mirror of
https://github.com/hwchase17/langchain.git
synced 2025-07-15 17:33:53 +00:00
docs: replace initialize_agent with create_react_agent in agent_vectorstore.ipynb (#31183)
Thank you for contributing to LangChain!
- [x] **PR title**: "package: description"
- Where "package" is whichever of langchain, core, etc. is being
modified. Use "docs: ..." for purely docs changes, "infra: ..." for CI
changes.
- Example: "core: add foobar LLM"
- [x] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** a description of the change
- **Issue:** the issue # it fixes, if applicable
- **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!
- [x] **Add tests and docs**: If you're adding a new integration, please
include
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.
- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, eyurtsev, ccurme, vbarda, hwchase17.
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
This commit is contained in:
Michael Li
GitHub
parent
ff9183fd3c
commit
0d59fe9789
@ -22,7 +22,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"execution_count": 1,
|
||||
"id": "e8d63d14-138d-4aa5-a741-7fd3537d00aa",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"OPENAI_API_KEY\"] = \"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "2e87c10a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -37,7 +49,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"execution_count": 3,
|
||||
"id": "0b7b772b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -54,19 +66,10 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"execution_count": 4,
|
||||
"id": "f2675861",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Running Chroma using direct local API.\n",
|
||||
"Using DuckDB in-memory for database. Data will be transient.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_community.document_loaders import TextLoader\n",
|
||||
"\n",
|
||||
@ -81,7 +84,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 5,
|
||||
"id": "bc5403d4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -93,17 +96,25 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 6,
|
||||
"id": "1431cded",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"USER_AGENT environment variable not set, consider setting it to identify your requests.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain_community.document_loaders import WebBaseLoader"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 7,
|
||||
"id": "915d3ff3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@ -113,16 +124,20 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": 8,
|
||||
"id": "96a2edf8",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Running Chroma using direct local API.\n",
|
||||
"Using DuckDB in-memory for database. Data will be transient.\n"
|
||||
"Created a chunk of size 2122, which is longer than the specified 1000\n",
|
||||
"Created a chunk of size 3187, which is longer than the specified 1000\n",
|
||||
"Created a chunk of size 1017, which is longer than the specified 1000\n",
|
||||
"Created a chunk of size 1049, which is longer than the specified 1000\n",
|
||||
"Created a chunk of size 1256, which is longer than the specified 1000\n",
|
||||
"Created a chunk of size 2321, which is longer than the specified 1000\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -135,14 +150,6 @@
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "71ecef90",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c0a6c031",
|
||||
@ -153,31 +160,30 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 43,
|
||||
"execution_count": 9,
|
||||
"id": "eb142786",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Import things that are needed generically\n",
|
||||
"from langchain.agents import AgentType, Tool, initialize_agent\n",
|
||||
"from langchain_openai import OpenAI"
|
||||
"from langchain.agents import Tool"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 44,
|
||||
"execution_count": 10,
|
||||
"id": "850bc4e9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tools = [\n",
|
||||
" Tool(\n",
|
||||
" name=\"State of Union QA System\",\n",
|
||||
" name=\"state_of_union_qa_system\",\n",
|
||||
" func=state_of_union.run,\n",
|
||||
" description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question.\",\n",
|
||||
" ),\n",
|
||||
" Tool(\n",
|
||||
" name=\"Ruff QA System\",\n",
|
||||
" name=\"ruff_qa_system\",\n",
|
||||
" func=ruff.run,\n",
|
||||
" description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question.\",\n",
|
||||
" ),\n",
|
||||
@ -186,94 +192,116 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 45,
|
||||
"id": "fc47f230",
|
||||
"execution_count": 11,
|
||||
"id": "70c461d8-aaca-4f2a-9a93-bf35841cc615",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Construct the agent. We will use the default agent type here.\n",
|
||||
"# See documentation for a full list of options.\n",
|
||||
"agent = initialize_agent(\n",
|
||||
