mirror of
https://github.com/hwchase17/langchain.git
synced 2025-06-04 14:13:29 +00:00
docs: add component page for tool calls (#20282)
Note: includes links to API reference pages for ToolCall and other objects that currently don't exist (e.g., https://api.python.langchain.com/en/latest/messages/langchain_core.messages.tool.ToolCall.html#langchain_core.messages.tool.ToolCall).
This commit is contained in:
ccurme
GitHub
parent
6608089030
commit
f02e55aaf7
@ -1,68 +1,133 @@
|
|||||||
---
|
---
|
||||||
sidebar_position: 2
|
sidebar_position: 2
|
||||||
title: Function calling
|
title: Tool/function calling
|
||||||
---
|
---
|
||||||
|
|
||||||
# Function calling
|
# Tool calling
|
||||||
|
|
||||||
A growing number of chat models, like
|
:::info
|
||||||
[OpenAI](https://platform.openai.com/docs/guides/function-calling),
|
We use the term tool calling interchangeably with function calling. Although
|
||||||
[Gemini](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/function-calling),
|
function calling is sometimes meant to refer to invocations of a single function,
|
||||||
etc., have a function-calling API that lets you describe functions and
|
we treat all models as though they can return multiple tool or function calls in
|
||||||
their arguments, and have the model return a JSON object with a function
|
each message.
|
||||||
to invoke and the inputs to that function. Function-calling is extremely
|
:::
|
||||||
useful for building [tool-using chains and
|
|
||||||
agents](/docs/use_cases/tool_use/), and for getting
|
|
||||||
structured outputs from models more generally.
|
|
||||||
|
|
||||||
LangChain comes with a number of utilities to make function-calling
|
# Calling Tools
|
||||||
easy. Namely, it comes with:
|
|
||||||
|
|
||||||
- simple syntax for binding functions to models
|
Tool calling allows a model to respond to a given prompt by generating output that
|
||||||
- converters for formatting various types of objects to the expected
|
matches a user-defined schema. While the name implies that the model is performing
|
||||||
function schemas
|
some action, this is actually not the case! The model is coming up with the
|
||||||
- output parsers for extracting the function invocations from API
|
arguments to a tool, and actually running the tool (or not) is up to the user -
|
||||||
responses
|
for example, if you want to [extract output matching some schema](/docs/use_cases/extraction/)
|
||||||
- chains for getting structured outputs from a model, built on top of
|
from unstructured text, you could give the model an "extraction" tool that takes
|
||||||
function calling
|
parameters matching the desired schema, then treat the generated output as your final
|
||||||
|
result.
|
||||||
|
|
||||||
We’ll focus here on the first two points. For a detailed guide on output
|
A tool call includes a name, arguments dict, and an optional identifier. The
|
||||||
parsing check out the [OpenAI Tools output
|
arguments dict is structured `{argument_name: argument_value}`.
|
||||||
parsers](/docs/modules/model_io/output_parsers/types/openai_tools/)
|
|
||||||
and to see the structured output chains check out the [Structured output
|
|
||||||
guide](/docs/modules/model_io/chat/structured_output/).
|
|
||||||
|
|
||||||
Before getting started make sure you have `langchain-core` installed.
|
Many LLM providers, including [Anthropic](https://www.anthropic.com/),
|
||||||
|
[Cohere](https://cohere.com/), [Google](https://cloud.google.com/vertex-ai),
|
||||||
|
[Mistral](https://mistral.ai/), [OpenAI](https://openai.com/), and others,
|
||||||
|
support variants of a tool calling feature. These features typically allow requests
|
||||||
|
to the LLM to include available tools and their schemas, and for responses to include
|
||||||
|
calls to these tools. For instance, given a search engine tool, an LLM might handle a
|
||||||
|
query by first issuing a call to the search engine. The system calling the LLM can
|
||||||
|
receive the tool call, execute it, and return the output to the LLM to inform its
|
||||||
|
response. LangChain includes a suite of [built-in tools](/docs/integrations/tools/)
|
||||||
|
and supports several methods for defining your own [custom tools](/docs/modules/tools/custom_tools).
|
||||||
|
Tool-calling is extremely useful for building [tool-using chains and agents](/docs/use_cases/tool_use),
|
||||||
|
and for getting structured outputs from models more generally.
