OpenAILike(
         model=os.getenv("GITHUB_MODEL", "gpt-4o"),
-        api_base="https://models.github.ai",
+        api_base="https://models.github.ai/inference",
         api_key=os.environ["GITHUB_TOKEN"],
         is_chat_model=True,
     )
diff --git a/chat_pydanticai.py b/chat_pydanticai.py
@@ -26,7 +26,7 @@
     model = OpenAIModel(
         os.getenv("GITHUB_MODEL", "gpt-4o"),
         api_key=os.environ["GITHUB_TOKEN"],
-        base_url="https://models.github.ai",
+        base_url="https://models.github.ai/inference",
     )
 
 else:
diff --git a/chat_safety.py b/chat_safety.py
@@ -22,7 +22,7 @@
     client = openai.OpenAI(base_url=os.environ["OLLAMA_ENDPOINT"], api_key="nokeyneeded")
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 else:
     client = openai.OpenAI(api_key=os.environ["OPENAI_KEY"])
diff --git a/chat_stream.py b/chat_stream.py
@@ -22,7 +22,7 @@
     client = openai.OpenAI(base_url=os.environ["OLLAMA_ENDPOINT"], api_key="nokeyneeded")
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 else:
     client = openai.OpenAI(api_key=os.environ["OPENAI_KEY"])
diff --git a/few_shot_examples.py b/few_shot_examples.py
@@ -24,7 +24,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/function_calling_basic.py b/function_calling_basic.py
@@ -24,7 +24,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/function_calling_call.py b/function_calling_call.py
@@ -25,7 +25,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/function_calling_extended.py b/function_calling_extended.py
@@ -25,7 +25,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/function_calling_multiple.py b/function_calling_multiple.py
@@ -24,7 +24,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/prompt_engineering.py b/prompt_engineering.py
@@ -24,7 +24,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/rag_csv.py b/rag_csv.py
@@ -26,7 +26,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/rag_documents_flow.py b/rag_documents_flow.py
@@ -26,7 +26,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/rag_documents_hybrid.py b/rag_documents_hybrid.py
@@ -27,7 +27,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/rag_documents_ingestion.py b/rag_documents_ingestion.py
@@ -28,7 +28,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/rag_multiturn.py b/rag_multiturn.py
@@ -26,7 +26,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/rag_queryrewrite.py b/rag_queryrewrite.py
@@ -26,7 +26,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/retrieval_augmented_generation.py b/retrieval_augmented_generation.py
@@ -25,7 +25,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/spanish/chained_calls.py b/spanish/chained_calls.py
@@ -24,7 +24,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/spanish/chat.py b/spanish/chat.py
@@ -24,7 +24,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/spanish/chat_async.py b/spanish/chat_async.py
@@ -23,7 +23,7 @@
     client = openai.AsyncOpenAI(base_url=os.environ["OLLAMA_ENDPOINT"], api_key="nokeyneeded")
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 elif API_HOST == "github":
-    client = openai.AsyncOpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.AsyncOpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 else:
     client = openai.AsyncOpenAI(api_key=os.environ["OPENAI_KEY"])
diff --git a/spanish/chat_history.py b/spanish/chat_history.py
@@ -22,7 +22,7 @@
     client = openai.OpenAI(base_url=os.environ["OLLAMA_ENDPOINT"], api_key="nokeyneeded")
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 else:
     client = openai.OpenAI(api_key=os.environ["OPENAI_KEY"])
diff --git a/spanish/chat_history_stream.py b/spanish/chat_history_stream.py
@@ -22,7 +22,7 @@
     client = openai.OpenAI(base_url=os.environ["OLLAMA_ENDPOINT"], api_key="nokeyneeded")
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 else:
     client = openai.OpenAI(api_key=os.environ["OPENAI_KEY"])
diff --git a/spanish/chat_langchain.py b/spanish/chat_langchain.py
@@ -28,7 +28,7 @@
 elif API_HOST == "github":
     llm = ChatOpenAI(
         model_name=os.getenv("GITHUB_MODEL", "gpt-4o"),
-        openai_api_base="https://models.github.ai",
+        openai_api_base="https://models.github.ai/inference",
         openai_api_key=os.environ["GITHUB_TOKEN"],
     )
 else:
diff --git a/spanish/chat_llamaindex.py b/spanish/chat_llamaindex.py
@@ -30,7 +30,7 @@
 elif API_HOST == "github":
     llm = OpenAILike(
         model=os.getenv("GITHUB_MODEL", "gpt-4o"),
-        api_base="https://models.github.ai",
+        api_base="https://models.github.ai/inference",
         api_key=os.environ["GITHUB_TOKEN"],
         is_chat_model=True,
     )
diff --git a/spanish/chat_pydanticai.py b/spanish/chat_pydanticai.py
@@ -26,7 +26,7 @@
     model = OpenAIModel(
         os.getenv("GITHUB_MODEL", "gpt-4o"),
         api_key=os.environ["GITHUB_TOKEN"],
-        base_url="https://models.github.ai",
+        base_url="https://models.github.ai/inference",
     )
 
