github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-03 03:59:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

core[minor], ...: add tool calls message (#18947)

Browse Source 
core[minor], langchain[patch], openai[minor], anthropic[minor], fireworks[minor], groq[minor], mistralai[minor]

```python
class ToolCall(TypedDict):
    name: str
    args: Dict[str, Any]
    id: Optional[str]

class InvalidToolCall(TypedDict):
    name: Optional[str]
    args: Optional[str]
    id: Optional[str]
    error: Optional[str]

class ToolCallChunk(TypedDict):
    name: Optional[str]
    args: Optional[str]
    id: Optional[str]
    index: Optional[int]


class AIMessage(BaseMessage):
    ...
    tool_calls: List[ToolCall] = []
    invalid_tool_calls: List[InvalidToolCall] = []
    ...


class AIMessageChunk(AIMessage, BaseMessageChunk):
    ...
    tool_call_chunks: Optional[List[ToolCallChunk]] = None
    ...
```
Important considerations:
- Parsing logic occurs within different providers;
- ~Changing output type is a breaking change for anyone doing explicit
type checking;~
- ~Langsmith rendering will need to be updated:
https://github.com/langchain-ai/langchainplus/pull/3561~
- ~Langserve will need to be updated~
- Adding chunks:
- ~AIMessage + ToolCallsMessage = ToolCallsMessage if either has
non-null .tool_calls.~
- Tool call chunks are appended, merging when having equal values of
`index`.
  - additional_kwargs accumulate the normal way.
- During streaming:
- ~Messages can change types (e.g., from AIMessageChunk to
AIToolCallsMessageChunk)~
- Output parsers parse additional_kwargs (during .invoke they read off
tool calls).

Packages outside of `partners/`:
- https://github.com/langchain-ai/langchain-cohere/pull/7
- https://github.com/langchain-ai/langchain-google/pull/123/files

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
This commit is contained in:
Bagatur
2024-04-09 18:41:42 -05:00
committed by GitHub
parent 00552918ac
commit 9514bc4d67
31 changed files with 2347 additions and 389 deletions
Download Patch File Download Diff File Expand all files Collapse all files

423
cookbook/tool_call_messages.ipynb Normal file
View File

@@ -0,0 +1,423 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "c48812ed-35bd-4fbe-9a2c-6c7335e5645e",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/chestercurme/repos/langchain/libs/core/langchain_core/_api/beta_decorator.py:87: LangChainBetaWarning: The function `bind_tools` is in beta. It is actively being worked on, so the API may change.\n",
" warn_beta(\n"
]
}
],
"source": [
"from langchain_anthropic import ChatAnthropic\n",
"from langchain_core.runnables import ConfigurableField\n",
"from langchain_core.tools import tool\n",
"from langchain_openai import ChatOpenAI\n",
"\n",
"\n",
"@tool\n",
"def multiply(x: float, y: float) -> float:\n",
" \"\"\"Multiply 'x' times 'y'.\"\"\"\n",
" return x * y\n",
"\n",
"\n",
"@tool\n",
"def exponentiate(x: float, y: float) -> float:\n",
" \"\"\"Raise 'x' to the 'y'.\"\"\"\n",
" return x**y\n",
"\n",
"\n",
"@tool\n",
"def add(x: float, y: float) -> float:\n",
" \"\"\"Add 'x' and 'y'.\"\"\"\n",
" return x + y\n",
"\n",
"\n",
"tools = [multiply, exponentiate, add]\n",
"\n",
"gpt35 = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0).bind_tools(tools)\n",
"claude3 = ChatAnthropic(model=\"claude-3-sonnet-20240229\").bind_tools(tools)\n",
"llm_with_tools = gpt35.configurable_alternatives(\n",
" ConfigurableField(id=\"llm\"), default_key=\"gpt35\", claude3=claude3\n",
")"
]
},
{
"cell_type": "markdown",
"id": "4719ebdb-ad50-468e-9b30-fb5fb086e140",
"metadata": {},
"source": [
"# AgentExecutor"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "b98feaa5-8c2d-4125-9519-67114a1fef31",