|
||||||
|
|
||||||
|
Providers adopt different conventions for formatting tool schemas and tool calls.
|
||||||
|
For instance, Anthropic returns tool calls as parsed structures within a larger content block:
|
||||||
|
```
|
||||||
|
[
|
||||||
|
{
|
||||||
|
"text": "<thinking>\nI should use a tool.\n</thinking>",
|
||||||
|
"type": "text"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"id": "id_value",
|
||||||
|
"input": {"arg_name": "arg_value"},
|
||||||
|
"name": "tool_name",
|
||||||
|
"type": "tool_use"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
```
|
||||||
|
whereas OpenAI separates tool calls into a distinct parameter, with arguments as JSON strings:
|
||||||
|
```
|
||||||
|
{
|
||||||
|
"tool_calls": [
|
||||||
|
{
|
||||||
|
"id": "id_value",
|
||||||
|
"function": {
|
||||||
|
"arguments": '{"arg_name": "arg_value"}',
|
||||||
|
"name": "tool_name"
|
||||||
|
},
|
||||||
|
"type": "function"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
```
|
||||||
|
LangChain implements standard interfaces for defining tools, passing them to LLMs,
|
||||||
|
and representing tool calls.
|
||||||
|
|
||||||
|
## Passing tools to LLMs
|
||||||
|
|
||||||
|
Chat models supporting tool calling features implement a `.bind_tools` method, which
|
||||||
|
receives a list of LangChain [tool objects](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.BaseTool.html#langchain_core.tools.BaseTool)
|
||||||
|
and binds them to the chat model in its expected format. Subsequent invocations of the
|
||||||
|
chat model will include tool schemas in its calls to the LLM.
|
||||||
|
|
||||||
|
For example, we can define the schema for custom tools using the `@tool` decorator
|
||||||
|
on Python functions:
|
||||||
|
|
||||||
```python
|
```python
|
||||||
%pip install -qU langchain-core langchain-openai
|
from langchain.tools import tool
|
||||||
|
|
||||||
|
|
||||||
|
@tool
|
||||||
|
def add(a: int, b: int) -> int:
|
||||||
|
"""Adds a and b."""
|
||||||
|
return a + b
|
||||||
|
|
||||||
|
|
||||||
|
@tool
|
||||||
|
def multiply(a: int, b: int) -> int:
|
||||||
|
"""Multiplies a and b."""
|
||||||
|
return a * b
|
||||||
|
|
||||||
|
|
||||||
|
tools = [add, multiply]
|
||||||
```
|
```
|
||||||
|
|
||||||
```python
|
Or below, we define the schema using Pydantic:
|
||||||
import getpass
|
|
||||||
import os
|
|
||||||
```
|
|
||||||
|
|
||||||
## Binding functions
|
|
||||||
|
|
||||||
A number of models implement helper methods that will take care of
|
|
||||||
formatting and binding different function-like objects to the model.
|
|
||||||
Let’s take a look at how we might take the following Pydantic function
|
|
||||||
schema and get different models to invoke it:
|
|
||||||
|
|
||||||
```python
|
```python
|
||||||
from langchain_core.pydantic_v1 import BaseModel, Field
|
from langchain_core.pydantic_v1 import BaseModel, Field
|
||||||
|
|
||||||
|
|
||||||
# Note that the docstrings here are crucial, as they will be passed along
|
# Note that the docstrings here are crucial, as they will be passed along
|
||||||
# to the model along with the class name.
|
# to the model along with the class name.
|
||||||
|
class Add(BaseModel):
|
||||||
|
"""Add two integers together."""
|
||||||
|
|
||||||
|
a: int = Field(..., description="First integer")
|
||||||
|
b: int = Field(..., description="Second integer")
|
||||||
|
|
||||||
|
|
||||||
class Multiply(BaseModel):
|
class Multiply(BaseModel):
|
||||||
"""Multiply two integers together."""
|
"""Multiply two integers together."""
