Merge branch 'langchain-ai:master' into master

.github/workflows/_integration_test.yml

@@ -12,7 +12,6 @@ env:
 
 jobs:
   build:
-    environment: Scheduled testing
     defaults:
       run:
         working-directory: ${{ inputs.working-directory }}
@@ -53,8 +52,15 @@ jobs:
         shell: bash
         env:
           AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
+          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
+          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
+          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
+          AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
           MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
           TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}

docs/docs/how_to/streaming.ipynb

@@ -1003,7 +1003,7 @@
    "id": "798ea891-997c-454c-bf60-43124f40ee1b",
    "metadata": {},
    "source": [
-    "Because both the model and the parser support streaming, we see sreaming events from both components in real time! Kind of cool isn't it? 🦜"
+    "Because both the model and the parser support streaming, we see streaming events from both components in real time! Kind of cool isn't it? 🦜"
    ]
   },
   {

docs/docs/integrations/chat/nvidia_ai_endpoints.ipynb

@@ -134,7 +134,7 @@
     "from langchain_nvidia_ai_endpoints import ChatNVIDIA\n",
     "\n",
     "# connect to an embedding NIM running at localhost:8000, specifying a specific model\n",
-    "llm = ChatNVIDIA(base_url=\"http://localhost:8000/v1\", model=\"meta-llama3-8b-instruct\")"
+    "llm = ChatNVIDIA(base_url=\"http://localhost:8000/v1\", model=\"meta/llama3-8b-instruct\")"
    ]
   },
   {
@@ -658,7 +658,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.10.2"
   }
  },
  "nbformat": 4,

docs/docs/integrations/providers/nvidia.mdx

@@ -62,7 +62,7 @@ When ready to deploy, you can self-host models with NVIDIA NIM—which is includ
 from langchain_nvidia_ai_endpoints import ChatNVIDIA, NVIDIAEmbeddings, NVIDIARerank
 
 # connect to an chat NIM running at localhost:8000, specifyig a specific model
-llm = ChatNVIDIA(base_url="http://localhost:8000/v1", model="meta-llama3-8b-instruct")
+llm = ChatNVIDIA(base_url="http://localhost:8000/v1", model="meta/llama3-8b-instruct")
 
 # connect to an embedding NIM running at localhost:8080
 embedder = NVIDIAEmbeddings(base_url="http://localhost:8080/v1")

libs/community/langchain_community/chat_models/zhipuai.py

@@ -163,23 +163,115 @@ def _truncate_params(payload: Dict[str, Any]) -> None:
 
 
 class ChatZhipuAI(BaseChatModel):
-    """
-    `ZhipuAI` large language chat models API.
+    """ZhipuAI chat model integration.
 
-    To use, you should have the ``PyJWT`` python package installed.
+    Setup:
+        Install ``PyJWT`` and set environment variable ``ZHIPUAI_API_KEY``
 
-    Example:
-    .. code-block:: python
+        .. code-block:: bash
 
-    from langchain_community.chat_models import ChatZhipuAI
+            pip install pyjwt
+            export ZHIPUAI_API_KEY="your-api-key"
 
-    zhipuai_chat = ChatZhipuAI(
-        temperature=0.5,
-        api_key="your-api-key",
-        model="glm-4"
-    )
+    Key init args — completion params:
+        model: Optional[str]
+            Name of OpenAI model to use.
+        temperature: float
+            Sampling temperature.
+        max_tokens: Optional[int]
+            Max number of tokens to generate.
 
-    """
+    Key init args — client params:
+        api_key: Optional[str]
+        ZhipuAI API key. If not passed in will be read from env var ZHIPUAI_API_KEY.
+        api_base: Optional[str]
+        Base URL for API requests.
+
+    See full list of supported init args and their descriptions in the params section.
+
+    Instantiate:
+        .. code-block:: python
+
+            from langchain_community.chat_models import ChatZhipuAI
+
+            zhipuai_chat = ChatZhipuAI(
+                temperature=0.5,
+                api_key="your-api-key",
+                model="glm-4",
+                # api_base="...",
+                # other params...
+            )
+
+    Invoke:
+        .. code-block:: python
+
+            messages = [
+                ("system", "你是一名专业的翻译家，可以将用户的中文翻译为英文。"),
+                ("human", "我喜欢编程。"),
+            ]
+            zhipuai_chat.invoke(messages)
+
+        .. code-block:: python
+
+            AIMessage(content='I enjoy programming.', response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 23, 'total_tokens': 29}, 'model_name': 'glm-4', 'finish_reason': 'stop'}, id='run-c5d9af91-55c6-470e-9545-02b2fa0d7f9d-0')
+
+    Stream:
+        .. code-block:: python
+
+            for chunk in zhipuai_chat.stream(messages):
+                print(chunk)
+
+        .. code-block:: python
+
+            content='I' id='run-4df71729-618f-4e2b-a4ff-884682723082'
+            content=' enjoy' id='run-4df71729-618f-4e2b-a4ff-884682723082'
+            content=' programming' id='run-4df71729-618f-4e2b-a4ff-884682723082'
+            content='.' id='run-4df71729-618f-4e2b-a4ff-884682723082'
+            content='' response_metadata={'finish_reason': 'stop'} id='run-4df71729-618f-4e2b-a4ff-884682723082'
+
+        .. code-block:: python
+
+            stream = llm.stream(messages)
+            full = next(stream)
+            for chunk in stream:
+                full += chunk
+            full
+
+        .. code-block::
+
+            AIMessageChunk(content='I enjoy programming.', response_metadata={'finish_reason': 'stop'}, id='run-20b05040-a0b4-4715-8fdc-b39dba9bfb53')
+
+    Async:
+        .. code-block:: python
+
+            await zhipuai_chat.ainvoke(messages)
+
+            # stream:
+            # async for chunk in zhipuai_chat.astream(messages):
+            #    print(chunk)
+
+            # batch:
+            # await zhipuai_chat.abatch([messages])
+
+        .. code-block:: python
+
+            [AIMessage(content='I enjoy programming.', response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 23, 'total_tokens': 29}, 'model_name': 'glm-4', 'finish_reason': 'stop'}, id='run-ba06af9d-4baa-40b2-9298-be9c62aa0849-0')]
+
+    Response metadata
+        .. code-block:: python
+
+            ai_msg = zhipuai_chat.invoke(messages)
+            ai_msg.response_metadata
+
+        .. code-block:: python
+
+            {'token_usage': {'completion_tokens': 6,
+              'prompt_tokens': 23,
+              'total_tokens': 29},
+              'model_name': 'glm-4',
+              'finish_reason': 'stop'}
+
+    """  # noqa: E501
 
     @property
     def lc_secrets(self) -> Dict[str, str]: