ChatZhipuAI

Setup:

Install PyJWT and set environment variable ZHIPUAI_API_KEY

.. code-block:: bash

pip install pyjwt
export ZHIPUAI_API_KEY="your-api-key"

Key init args — completion params: model: Optional[str] Name of ZhipuAI 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 = zhipuai_chat.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')]

Tool calling:

.. code-block:: python

from pydantic import BaseModel, Field

class GetWeather(BaseModel):
    '''Get the current weather in a given location'''

    location: str = Field(
        ..., description="The city and state, e.g. San Francisco, CA"
    )

class GetPopulation(BaseModel):
    '''Get the current population in a given location'''

    location: str = Field(
        ..., description="The city and state, e.g. San Francisco, CA"
    )

chat_with_tools = zhipuai_chat.bind_tools([GetWeather, GetPopulation])
ai_msg = chat_with_tools.invoke(
    "Which city is hotter today and which is bigger: LA or NY?"
)
ai_msg.tool_calls

.. code-block:: python

[
    {
        'name': 'GetWeather',
        'args': {'location': 'Los Angeles, CA'},
        'id': 'call_202408222146464ea49ec8731145a9',
        'type': 'tool_call'
    }
]

Structured output:

.. code-block:: python

from typing import Optional

from pydantic import BaseModel, Field

class Joke(BaseModel):
    '''Joke to tell user.'''

    setup: str = Field(description="The setup of the joke")
    punchline: str = Field(description="The punchline to the joke")
    rating: Optional[int] = Field(description="How funny the joke is, from 1 to 10")

structured_chat = zhipuai_chat.with_structured_output(Joke)
structured_chat.invoke("Tell me a joke about cats")

.. code-block:: python

Joke(setup='What do cats like to eat for breakfast?', punchline='Mice Krispies!', rating=None)

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'}