|
||||||
|
|
||||||
a: int = Field(..., description="First integer")
|
a: int = Field(..., description="First integer")
|
||||||
b: int = Field(..., description="Second integer")
|
b: int = Field(..., description="Second integer")
|
||||||
|
|
||||||
|
|
||||||
|
tools = [Add, Multiply]
|
||||||
```
|
```
|
||||||
|
|
||||||
|
We can bind them to chat models as follows:
|
||||||
|
|
||||||
import Tabs from "@theme/Tabs";
|
import Tabs from "@theme/Tabs";
|
||||||
import TabItem from "@theme/TabItem";
|
import TabItem from "@theme/TabItem";
|
||||||
|
|
||||||
@ -72,230 +137,180 @@ import ChatModelTabs from "@theme/ChatModelTabs";
|
|||||||
customVarName="llm"
|
customVarName="llm"
|
||||||
fireworksParams={`model="accounts/fireworks/models/firefunction-v1", temperature=0`}
|
fireworksParams={`model="accounts/fireworks/models/firefunction-v1", temperature=0`}
|
||||||
hideGoogle={true}
|
hideGoogle={true}
|
||||||
hideAnthropic={true}
|
hideAnthropic={false}
|
||||||
/>
|
/>
|
||||||
|
|
||||||
We can use the `bind_tools()` method to handle converting
|
We can use the `bind_tools()` method to handle converting
|
||||||
`Multiply` to a "function" and binding it to the model (i.e.,
|
`Multiply` to a "tool" and binding it to the model (i.e.,
|
||||||
passing it in each time the model is invoked).
|
passing it in each time the model is invoked).
|
||||||
|
|
||||||
```python
|
```python
|
||||||
llm_with_tools = llm.bind_tools([Multiply])
|
llm_with_tools = llm.bind_tools(tools)
|
||||||
llm_with_tools.invoke("what's 3 * 12")
|
|
||||||
```
|
```
|
||||||
|
|
||||||
```text
|
## Tool calls
|
||||||
AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_Q8ZQ97Qrj5zalugSkYMGV1Uo', 'function': {'arguments': '{"a":3,"b":12}', 'name': 'Multiply'}, 'type': 'function'}]})
|
|
||||||
```
|
|
||||||
|
|
||||||
We can add a tool parser to extract the tool calls from the generated
|
If tool calls are included in a LLM response, they are attached to the corresponding
|
||||||
message to JSON:
|
[message](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessage.html#langchain_core.messages.ai.AIMessage)
|
||||||
|
or [message chunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html#langchain_core.messages.ai.AIMessageChunk)
|
||||||
|
as a list of [tool call](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.tool.ToolCall.html#langchain_core.messages.tool.ToolCall)
|
||||||
|
objects in the `.tool_calls` attribute. A `ToolCall` is a typed dict that includes a
|
||||||
|
tool name, dict of argument values, and (optionally) an identifier. Messages with no
|
||||||
|
tool calls default to an empty list for this attribute.
|
||||||
|
|
||||||
|
Example:
|
||||||
|
|
||||||
```python
|
```python
|
||||||
from langchain_core.output_parsers.openai_tools import JsonOutputToolsParser
|
query = "What is 3 * 12? Also, what is 11 + 49?"
|
||||||
|
|
||||||
tool_chain = llm_with_tools | JsonOutputToolsParser()
|
llm_with_tools.invoke(query).tool_calls
|
||||||
tool_chain.invoke("what's 3 * 12")
|
|
||||||
```
|
```
|
||||||
|
|
||||||
```text
|
```text
|
||||||
[{'type': 'Multiply', 'args': {'a': 3, 'b': 12}}]
|
[{'name': 'Multiply',
|
||||||
|
'args': {'a': 3, 'b': 12},
|
||||||
|
'id': 'call_viACG45wBz9jYzljHIwHamXw'},
|
||||||
|
{'name': 'Add',
|
||||||
|
'args': {'a': 11, 'b': 49},
|
||||||
|
'id': 'call_JMFUqoi5L27rGeMuII4MJMWo'}]
|
||||||
```
|
```
|
||||||
|
|
||||||
Or back to the original Pydantic class:
|
The `.tool_calls` attribute should contain valid tool calls. Note that on occasion,
|
||||||
|
model providers may output malformed tool calls (e.g., arguments that are not
|
||||||
|
valid JSON). When parsing fails in these cases, instances
|
||||||
|
of [InvalidToolCall](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.tool.InvalidToolCall.html#langchain_core.messages.tool.InvalidToolCall)
|
||||||
|
are populated in the `.invalid_tool_calls` attribute. An `InvalidToolCall` can have
|
||||||
|
a name, string arguments, identifier, and error message.