"metadata": {},
"outputs": [],
"source": [
"from typing import List, Tuple, Union\n",
"\n",
"from langchain.agents import AgentExecutor\n",
"from langchain.agents.output_parsers.openai_tools import OpenAIToolAgentAction\n",
"from langchain_core.agents import AgentFinish, _convert_agent_action_to_messages\n",
"from langchain_core.messages import (\n",
" AIMessage,\n",
" BaseMessage,\n",
" ToolMessage,\n",
")\n",
"from langchain_core.prompts import ChatPromptTemplate\n",
"from langchain_core.runnables import RunnablePassthrough\n",
"\n",
"\n",
"def actions_observations_to_messages(\n",
" steps: List[Tuple[OpenAIToolAgentAction, str]],\n",
") -> List[BaseMessage]:\n",
" messages = []\n",
" for action, observation in steps:\n",
" messages.extend([m for m in action.message_log if m not in messages])\n",
" messages.append(ToolMessage(observation, tool_call_id=action.tool_call_id))\n",
" return messages\n",
"\n",
"\n",
"def messages_to_action(\n",
" msg: AIMessage,\n",
") -> Union[List[OpenAIToolAgentAction], AgentFinish]:\n",
" if isinstance(msg, AIMessage) and msg.tool_calls is not None:\n",
" actions = []\n",
" for tool_call in msg.tool_calls:\n",
" actions.append(\n",
" OpenAIToolAgentAction(\n",
" tool=tool_call.name,\n",
" tool_input=tool_call.args,\n",
" tool_call_id=tool_call.id,\n",
" message_log=[msg],\n",
" log=\"\",\n",
" )\n",
" )\n",
" return actions\n",
" else:\n",
" return AgentFinish(return_values={\"output\": msg.content}, log=\"\")\n",
"\n",
"\n",
"prompt = ChatPromptTemplate.from_messages(\n",
" [\n",
" (\"system\", \"You're a helpful assistant with access to tools\"),\n",
" (\"human\", \"{input}\"),\n",
" (\"placeholder\", \"{agent_scratchpad}\"),\n",
" ]\n",
")\n",
"\n",
"agent = (\n",
" RunnablePassthrough.assign(\n",
" agent_scratchpad=lambda x: actions_observations_to_messages(\n",
" x[\"intermediate_steps\"]\n",
" ),\n",
" )\n",
" | prompt\n",
" | llm_with_tools\n",
" | messages_to_action\n",
")\n",
"\n",
"agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "b4c0fc7a-80bb-4bb8-a87b-7388291ae8b6",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\u001b[0m\u001b[33;1m\u001b[1;3m300.03770462067547\u001b[0m\u001b[32;1m\u001b[1;3m\u001b[0m\u001b[38;5;200m\u001b[1;3m-900.8841\u001b[0m\u001b[32;1m\u001b[1;3m\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"{'input': \"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\",\n",
" 'output': 'The result of \\\\(3 + 5^{2.743}\\\\) is approximately 300.04, and the result of \\\\(17.24 - 918.1241\\\\) is approximately -900.88.'}"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.invoke(\n",
" {\"input\": \"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"}\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "41a3a3c8-185d-4861-b6f0-7592668feb62",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/chestercurme/repos/langchain/libs/partners/anthropic/langchain_anthropic/chat_models.py:336: UserWarning: stream: Tool use is not yet supported in streaming mode.\n",
" warnings.warn(\"stream: Tool use is not yet supported in streaming mode.\")\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[32;1m\u001b[1;3m\u001b[0m\u001b[33;1m\u001b[1;3m82.65606421491815\u001b[0m"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/chestercurme/repos/langchain/libs/partners/anthropic/langchain_anthropic/chat_models.py:336: UserWarning: stream: Tool use is not yet supported in streaming mode.\n",
" warnings.warn(\"stream: Tool use is not yet supported in streaming mode.\")\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[32;1m\u001b[1;3m\u001b[0m\u001b[38;5;200m\u001b[1;3m85.65606421491815\u001b[0m"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/chestercurme/repos/langchain/libs/partners/anthropic/langchain_anthropic/chat_models.py:336: UserWarning: stream: Tool use is not yet supported in streaming mode.\n",
