当我运行代码时，我收到错误，我的 ollama 没有属性 bind_functions，我使用的 llm 是 ollama 模型 llama -2

Question

# Setup your supervisor, conditional logic, and integrate the nodes into the workflow
members = ["Web_Searcher", "Web_Searcher_Quality","Blog_Searcher", "Blog_Searcher_Quality", "Content_Writer"]
system_prompt = (
    """As a supervisor, your role is to oversee a dialogue between these
    workers: {members}. and excute all the agents one by one,
    determine which worker should take the next action. Each worker is responsible for
    executing a specific task and reporting back their findings and progress. Once all tasks are complete,
    indicate with 'FINISH'."""
)

options = ["FINISH"] + members
function_def = {
    "name": "route",
    "description": "Select the next role.",
    "parameters": {
        "title": "routeSchema",
        "type": "object",
        "properties": {"next": {"title": "Next", "anyOf": [{"enum": options}] }},
        "required": ["next"],
    },
}

prompt = ChatPromptTemplate.from_messages([
    ("system", system_prompt),
    MessagesPlaceholder(variable_name="messages"),
    ("system", "Given the conversation above, who should act next? Or should we FINISH? Select one of: {options}"),
]).partial(options=str(options), members=", ".join(members))

manager_chain = (prompt | llm.bind_functions(functions=[function_def], function_call="route") | JsonOutputFunctionsParser())

我期待它运行，我不知道为什么我被卡住了，这是我得到的输出。 流动 manager_chain = (提示 | llm.bind_functions(functions=[function_def], function_call="route") | JsonOutputFunctionsParser()) ^^^^^^^^^^^^^^^^^^^ AttributeError：“Ollama”对象没有属性“bind_functions”

Answer 1

如错误所示，

Ollama

类没有

bind_functions()

方法。相反，

ChatOpenAI

类确实有

bind_functions()

方法。

Ollama 本身并不支持函数调用，但创建了一个实验性的

OllamaFunctions

包装类，为其提供与 OpenAI Functions 相同的 API。

示例：

from langchain_experimental.llms.ollama_functions import OllamaFunctions

model = OllamaFunctions(model="llama2")

model = model.bind(
    functions=[
        {
            "name": "route",
            "description": "Select the next role.",
            "parameters": {
                "title": "routeSchema",
                "type": "object",
                "properties": {"next": {"title": "Next", "anyOf": [{"enum": options}] }},
                "required": ["next"],
            },
        }
    ],
    function_call={"name": "route"},
)

此实现可能适用于您的函数调用用例。但是，正如文档所述，“更强大、更有能力的模型将在复杂的模式和/或多个功能上表现更好。”

参考资料：

1. OllamaFunctions（LangChain）
2. Ollama（GitHub）