|
||||||
|
|
||||||
|
If desired, [output parsers](/docs/modules/model_io/output_parsers) can further
|
||||||
|
process the output. For example, we can convert back to the original Pydantic class:
|
||||||
|
|
||||||
```python
|
```python
|
||||||
from langchain_core.output_parsers.openai_tools import PydanticToolsParser
|
from langchain_core.output_parsers.openai_tools import PydanticToolsParser
|
||||||
|
|
||||||
tool_chain = llm_with_tools | PydanticToolsParser(tools=[Multiply])
|
chain = llm_with_tools | PydanticToolsParser(tools=[Multiply, Add])
|
||||||
tool_chain.invoke("what's 3 * 12")
|
chain.invoke(query)
|
||||||
```
|
```
|
||||||
|
|
||||||
```text
|
```text
|
||||||
[Multiply(a=3, b=12)]
|
[Multiply(a=3, b=12), Add(a=11, b=49)]
|
||||||
```
|
```
|
||||||
|
|
||||||
If our model isn’t using the tool, as is the case here, we can force
|
### Streaming
|
||||||
tool usage by specifying `tool_choice="any"` or by specifying the name
|
|
||||||
of the specific tool we want used:
|
When tools are called in a streaming context,
|
||||||
|
[message chunks](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html#langchain_core.messages.ai.AIMessageChunk)
|
||||||
|
will be populated with [tool call chunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.tool.ToolCallChunk.html#langchain_core.messages.tool.ToolCallChunk)
|
||||||
|
objects in a list via the `.tool_call_chunks` attribute. A `ToolCallChunk` includes
|
||||||
|
optional string fields for the tool `name`, `args`, and `id`, and includes an optional
|
||||||
|
integer field `index` that can be used to join chunks together. Fields are optional
|
||||||
|
because portions of a tool call may be streamed across different chunks (e.g., a chunk
|
||||||
|
that includes a substring of the arguments may have null values for the tool name and id).
|
||||||
|
|
||||||
|
Because message chunks inherit from their parent message class, an
|
||||||
|
[AIMessageChunk](https://api.python.langchain.com/en/latest/messages/langchain_core.messages.ai.AIMessageChunk.html#langchain_core.messages.ai.AIMessageChunk)
|
||||||
|
with tool call chunks will also include `.tool_calls` and `.invalid_tool_calls` fields.
|
||||||
|
These fields are parsed best-effort from the message's tool call chunks.
|
||||||
|
|
||||||
|
Note that not all providers currently support streaming for tool calls.
|
||||||
|
|
||||||
|
Example:
|
||||||
|
|
||||||
```python
|
```python
|
||||||
llm_with_tools = llm.bind_tools([Multiply], tool_choice="Multiply")
|
async for chunk in llm_with_tools.astream(query):
|
||||||
llm_with_tools.invoke("what's 3 * 12")
|
print(chunk.tool_call_chunks)
|
||||||
```
|
```
|
||||||
|
|
||||||
```text
|
```text
|
||||||
AIMessage(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_qIP2bJugb67LGvc6Zhwkvfqc', 'type': 'function', 'function': {'name': 'Multiply', 'arguments': '{"a": 3, "b": 12}'}}]})
|
[]
|
||||||
|
[{'name': 'Multiply', 'args': '', 'id': 'call_Al2xpR4uFPXQUDzGTSawMOah', 'index': 0}]
|
||||||
|
[{'name': None, 'args': '{"a"', 'id': None, 'index': 0}]
|
||||||
|
[{'name': None, 'args': ': 3, ', 'id': None, 'index': 0}]
|
||||||
|
[{'name': None, 'args': '"b": 1', 'id': None, 'index': 0}]
|
||||||
|
[{'name': None, 'args': '2}', 'id': None, 'index': 0}]
|
||||||
|
[{'name': 'Add', 'args': '', 'id': 'call_VV6ck8JSQ6joKtk2xGtNKgXf', 'index': 1}]
|
||||||
|
[{'name': None, 'args': '{"a"', 'id': None, 'index': 1}]
|
||||||
|
[{'name': None, 'args': ': 11,', 'id': None, 'index': 1}]
|
||||||
|
[{'name': None, 'args': ' "b": ', 'id': None, 'index': 1}]
|
||||||
|
[{'name': None, 'args': '49}', 'id': None, 'index': 1}]
|
||||||
|
[]
|
||||||
```
|
```
|
||||||
|
|
||||||
If we wanted to force that a tool is used (and that it is used only
|
Note that adding message chunks will merge their corresponding tool call chunks. This is the principle by which LangChain's various [tool output parsers](/docs/modules/model_io/output_parsers/types/openai_tools/) support streaming.