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
||||
")"
|
||||
"from langgraph.prebuilt import create_react_agent\n",
|
||||
"\n",
|
||||
"agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 46,
|
||||
"id": "10ca2db8",
|
||||
"execution_count": 12,
|
||||
"id": "a6d2b911-3044-4430-a35b-75832bb45334",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"================================\u001b[1m Human Message \u001b[0m=================================\n",
|
||||
"\n",
|
||||
"What did biden say about ketanji brown jackson in the state of the union address?\n",
|
||||
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
|
||||
"Tool Calls:\n",
|
||||
" state_of_union_qa_system (call_26QlRdsptjEJJZjFsAUjEbaH)\n",
|
||||
" Call ID: call_26QlRdsptjEJJZjFsAUjEbaH\n",
|
||||
" Args:\n",
|
||||
" __arg1: What did Biden say about Ketanji Brown Jackson in the state of the union address?\n",
|
||||
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
|
||||
"Name: state_of_union_qa_system\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to find out what Biden said about Ketanji Brown Jackson in the State of the Union address.\n",
|
||||
"Action: State of Union QA System\n",
|
||||
"Action Input: What did Biden say about Ketanji Brown Jackson in the State of the Union address?\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
|
||||
" Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n",
|
||||
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
"In the State of the Union address, Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 46,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\n",
|
||||
" \"What did biden say about ketanji brown jackson in the state of the union address?\"\n",
|
||||
")"
|
||||
"input_message = {\n",
|
||||
" \"role\": \"user\",\n",
|
||||
" \"content\": \"What did biden say about ketanji brown jackson in the state of the union address?\",\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"for step in agent.stream(\n",
|
||||
" {\"messages\": [input_message]},\n",
|
||||
" stream_mode=\"values\",\n",
|
||||
"):\n",
|
||||
" step[\"messages\"][-1].pretty_print()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 47,
|
||||
"id": "4e91b811",
|
||||
"execution_count": 13,
|
||||
"id": "e836b4cd-abf7-49eb-be0e-b9ad501213f3",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"================================\u001b[1m Human Message \u001b[0m=================================\n",
|
||||
"\n",
|
||||
"Why use ruff over flake8?\n",
|
||||
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
|
||||
"Tool Calls:\n",
|
||||
" ruff_qa_system (call_KqDoWeO9bo9OAXdxOsCb6msC)\n",
|
||||
" Call ID: call_KqDoWeO9bo9OAXdxOsCb6msC\n",
|
||||
" Args:\n",
|
||||
" __arg1: Why use ruff over flake8?\n",
|
||||
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
|
||||
"Name: ruff_qa_system\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to find out the advantages of using ruff over flake8\n",
|
||||
"Action: Ruff QA System\n",
|
||||
"Action Input: What are the advantages of using ruff over flake8?\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.\u001b[0m\n",
|
||||
"There are a few reasons why someone might choose to use Ruff over Flake8:\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
"1. Larger rule set: Ruff implements over 800 rules, while Flake8 only implements around 200. This means that Ruff can catch more potential issues in your code.\n",
|
||||
"\n",
|
||||
"2. Better compatibility with other tools: Ruff is designed to work well with other tools like Black, isort, and type checkers like Mypy. This means that you can use Ruff alongside these tools to get more comprehensive feedback on your code.\n",
|
||||
"\n",
|
||||
"3. Automatic fixing of lint violations: Unlike Flake8, Ruff is capable of automatically fixing its own lint violations. This can save you time and effort when fixing issues in your code.\n",
|
||||
"\n",
|
||||
"4. Native implementation of popular Flake8 plugins: Ruff re-implements some of the most popular Flake8 plugins natively, which means you don't have to install and configure multiple plugins to get the same functionality.\n",
|
||||
"\n",
|
||||
"Overall, Ruff offers a more comprehensive and user-friendly experience compared to Flake8, making it a popular choice for many developers.\n",
|
||||
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
|
||||
"\n",
|
||||
"You might choose to use Ruff over Flake8 for several reasons:\n",
|
||||
"\n",
|
||||
"1. Ruff has a much larger rule set, implementing over 800 rules compared to Flake8's roughly 200, so it can catch more potential issues.\n",
|
||||
"2. Ruff is designed to work better with other tools like Black, isort, and type checkers like Mypy, providing more comprehensive code feedback.\n",
|
||||
"3. Ruff can automatically fix its own lint violations, which Flake8 cannot, saving time and effort.\n",
|
||||