" warnings.warn(\"stream: Tool use is not yet supported in streaming mode.\")\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[32;1m\u001b[1;3m\u001b[0m\u001b[38;5;200m\u001b[1;3m-900.8841\u001b[0m"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/chestercurme/repos/langchain/libs/partners/anthropic/langchain_anthropic/chat_models.py:336: UserWarning: stream: Tool use is not yet supported in streaming mode.\n",
" warnings.warn(\"stream: Tool use is not yet supported in streaming mode.\")\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[32;1m\u001b[1;3m\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"{'input': \"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\",\n",
" 'output': 'Therefore, 17.24 - 918.1241 = -900.8841'}"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor = AgentExecutor(\n",
" agent=agent.with_config(configurable={\"llm\": \"claude3\"}), tools=tools, verbose=True\n",
")\n",
"agent_executor.invoke(\n",
" {\"input\": \"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"},\n",
")"
]
},
{
"cell_type": "markdown",
"id": "9c186263-1b98-4cb2-b6d1-71f65eb0d811",
"metadata": {},
"source": [
"# LangGraph"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "28fc2c60-7dbc-428a-8983-1a6a15ea30d2",
"metadata": {},
"outputs": [],
"source": [
"import operator\n",
"from typing import Annotated, Sequence, TypedDict\n",
"\n",
"from langchain_core.messages import AIMessage, BaseMessage, HumanMessage\n",
"from langchain_core.runnables import RunnableLambda\n",
"from langgraph.graph import END, StateGraph\n",
"\n",
"\n",
"class AgentState(TypedDict):\n",
" messages: Annotated[Sequence[BaseMessage], operator.add]\n",
"\n",
"\n",
"def should_continue(state):\n",
" return \"continue\" if state[\"messages\"][-1].tool_calls is not None else \"end\"\n",
"\n",
"\n",
"def call_model(state, config):\n",
" return {\"messages\": [llm_with_tools.invoke(state[\"messages\"], config=config)]}\n",
"\n",
"\n",
"def _invoke_tool(tool_call):\n",
" tool = {tool.name: tool for tool in tools}[tool_call.name]\n",
" return ToolMessage(tool.invoke(tool_call.args), tool_call_id=tool_call.id)\n",
"\n",
"\n",
"tool_executor = RunnableLambda(_invoke_tool)\n",
"\n",
"\n",
"def call_tools(state):\n",
" last_message = state[\"messages\"][-1]\n",
" return {\"messages\": tool_executor.batch(last_message.tool_calls)}\n",
"\n",
"\n",
"workflow = StateGraph(AgentState)\n",
"workflow.add_node(\"agent\", call_model)\n",
"workflow.add_node(\"action\", call_tools)\n",
"workflow.set_entry_point(\"agent\")\n",
"workflow.add_conditional_edges(\n",
" \"agent\",\n",
" should_continue,\n",
" {\n",
" \"continue\": \"action\",\n",
" \"end\": END,\n",
" },\n",
")\n",
"workflow.add_edge(\"action\", \"agent\")\n",
"graph = workflow.compile()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "24463798-74e6-4c39-8092-7a1524d83225",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'messages': [HumanMessage(content=\"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"),\n",
" AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_kbBUUeqK75fZZqDTvu8aif7Z', 'function': {'arguments': '{\"x\": 8, \"y\": 2.743}', 'name': 'exponentiate'}, 'type': 'function'}, {'id': 'call_pBD8daSyXidXnrIyG4vG5C9O', 'function': {'arguments': '{\"x\": 17.24, \"y\": -918.1241}', 'name': 'add'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 58, 'prompt_tokens': 168, 'total_tokens': 226}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-8e1d9687-611c-4c8e-9fcd-ef6e48bd22a6-0', tool_calls=[ToolCall(name='exponentiate', args={'x': 8, 'y': 2.743}, id='call_kbBUUeqK75fZZqDTvu8aif7Z'), ToolCall(name='add', args={'x': 17.24, 'y': -918.1241}, id='call_pBD8daSyXidXnrIyG4vG5C9O')]),\n",