|
||||||
once), we can set the `tool_choice` argument to the name of the tool:
|
|
||||||
|
For example, below we accumulate tool call chunks:
|
||||||
|
|
||||||
```python
|
```python
|
||||||
llm_with_multiply = llm.bind_tools([Multiply], tool_choice="Multiply")
|
first = True
|
||||||
llm_with_multiply.invoke(
|
async for chunk in llm_with_tools.astream(query):
|
||||||
"make up some numbers if you really want but I'm not forcing you"
|
if first:
|
||||||
)
|
gathered = chunk
|
||||||
|
first = False
|
||||||
|
else:
|
||||||
|
gathered = gathered + chunk
|
||||||
|
|
||||||
|
print(gathered.tool_call_chunks)
|
||||||
```
|
```
|
||||||
|
|
||||||
```text
|
```text
|
||||||
AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_f3DApOzb60iYjTfOhVFhDRMI', 'function': {'arguments': '{"a":5,"b":10}', 'name': 'Multiply'}, 'type': 'function'}]})
|
[]
|
||||||
|
[{'name': 'Multiply', 'args': '', 'id': 'call_2MG1IGft6WmgMooqZgJ07JX6', 'index': 0}]
|
||||||
|
[{'name': 'Multiply', 'args': '{"a"', 'id': 'call_2MG1IGft6WmgMooqZgJ07JX6', 'index': 0}]
|
||||||
|
[{'name': 'Multiply', 'args': '{"a": 3, ', 'id': 'call_2MG1IGft6WmgMooqZgJ07JX6', 'index': 0}]
|
||||||
|
[{'name': 'Multiply', 'args': '{"a": 3, "b": 1', 'id': 'call_2MG1IGft6WmgMooqZgJ07JX6', 'index': 0}]
|
||||||
|
[{'name': 'Multiply', 'args': '{"a": 3, "b": 12}', 'id': 'call_2MG1IGft6WmgMooqZgJ07JX6', 'index': 0}]
|
||||||
|
[{'name': 'Multiply', 'args': '{"a": 3, "b": 12}', 'id': 'call_2MG1IGft6WmgMooqZgJ07JX6', 'index': 0}, {'name': 'Add', 'args': '', 'id': 'call_uGot9MOHDcz67Bj0h13c7QA5', 'index': 1}]
|
||||||
|
[{'name': 'Multiply', 'args': '{"a": 3, "b": 12}', 'id': 'call_2MG1IGft6WmgMooqZgJ07JX6', 'index': 0}, {'name': 'Add', 'args': '{"a"', 'id': 'call_uGot9MOHDcz67Bj0h13c7QA5', 'index': 1}]
|
||||||
|
[{'name': 'Multiply', 'args': '{"a": 3, "b": 12}', 'id': 'call_2MG1IGft6WmgMooqZgJ07JX6', 'index': 0}, {'name': 'Add', 'args': '{"a": 11,', 'id': 'call_uGot9MOHDcz67Bj0h13c7QA5', 'index': 1}]
|
||||||
|
[{'name': 'Multiply', 'args': '{"a": 3, "b": 12}', 'id': 'call_2MG1IGft6WmgMooqZgJ07JX6', 'index': 0}, {'name': 'Add', 'args': '{"a": 11, "b": ', 'id': 'call_uGot9MOHDcz67Bj0h13c7QA5', 'index': 1}]
|
||||||
|
[{'name': 'Multiply', 'args': '{"a": 3, "b": 12}', 'id': 'call_2MG1IGft6WmgMooqZgJ07JX6', 'index': 0}, {'name': 'Add', 'args': '{"a": 11, "b": 49}', 'id': 'call_uGot9MOHDcz67Bj0h13c7QA5', 'index': 1}]
|
||||||
|
[{'name': 'Multiply', 'args': '{"a": 3, "b": 12}', 'id': 'call_2MG1IGft6WmgMooqZgJ07JX6', 'index': 0}, {'name': 'Add', 'args': '{"a": 11, "b": 49}', 'id': 'call_uGot9MOHDcz67Bj0h13c7QA5', 'index': 1}]
|
||||||
```
|
```
|
||||||
|
|
||||||
For more see the [ChatOpenAI API
|
|
||||||
reference](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html#langchain_openai.chat_models.base.ChatOpenAI.bind_tools).