"4. Ruff natively implements some popular Flake8 plugins, so you don't need to install and configure multiple plugins separately.\n",
|
||||
"\n",
|
||||
"Overall, Ruff offers a more comprehensive and user-friendly experience compared to Flake8.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 47,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"Why use ruff over flake8?\")"
|
||||
"input_message = {\n",
|
||||
" \"role\": \"user\",\n",
|
||||
" \"content\": \"Why use ruff over flake8?\",\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"for step in agent.stream(\n",
|
||||
" {\"messages\": [input_message]},\n",
|
||||
" stream_mode=\"values\",\n",
|
||||
"):\n",
|
||||
" step[\"messages\"][-1].pretty_print()"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -296,20 +324,20 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 48,
|
||||
"execution_count": 14,
|
||||
"id": "f59b377e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tools = [\n",
|
||||
" Tool(\n",
|
||||
" name=\"State of Union QA System\",\n",
|
||||
" name=\"state_of_union_qa_system\",\n",
|
||||
" func=state_of_union.run,\n",
|
||||
" description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question.\",\n",
|
||||
" return_direct=True,\n",
|
||||
" ),\n",
|
||||
" Tool(\n",
|
||||
" name=\"Ruff QA System\",\n",
|
||||
" name=\"ruff_qa_system\",\n",
|
||||
" func=ruff.run,\n",
|
||||
" description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question.\",\n",
|
||||
" return_direct=True,\n",
|
||||
@ -319,90 +347,92 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 49,
|
||||
"id": "8615707a",
|
||||
"execution_count": 15,
|
||||
"id": "06f69c0f-c83d-4b7f-a1c8-7614aced3bae",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent = initialize_agent(\n",
|
||||
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
||||
")"
|
||||
"from langgraph.prebuilt import create_react_agent\n",
|
||||
"\n",
|
||||
"agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 50,
|
||||
"id": "36e718a9",
|
||||
"execution_count": 16,
|
||||
"id": "a6b38c12-ac25-43c0-b9c2-2b1985ab4825",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"================================\u001b[1m Human Message \u001b[0m=================================\n",
|
||||
"\n",
|
||||
"What did biden say about ketanji brown jackson in the state of the union address?\n",
|
||||
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
|
||||
"Tool Calls:\n",
|
||||
" state_of_union_qa_system (call_yjxh11OnZiauoyTAn9npWdxj)\n",
|
||||
" Call ID: call_yjxh11OnZiauoyTAn9npWdxj\n",
|
||||
" Args:\n",
|
||||
" __arg1: What did Biden say about Ketanji Brown Jackson in the state of the union address?\n",
|
||||
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
|
||||
"Name: state_of_union_qa_system\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to find out what Biden said about Ketanji Brown Jackson in the State of the Union address.\n",
|
||||
"Action: State of Union QA System\n",
|
||||
"Action Input: What did Biden say about Ketanji Brown Jackson in the State of the Union address?\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
" Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 50,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\n",
|
||||
" \"What did biden say about ketanji brown jackson in the state of the union address?\"\n",
|
||||
")"
|
||||
"input_message = {\n",
|
||||
" \"role\": \"user\",\n",
|
||||
" \"content\": \"What did biden say about ketanji brown jackson in the state of the union address?\",\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"for step in agent.stream(\n",
|
||||
" {\"messages\": [input_message]},\n",
|
||||
" stream_mode=\"values\",\n",
|
||||
"):\n",
|
||||
" step[\"messages\"][-1].pretty_print()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 51,
|
||||
"id": "edfd0a1a",
|
||||
"execution_count": 17,
|
||||
"id": "88f08d86-7972-4148-8128-3ac8898ad68a",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"================================\u001b[1m Human Message \u001b[0m=================================\n",
|
||||
"\n",
|
||||
"Why use ruff over flake8?\n",
|
||||
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
|
||||
"Tool Calls:\n",
|
||||
" ruff_qa_system (call_GiWWfwF6wbbRFQrHlHbhRtGW)\n",
|
||||
" Call ID: call_GiWWfwF6wbbRFQrHlHbhRtGW\n",
|
||||
" Args:\n",
|
||||
" __arg1: What are the advantages of using ruff over flake8 for Python linting?\n",
|
||||
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
|
||||
"Name: ruff_qa_system\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to find out the advantages of using ruff over flake8\n",
|
||||
"Action: Ruff QA System\n",
|
||||
"Action Input: What are the advantages of using ruff over flake8?\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
" Ruff has a larger rule set, supports automatic fixing of lint violations, and does not require the installation of additional plugins. It also has better compatibility with Black and can be used alongside a type checker for more comprehensive code analysis.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 51,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"Why use ruff over flake8?\")"