" ToolMessage(content='300.03770462067547', tool_call_id='call_kbBUUeqK75fZZqDTvu8aif7Z'),\n",
" ToolMessage(content='-900.8841', tool_call_id='call_pBD8daSyXidXnrIyG4vG5C9O'),\n",
" AIMessage(content='The result of \\\\(3 + 5^{2.743}\\\\) is approximately 300.04, and the result of \\\\(17.24 - 918.1241\\\\) is approximately -900.88.', response_metadata={'token_usage': {'completion_tokens': 44, 'prompt_tokens': 251, 'total_tokens': 295}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'stop', 'logprobs': None}, id='run-47fe5cbc-3f25-44c3-85b2-6540c3054a77-0')]}"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"graph.invoke(\n",
" {\n",
" \"messages\": [\n",
" HumanMessage(\n",
" \"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"\n",
" )\n",
" ]\n",
" }\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "073c074e-d722-42e0-85ec-c62c079207e4",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'messages': [HumanMessage(content=\"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"),\n",
" AIMessage(content=[{'text': \"Okay, let's break this down into steps:\", 'type': 'text'}, {'id': 'toolu_01DJkSDpB8ztmJx2DLNbc3eW', 'input': {'x': 5, 'y': 2.743}, 'name': 'exponentiate', 'type': 'tool_use'}], response_metadata={'id': 'msg_01KuVNohyJr24cPhJkY3XVtt', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 450, 'output_tokens': 84}}, id='run-336cdfb6-0fe4-4d7a-9946-9f01c2eb41ae-0', tool_calls=[ToolCall(name='exponentiate', args={'x': 5, 'y': 2.743}, id='toolu_01DJkSDpB8ztmJx2DLNbc3eW', index=1)]),\n",
" ToolMessage(content='82.65606421491815', tool_call_id='toolu_01DJkSDpB8ztmJx2DLNbc3eW'),\n",
" AIMessage(content=[{'text': 'To get 5 raised to the 2.743 power.', 'type': 'text'}, {'id': 'toolu_01MKQqnDw5CtyuKjQP8YG1FX', 'input': {'x': 3, 'y': 82.65606421491815}, 'name': 'add', 'type': 'tool_use'}], response_metadata={'id': 'msg_01UBsKkvA4StUR4NEvoFFFep', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 552, 'output_tokens': 91}}, id='run-9d25b7bd-58aa-47dd-933f-15459b24b2c2-0', tool_calls=[ToolCall(name='add', args={'x': 3, 'y': 82.65606421491815}, id='toolu_01MKQqnDw5CtyuKjQP8YG1FX', index=1)]),\n",
" ToolMessage(content='85.65606421491815', tool_call_id='toolu_01MKQqnDw5CtyuKjQP8YG1FX'),\n",
" AIMessage(content=[{'text': 'So 3 plus 5 raised to the 2.743 power is 85.656.\\n\\nFor the second part:', 'type': 'text'}, {'id': 'toolu_019Wb2zPouCR3dw2bSKvCRUL', 'input': {'x': 17.24, 'y': -918.1241}, 'name': 'add', 'type': 'tool_use'}], response_metadata={'id': 'msg_01Y2H2L8FWcDtVkCtuosie2P', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 661, 'output_tokens': 105}}, id='run-e553c1e3-24ba-4e1b-93ba-6f1985932db4-0', tool_calls=[ToolCall(name='add', args={'x': 17.24, 'y': -918.1241}, id='toolu_019Wb2zPouCR3dw2bSKvCRUL', index=1)]),\n",
" ToolMessage(content='-900.8841', tool_call_id='toolu_019Wb2zPouCR3dw2bSKvCRUL'),\n",
" AIMessage(content='Therefore, 17.24 - 918.1241 = -900.8841', response_metadata={'id': 'msg_01Q14dqvaCD2eA4zwrUvxTcF', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 782, 'output_tokens': 24}}, id='run-f6b6e525-2df6-4617-9bb3-b39d5cc963a9-0')]}"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"graph.invoke(\n",
" {\n",
" \"messages\": [\n",
" HumanMessage(\n",
" \"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"\n",
" )\n",
" ]\n",
" },\n",
" config={\"configurable\": {\"llm\": \"claude3\"}},\n",
")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.4"
}
},
"nbformat": 4,
"nbformat_minor": 5
}