PREREQUISITES
This guide assumes familiarity with the following concepts:
Sometimes we want to invoke a Runnable within a RunnableSequence with constant arguments that are not part of the output of the preceding Runnable in the sequence, and which are not part of the user input. We can use the Runnable.bind() method to set these arguments ahead of time.
有时，我们想使用常量参数来调用 RunnableSequence 中的 Runnable，这些参数既不是序列中前一个 Runnable 的输出，也不是用户输入。我们可以使用 Runnable.bind() 方法提前设置这些参数。
Suppose we have a simple prompt + model chain:
假设我们有一个简单的提示+模型链：
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import ChatOpenAI
prompt = ChatPromptTemplate.from_messages(
[
(
"system",
"Write out the following equation using algebraic symbols then solve it. Use the format\n\nEQUATION:...\nSOLUTION:...\n\n",
),
("human", "{equation_statement}"),
]
)
model = ChatOpenAI(temperature=0)
runnable = (
{"equation_statement": RunnablePassthrough()} | prompt | model | StrOutputParser()
)
print(runnable.invoke("x raised to the third plus seven equals 12"))
API Reference: StrOutputParser | ChatPromptTemplate | RunnablePassthrough | ChatOpenAI
EQUATION: x^3 + 7 = 12
SOLUTION:
Subtract 7 from both sides:
x^3 = 5
Take the cube root of both sides:
x = ∛5
and want to call the model with certain stop words so that we shorten the output as is useful in certain types of prompting techniques. While we can pass some arguments into the constructor, other runtime args use the .bind() method as follows:
并希望使用某些停用词来调用模型，以便我们缩短输出，这在某些类型的提示技术中很有用。虽然我们可以将一些参数传递给构造函数，但其他运行时参数使用 .bind() 方法，如下所示：
runnable = (
{"equation_statement": RunnablePassthrough()}
| prompt
| model.bind(stop="SOLUTION")
| StrOutputParser()
)
print(runnable.invoke("x raised to the third plus seven equals 12"))
EQUATION: x^3 + 7 = 12
What you can bind to a Runnable will depend on the extra parameters you can pass when invoking it.
您可以绑定到 Runnable 的内容取决于您在调用它时可以传递的额外参数。
Attaching OpenAI tools
Another common use-case is tool calling. While you should generally use the .bind_tools() method for tool-calling models, you can also bind provider-specific args directly if you want lower level control:
另一个常见的用例是工具调用。虽然您通常应该使用 .bind_tools() 方法来调用工具模型，但如果您想要较低级别的控制，您也可以直接绑定提供程序特定的参数：
tools = [
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
},
"required": ["location"],
},
},
}
]
model = ChatOpenAI(model="gpt-3.5-turbo-1106").bind(tools=tools)
model.invoke("What's the weather in SF, NYC and LA?")
AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_z0OU2CytqENVrRTI6T8DkI3u', 'function': {'arguments': '{"location": "San Francisco, CA", "unit": "celsius"}', 'name': 'get_current_weather'}, 'type': 'function'}, {'id': 'call_ft96IJBh0cMKkQWrZjNg4bsw', 'function': {'arguments': '{"location": "New York, NY", "unit": "celsius"}', 'name': 'get_current_weather'}, 'type': 'function'}, {'id': 'call_tfbtGgCLmuBuWgZLvpPwvUMH', 'function': {'arguments': '{"location": "Los Angeles, CA", "unit": "celsius"}', 'name': 'get_current_weather'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 84, 'prompt_tokens': 85, 'total_tokens': 169}, 'model_name': 'gpt-3.5-turbo-1106', 'system_fingerprint': 'fp_77a673219d', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-d57ad5fa-b52a-4822-bc3e-74f838697e18-0', tool_calls=[{'name': 'get_current_weather', 'args': {'location': 'San Francisco, CA', 'unit': 'celsius'}, 'id': 'call_z0OU2CytqENVrRTI6T8DkI3u'}, {'name': 'get_current_weather', 'args': {'location': 'New York, NY', 'unit': 'celsius'}, 'id': 'call_ft96IJBh0cMKkQWrZjNg4bsw'}, {'name': 'get_current_weather', 'args': {'location': 'Los Angeles, CA', 'unit': 'celsius'}, 'id': 'call_tfbtGgCLmuBuWgZLvpPwvUMH'}])