|
||||
"input_message = {\n",
|
||||
" \"role\": \"user\",\n",
|
||||
" \"content\": \"Why use ruff over flake8?\",\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"for step in agent.stream(\n",
|
||||
" {\"messages\": [input_message]},\n",
|
||||
" stream_mode=\"values\",\n",
|
||||
"):\n",
|
||||
" step[\"messages\"][-1].pretty_print()"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -417,19 +447,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 57,
|
||||
"execution_count": 18,
|
||||
"id": "d397a233",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tools = [\n",
|
||||
" Tool(\n",
|
||||
" name=\"State of Union QA System\",\n",
|
||||
" name=\"state_of_union_qa_system\",\n",
|
||||
" func=state_of_union.run,\n",
|
||||
" description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question, not referencing any obscure pronouns from the conversation before.\",\n",
|
||||
" ),\n",
|
||||
" Tool(\n",
|
||||
" name=\"Ruff QA System\",\n",
|
||||
" name=\"ruff_qa_system\",\n",
|
||||
" func=ruff.run,\n",
|
||||
" description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question, not referencing any obscure pronouns from the conversation before.\",\n",
|
||||
" ),\n",
|
||||
@ -438,60 +468,60 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 58,
|
||||
"id": "06157240",
|
||||
"execution_count": 19,
|
||||
"id": "41743f29-150d-40ba-aa8e-3a63c32216aa",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Construct the agent. We will use the default agent type here.\n",
|
||||
"# See documentation for a full list of options.\n",
|
||||
"agent = initialize_agent(\n",
|
||||
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
||||
")"
|
||||
"from langgraph.prebuilt import create_react_agent\n",
|
||||
"\n",
|
||||
"agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 59,
|
||||
"id": "b492b520",
|
||||
"execution_count": 20,
|
||||
"id": "e20e81dd-284a-4d07-9160-63a84b65cba8",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"================================\u001b[1m Human Message \u001b[0m=================================\n",
|
||||
"\n",
|
||||
"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\n",
|
||||
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
|
||||
"Tool Calls:\n",
|
||||
" ruff_qa_system (call_VOnxiOEehauQyVOTjDJkR5L2)\n",
|
||||
" Call ID: call_VOnxiOEehauQyVOTjDJkR5L2\n",
|
||||
" Args:\n",
|
||||
" __arg1: What tool does ruff use to run over Jupyter Notebooks?\n",
|
||||
" state_of_union_qa_system (call_AbSsXAxwe4JtCRhga926SxOZ)\n",
|
||||
" Call ID: call_AbSsXAxwe4JtCRhga926SxOZ\n",
|
||||
" Args:\n",
|
||||
" __arg1: Did the president mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union?\n",
|
||||
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
|
||||
"Name: state_of_union_qa_system\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to find out what tool ruff uses to run over Jupyter Notebooks, and if the president mentioned it in the state of the union.\n",
|
||||
"Action: Ruff QA System\n",
|
||||
"Action Input: What tool does ruff use to run over Jupyter Notebooks?\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.html\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now need to find out if the president mentioned this tool in the state of the union.\n",
|
||||
"Action: State of Union QA System\n",
|
||||
"Action Input: Did the president mention nbQA in the state of the union?\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||
"Final Answer: No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
|
||||
" No, the president did not mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union.\n",
|
||||
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
"Ruff does not support source.organizeImports and source.fixAll code actions in Jupyter Notebooks. Additionally, the president did not mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'No, the president did not mention nbQA in the state of the union.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 59,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\n",
|
||||
" \"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\"\n",
|
||||
")"
|
||||
"input_message = {\n",
|
||||
" \"role\": \"user\",\n",
|
||||
" \"content\": \"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\",\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"for step in agent.stream(\n",
|
||||
" {\"messages\": [input_message]},\n",
|
||||
" stream_mode=\"values\",\n",
|
||||
"):\n",
|
||||
" step[\"messages\"][-1].pretty_print()"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -519,7 +549,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.1"
|
||||
"version": "3.12.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
Loading…
Reference in New Issue
Block a user