update to 0.1, remove deprecated functionality and focus on api catalog backend

libs/ai-endpoints/README.md

@@ -221,7 +221,7 @@ for txt in chain.stream({"input": "Why is a PB&J?"}):
 
 NVIDIA also supports multimodal inputs, meaning you can provide both images and text for the model to reason over.
 
-An example model supporting multimodal inputs is `ai-neva-22b`.
+An example model supporting multimodal inputs is `nvidia/neva-22b`.
 
 These models accept LangChain's standard image formats. Below are examples.
 
@@ -237,7 +237,7 @@ Initialize the model like so:
 ```python
 from langchain_nvidia_ai_endpoints import ChatNVIDIA
 
-llm = ChatNVIDIA(model="ai-neva-22b")
+llm = ChatNVIDIA(model="nvidia/neva-22b")
 ```
 
 #### Passing an image as a URL

libs/ai-endpoints/docs/text_embedding/nvidia_ai_endpoints.ipynb

@@ -451,7 +451,7 @@
     "    ]\n",
     ")\n",
     "\n",
-    "model = ChatNVIDIA(model=\"ai-mixtral-8x7b-instruct\")\n",
+    "model = ChatNVIDIA(model=\"mistralai/mixtral-8x7b-instruct-v0.1\")\n",
     "\n",
     "chain = (\n",
     "    {\"context\": retriever, \"question\": RunnablePassthrough()}\n",