|
|
||||||
|
|
||||||
## Defining functions schemas
|
|
||||||
|
|
||||||
In case you need to access function schemas directly, LangChain has a built-in converter that can turn
|
|
||||||
Python functions, Pydantic classes, and LangChain Tools into the OpenAI format JSON schema:
|
|
||||||
|
|
||||||
### Python function
|
|
||||||
|
|
||||||
```python
|
```python
|
||||||
import json
|
print(type(gathered.tool_call_chunks[0]["args"]))
|
||||||
|
|
||||||
from langchain_core.utils.function_calling import convert_to_openai_tool
|
|
||||||
|
|
||||||
|
|
||||||
def multiply(a: int, b: int) -> int:
|
|
||||||
"""Multiply two integers together.
|
|
||||||
|
|
||||||
Args:
|
|
||||||
a: First integer
|
|
||||||
b: Second integer
|
|
||||||
"""
|
|
||||||
return a * b
|
|
||||||
|
|
||||||
|
|
||||||
print(json.dumps(convert_to_openai_tool(multiply), indent=2))
|
|
||||||
```
|
```
|
||||||
|
|
||||||
```text
|
```text
|
||||||
{
|
<class 'str'>
|
||||||
"type": "function",
|
|
||||||
"function": {
|
|
||||||
"name": "multiply",
|
|
||||||
"description": "Multiply two integers together.",
|
|
||||||
"parameters": {
|
|
||||||
"type": "object",
|
|
||||||
"properties": {
|
|
||||||
"a": {
|
|
||||||
"type": "integer",
|
|
||||||
"description": "First integer"
|
|
||||||
},
|
|
||||||
"b": {
|
|
||||||
"type": "integer",
|
|
||||||
"description": "Second integer"
|
|
||||||
}
|
|
||||||
},
|
|
||||||
"required": [
|
|
||||||
"a",
|
|
||||||
"b"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
```
|
```
|
||||||
|
|
||||||
### Pydantic class
|
And below we accumulate tool calls to demonstrate partial parsing:
|
||||||
|
|
||||||
```python
|
```python
|
||||||
from langchain_core.pydantic_v1 import BaseModel, Field
|
first = True
|
||||||
|
async for chunk in llm_with_tools.astream(query):
|
||||||
|
if first:
|
||||||
|
gathered = chunk
|
||||||
|
first = False
|
||||||
|
else:
|
||||||
|
gathered = gathered + chunk
|
||||||
|
|
||||||
|
print(gathered.tool_calls)
|
||||||
class multiply(BaseModel):
|
|
||||||
"""Multiply two integers together."""