 else:
diff --git a/spanish/chat_safety.py b/spanish/chat_safety.py
@@ -22,7 +22,7 @@
     client = openai.OpenAI(base_url=os.environ["OLLAMA_ENDPOINT"], api_key="nokeyneeded")
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 else:
     client = openai.OpenAI(api_key=os.environ["OPENAI_KEY"])
diff --git a/spanish/chat_stream.py b/spanish/chat_stream.py
@@ -22,7 +22,7 @@
     client = openai.OpenAI(base_url=os.environ["OLLAMA_ENDPOINT"], api_key="nokeyneeded")
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 else:
     client = openai.OpenAI(api_key=os.environ["OPENAI_KEY"])
diff --git a/spanish/few_shot_examples.py b/spanish/few_shot_examples.py
@@ -24,7 +24,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/spanish/function_calling_basic.py b/spanish/function_calling_basic.py
@@ -24,7 +24,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/spanish/function_calling_call.py b/spanish/function_calling_call.py
@@ -25,7 +25,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/spanish/function_calling_extended.py b/spanish/function_calling_extended.py
@@ -25,7 +25,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/spanish/function_calling_multiple.py b/spanish/function_calling_multiple.py
@@ -24,7 +24,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/spanish/prompt_engineering.py b/spanish/prompt_engineering.py
@@ -24,7 +24,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/spanish/rag_csv.py b/spanish/rag_csv.py
@@ -26,7 +26,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/spanish/rag_documents_flow.py b/spanish/rag_documents_flow.py
@@ -26,7 +26,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/spanish/rag_documents_hybrid.py b/spanish/rag_documents_hybrid.py
@@ -27,7 +27,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/spanish/rag_documents_ingestion.py b/spanish/rag_documents_ingestion.py
@@ -28,7 +28,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/spanish/rag_multiturn.py b/spanish/rag_multiturn.py
@@ -26,7 +26,7 @@
     MODEL_NAME = os.environ["OLLAMA_MODEL"]
 
 elif API_HOST == "github":
-    client = openai.OpenAI(base_url="https://models.github.ai", api_key=os.environ["GITHUB_TOKEN"])
+    client = openai.OpenAI(base_url="https://models.github.ai/inference", api_key=os.environ["GITHUB_TOKEN"])
     MODEL_NAME = os.getenv("GITHUB_MODEL", "gpt-4o")
 
 else:
diff --git a/spanish/rag_queryrewrite.py b/spanish/rag_queryrewrite.py
diff --git a/spanish/retrieval_augmented_generation.py b/spanish/retrieval_augmented_generation.py
diff --git a/spanish/structured_outputs_basic.py b/spanish/structured_outputs_basic.py
diff --git a/spanish/structured_outputs_description.py b/spanish/structured_outputs_description.py
diff --git a/spanish/structured_outputs_enum.py b/spanish/structured_outputs_enum.py
diff --git a/spanish/structured_outputs_function_calling.py b/spanish/structured_outputs_function_calling.py
diff --git a/spanish/structured_outputs_nested.py b/spanish/structured_outputs_nested.py
diff --git a/structured_outputs_basic.py b/structured_outputs_basic.py
diff --git a/structured_outputs_description.py b/structured_outputs_description.py
diff --git a/structured_outputs_enum.py b/structured_outputs_enum.py
diff --git a/structured_outputs_function_calling.py b/structured_outputs_function_calling.py
diff --git a/structured_outputs_nested.py b/structured_outputs_nested.py

Original file line number	Diff line number	Diff line change
`@@ -28,7 +28,7 @@`
`28`	`28`	`elif API_HOST == "github":`
`29`	`29`	`llm = ChatOpenAI(`
`30`	`30`	`model_name=os.getenv("GITHUB_MODEL", "gpt-4o"),`
`31`		`- openai_api_base="https://models.github.ai",`
	`31`	`+ openai_api_base="https://models.github.ai/inference",`
`32`	`32`	`openai_api_key=os.environ["GITHUB_TOKEN"],`
`33`	`33`	`)`
`34`	`34`	`else:`
Original file line number	Diff line number	Diff line change
`@@ -30,7 +30,7 @@`
`30`	`30`	`elif API_HOST == "github":`
`31`	`31`	`llm = OpenAILike(`
`32`	`32`	`model=os.getenv("GITHUB_MODEL", "gpt-4o"),`
`33`		`- api_base="https://models.github.ai",`
	`33`	`+ api_base="https://models.github.ai/inference",`
`34`	`34`	`api_key=os.environ["GITHUB_TOKEN"],`
`35`	`35`	`is_chat_model=True,`
`36`	`36`	`)`
Original file line number	Diff line number	Diff line change
`@@ -26,7 +26,7 @@`
`26`	`26`	`model = OpenAIModel(`
`27`	`27`	`os.getenv("GITHUB_MODEL", "gpt-4o"),`
`28`	`28`	`api_key=os.environ["GITHUB_TOKEN"],`
`29`		`- base_url="https://models.github.ai",`
	`29`	`+ base_url="https://models.github.ai/inference",`
`30`	`30`	`)`
`31`	`31`
`32`	`32`	`else:`