Merge pull request #106 from langchain-ai/erick/update-v0-2-to-latest…

…-docs-links

update v0.2 to latest docs links

cookbook/nvidia_nim_agents_llama3.1.ipynb

@@ -27,7 +27,7 @@
     "NIM supports models across domains like chat, embedding, and re-ranking models \n",
     "from the community as well as NVIDIA. These models are optimized by NVIDIA to deliver the best performance on NVIDIA \n",
     "accelerated infrastructure and deployed as a NIM, an easy-to-use, prebuilt containers that deploy anywhere using a single \n",
-    "command on NVIDIA accelerated infrastructure. If you're new to NIMs with LangChain, check out the [documentation](https://python.langchain.com/v0.2/docs/integrations/providers/nvidia/).\n",
+    "command on NVIDIA accelerated infrastructure. If you're new to NIMs with LangChain, check out the [documentation](https://python.langchain.com/docs/integrations/providers/nvidia/).\n",
     "\n",
     "Now, NIMs support tool calling, also known as \"function calling\" for models that have the aforementioned capability. \n",
     "\n",
@@ -78,7 +78,7 @@
    "id": "6c65b376",
    "metadata": {},
    "source": [
-    "If you're using NVIDIA hosted NIMs, you'll need to use an API key which you can setup below. Follow [NVIDIA NIMs LangChain documentation](https://python.langchain.com/v0.2/docs/integrations/chat/nvidia_ai_endpoints/) for more information on accessing and using NIMs. "
+    "If you're using NVIDIA hosted NIMs, you'll need to use an API key which you can setup below. Follow [NVIDIA NIMs LangChain documentation](https://python.langchain.com/docs/integrations/chat/nvidia_ai_endpoints/) for more information on accessing and using NIMs. "
    ]
   },
   {
@@ -119,7 +119,7 @@
    "id": "9ce17567",
    "metadata": {},
    "source": [
-    "Initialize [Tavily Tool](https://python.langchain.com/v0.2/docs/integrations/tools/tavily_search/)\n",
+    "Initialize [Tavily Tool](https://python.langchain.com/docs/integrations/tools/tavily_search/)\n",
     "\n",
     "Note that this requires an API key - they have a free tier, but if you don't have one or don't want to create one, you can always ignore this step or use a different tool. \n",
     "\n",
@@ -303,7 +303,7 @@
    "source": [
     "## 🔨 Tool Usage -- Adding on a Custom Tool and Using LangGraph\n",
     "\n",
-    "Let's see how to [define a custom tool](https://python.langchain.com/v0.2/docs/how_to/custom_tools/) for your NIM agent and how it handles multiple tools.  \n",
+    "Let's see how to [define a custom tool](https://python.langchain.com/docs/how_to/custom_tools/) for your NIM agent and how it handles multiple tools.  \n",
     "\n",
     "We'll enhance the NIM with Tavily search with some custom tools to determine a user's current location (based on IP address) and return a latitude and longitude. We will use these tools to have Tavily look up the weather in the user's current location.\n",
     "\n",

libs/ai-endpoints/langchain_nvidia_ai_endpoints/chat_models.py

@@ -770,7 +770,7 @@ class Choices(enum.Enum):
         # Output: None
         ```
 
-        For more, see https://python.langchain.com/v0.2/docs/how_to/structured_output/
+        For more, see https://python.langchain.com/docs/how_to/structured_output/
         """  # noqa: E501
 
         if "method" in kwargs:
@@ -790,7 +790,7 @@ class Choices(enum.Enum):
         if include_raw:
             raise NotImplementedError(
                 "include_raw=True is not implemented, consider "
-                "https://python.langchain.com/v0.2/docs/how_to/"
+                "https://python.langchain.com/docs/how_to/"
                 "structured_output/#prompting-and-parsing-model"
                 "-outputs-directly or rely on the structured response "
                 "being None when the LLM produces an incomplete response."