|
|
||||||
|
|
||||||
a: int = Field(..., description="First integer")
|
|
||||||
b: int = Field(..., description="Second integer")
|
|
||||||
|
|
||||||
|
|
||||||
print(json.dumps(convert_to_openai_tool(multiply), indent=2))
|
|
||||||
```
|
```
|
||||||
|
|
||||||
```text
|
```text
|
||||||
{
|
[]
|
||||||
"type": "function",
|
[]
|
||||||
"function": {
|
[{'name': 'Multiply', 'args': {}, 'id': 'call_z3B4o82SQDY5NCnmrXIcVQo4'}]
|
||||||
"name": "multiply",
|
[{'name': 'Multiply', 'args': {'a': 3}, 'id': 'call_z3B4o82SQDY5NCnmrXIcVQo4'}]
|
||||||
"description": "Multiply two integers together.",
|
[{'name': 'Multiply', 'args': {'a': 3, 'b': 1}, 'id': 'call_z3B4o82SQDY5NCnmrXIcVQo4'}]
|
||||||
"parameters": {
|
[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_z3B4o82SQDY5NCnmrXIcVQo4'}]
|
||||||
"type": "object",
|
[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_z3B4o82SQDY5NCnmrXIcVQo4'}]
|
||||||
"properties": {
|
[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_z3B4o82SQDY5NCnmrXIcVQo4'}, {'name': 'Add', 'args': {}, 'id': 'call_zPAyMWr8hN1q083GWGX2dSiB'}]
|
||||||
"a": {
|
[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_z3B4o82SQDY5NCnmrXIcVQo4'}, {'name': 'Add', 'args': {'a': 11}, 'id': 'call_zPAyMWr8hN1q083GWGX2dSiB'}]
|
||||||
"description": "First integer",
|
[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_z3B4o82SQDY5NCnmrXIcVQo4'}, {'name': 'Add', 'args': {'a': 11}, 'id': 'call_zPAyMWr8hN1q083GWGX2dSiB'}]
|
||||||
"type": "integer"
|
[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_z3B4o82SQDY5NCnmrXIcVQo4'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_zPAyMWr8hN1q083GWGX2dSiB'}]
|
||||||
},
|
[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_z3B4o82SQDY5NCnmrXIcVQo4'}, {'name': 'Add', 'args': {'a': 11, 'b': 49}, 'id': 'call_zPAyMWr8hN1q083GWGX2dSiB'}]
|
||||||
"b": {
|
|
||||||
"description": "Second integer",
|
|
||||||
"type": "integer"
|
|
||||||
}
|
|
||||||
},
|
|
||||||
"required": [
|
|
||||||
"a",
|
|
||||||
"b"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
```
|
```
|
||||||
|
|
||||||
### LangChain Tool
|
|
||||||
|
|
||||||
```python
|
```python
|
||||||
from typing import Any, Type
|
print(type(gathered.tool_calls[0]["args"]))
|
||||||
|
|
||||||
from langchain_core.tools import BaseTool
|
|
||||||
|
|
||||||
|
|
||||||
class MultiplySchema(BaseModel):
|
|
||||||
"""Multiply tool schema."""
|
|
||||||
|
|
||||||
a: int = Field(..., description="First integer")
|
|
||||||
b: int = Field(..., description="Second integer")
|
|
||||||
|
|
||||||
|
|
||||||
class Multiply(BaseTool):
|
|
||||||
args_schema: Type[BaseModel] = MultiplySchema
|
|
||||||
name: str = "multiply"
|
|
||||||
description: str = "Multiply two integers together."
|
|
||||||
|
|
||||||
def _run(self, a: int, b: int, **kwargs: Any) -> Any:
|
|
||||||
return a * b
|
|
||||||
|
|
||||||
|
|
||||||
# Note: we're passing in a Multiply object not the class itself.
|
|
||||||
print(json.dumps(convert_to_openai_tool(Multiply()), indent=2))
|
|
||||||
```
|
```
|
||||||
|
|
||||||
```text
|
```text
|
||||||
{
|
<class 'dict'>
|
||||||
"type": "function",
|
|
||||||
"function": {
|
|
||||||
"name": "multiply",
|
|
||||||
"description": "Multiply two integers together.",
|
|
||||||
"parameters": {
|
|
||||||
"type": "object",
|
|
||||||
"properties": {
|
|
||||||
"a": {
|
|
||||||
"description": "First integer",
|
|
||||||
"type": "integer"
|
|
||||||
},
|
|
||||||
"b": {
|
|
||||||
"description": "Second integer",
|
|
||||||
"type": "integer"
|
|
||||||
}
|
|
||||||
},
|
|
||||||
"required": [
|
|
||||||
"a",
|
|
||||||
"b"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
```
|
```
|
||||||
|
|
||||||
|
|
||||||
## Next steps
|
## Next steps
|
||||||
|
|
||||||
- **Output parsing**: See [OpenAI Tools output
|
- **Output parsing**: See [OpenAI Tools output
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user