ChatBaichuan

Setup:

To use, you should have the environment variableBAICHUAN_API_KEY set with

your API KEY.

.. code-block:: bash

    export BAICHUAN_API_KEY="your-api-key"

Key init args — completion params: model: Optional[str] Name of Baichuan model to use. max_tokens: Optional[int] Max number of tokens to generate. streaming: Optional[bool] Whether to stream the results or not. temperature: Optional[float] Sampling temperature. top_p: Optional[float] What probability mass to use. top_k: Optional[int] What search sampling control to use.

Key init args — client params: api_key: Optional[str] Baichuan API key. If not passed in will be read from env var BAICHUAN_API_KEY. base_url: 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 ChatBaichuan

chat = ChatBaichuan( api_key=api_key, model='Baichuan4', # temperature=..., # 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。"),
]
chat.invoke(messages)

.. code-block:: python

AIMessage(
    content='I enjoy programming.',
    response_metadata={
        'token_usage': {
            'prompt_tokens': 93,
            'completion_tokens': 5,
            'total_tokens': 98
        },
        'model': 'Baichuan4'
    },
    id='run-944ff552-6a93-44cf-a861-4e4d849746f9-0'
)

Stream:

.. code-block:: python

for chunk in chat.stream(messages):
    print(chunk)

.. code-block:: python

content='I' id='run-f99fcd6f-dd31-46d5-be8f-0b6a22bf77d8'
content=' enjoy programming.' id='run-f99fcd6f-dd31-46d5-be8f-0b6a22bf77d8

.. code-block:: python

stream = chat.stream(messages)
full = next(stream)
for chunk in stream:
    full += chunk
full

.. code-block:: python

AIMessageChunk(
    content='I like programming.',
    id='run-74689970-dc31-461d-b729-3b6aa93508d2'
)

Async:

.. code-block:: python

await chat.ainvoke(messages)

# stream
# async for chunk in chat.astream(messages):
#     print(chunk)

# batch
# await chat.abatch([messages])

.. code-block:: python

AIMessage(
    content='I enjoy programming.',
    response_metadata={
        'token_usage': {
            'prompt_tokens': 93,
            'completion_tokens': 5,
            'total_tokens': 98
        },
        'model': 'Baichuan4'
    },
    id='run-952509ed-9154-4ff9-b187-e616d7ddfbba-0'
)

Tool calling:

.. code-block:: python
    class get_current_weather(BaseModel):
        '''Get current weather.'''

        location: str = Field('City or province, such as Shanghai')

    llm_with_tools = ChatBaichuan(model='Baichuan3-Turbo').bind_tools([get_current_weather])
    llm_with_tools.invoke('How is the weather today?')

.. code-block:: python

    [{'name': 'get_current_weather',
    'args': {'location': 'New York'},
    'id': '3951017OF8doB0A',
    'type': 'tool_call'}]

Response metadata .. code-block:: python

    ai_msg = chat.invoke(messages)
    ai_msg.response_metadata

.. code-block:: python

    {
        'token_usage': {
            'prompt_tokens': 93,
            'completion_tokens': 5,
            'total_tokens': 98
        },
        'model': 'Baichuan4'
    }