github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-09 06:53:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Harrison/tools exp (#372)

Browse Source
This commit is contained in:
Harrison Chase
2022-12-18 21:51:23 -05:00
committed by GitHub
parent e7b625fe03
commit cf98f219f9
35 changed files with 1033 additions and 376 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/examples/agents.rst
View File

@@ -4,7 +4,7 @@ Agents
The examples here are all end-to-end agents for specific applications.
In all examples there is an Agent with a particular set of tools.
- Tools: A tool can be anything that takes in a string and returns a string. This means that you can use both the primitives AND the chains found in `this <chains.rst>`_ documentation.
- Tools: A tool can be anything that takes in a string and returns a string. This means that you can use both the primitives AND the chains found in `this <chains.rst>`_ documentation. LangChain also provides a list of easily loadable tools. For detailed information on those, please see `this documentation <../explanation/tools.md>`_
- Agents: An agent uses an LLMChain to determine which tools to use. For a list of all available agent types, see `here <../explanation/agents.md>`_.
**MRKL**

142
docs/examples/agents/custom_agent.ipynb
View File

@@ -28,7 +28,7 @@
"\n",
"The first way to create a custom agent is to use an existing Agent class, but use a custom LLMChain. This is the simplest way to create a custom Agent. It is highly reccomended that you work with the `ZeroShotAgent`, as at the moment that is by far the most generalizable one. \n",
"\n",
"Most of the work in creating the custom LLMChain comes down to the prompt. Because we are using an existing agent class to parse the output, it is very important that the prompt say to produce text in that format. However, besides those instructions, you can customize the prompt as you wish.\n",
"Most of the work in creating the custom LLMChain comes down to the prompt. Because we are using an existing agent class to parse the output, it is very important that the prompt say to produce text in that format. Additionally, we currently require an `agent_scratchpad` input variable to put notes on previous actions and observations. This should almost always be the final part of the prompt. However, besides those instructions, you can customize the prompt as you wish.\n",
"\n",
"To ensure that the prompt contains the appropriate instructions, we will utilize a helper method on that class. The helper method for the `ZeroShotAgent` takes the following arguments:\n",
"\n",
@@ -47,7 +47,7 @@
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import ZeroShotAgent, Tool\n",
"from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n",
"from langchain import OpenAI, SerpAPIWrapper, LLMChain"
]
},
@@ -78,13 +78,14 @@
"prefix = \"\"\"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\"\"\"\n",
"suffix = \"\"\"Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Args\"\n",
"\n",
"Question: {input}\"\"\"\n",
"Question: {input}\n",
"{agent_scratchpad}\"\"\"\n",
"\n",
"prompt = ZeroShotAgent.create_prompt(\n",
" tools, \n",
" prefix=prefix, \n",
" suffix=suffix, \n",
" input_variables=[\"input\"]\n",
" input_variables=[\"input\", \"agent_scratchpad\"]\n",
")"
]
},
@@ -123,7 +124,8 @@
"\n",
"Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Args\"\n",
"\n",
"Question: {input}\n"
"Question: {input}\n",
"{agent_scratchpad}\n"
]
}
],
@@ -148,12 +150,22 @@
"metadata": {},
"outputs": [],
"source": [
"agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)"
"agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "490604e9",
"metadata": {},
"outputs": [],
"source": [
"agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "653b1617",
"metadata": {},
"outputs": [
@@ -163,30 +175,126 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"How many people live in canada?\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look this up\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to find out how many people live in Canada\n",
"Action: Search\n",
"Action Input: How many people live in canada\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mThe current population of Canada is 38,533,678 as of Friday, November 25, 2022, based on Worldometer elaboration of the latest United Nations data. · Canada 2020 ...\u001b[0m\n",
"Action Input: Population of Canada\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mThe current population of Canada is 38,553,548 as of Saturday, December 17, 2022, based on Worldometer elaboration of the latest United Nations data. Canada ...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Arrr, there be 38,533,678 people in Canada\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"Final Answer: Arrr, there be 38,553,548 scallywags livin' in Canada!\u001b[0m\n",
"\u001b[1m> Finished AgentExecutor chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Arrr, there be 38,533,678 people in Canada'"
"\"Arrr, there be 38,553,548 scallywags livin' in Canada!\""
]
},
"execution_count": 7,
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"How many people live in canada?\")"
"agent_executor.run(\"How many people live in canada?\")"
]
},
{
"cell_type": "markdown",
"id": "040eb343",
"metadata": {},
"source": [
"### Multiple inputs\n",
"Agents can also work with prompts that require multiple inputs."
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "43dbfa2f",
"metadata": {},
"outputs": [],
"source": [
"prefix = \"\"\"Answer the following questions as best you can. You have access to the following tools:\"\"\"\n",
"suffix = \"\"\"When answering, you MUST speak in the following language: {language}.\n",
"\n",
"Question: {input}\n",
"{agent_scratchpad}\"\"\"\n",
"\n",
"prompt = ZeroShotAgent.create_prompt(\n",
" tools, \n",
" prefix=prefix, \n",
" suffix=suffix, \n",
" input_variables=[\"input\", \"language\", \"agent_scratchpad\"]\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "0f087313",
"metadata": {},
"outputs": [],
"source": [
"llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "92c75a10",
"metadata": {},
"outputs": [],
"source": [
"agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "ac5b83bf",
"metadata": {},
"outputs": [],
"source": [
"agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "c960e4ff",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I should look up the population of Canada.\n",
"Action: Search\n",
"Action Input: Population of Canada\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mThe current population of Canada is 38,553,548 as of Saturday, December 17, 2022, based on Worldometer elaboration of the latest United Nations data. Canada ...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: La popolazione attuale del Canada è 38.553.548 al sabato 17 dicembre 2022, secondo l'elaborazione di Worldometer dei dati più recenti delle Nazioni Unite.\u001b[0m\n",
"\u001b[1m> Finished AgentExecutor chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"La popolazione attuale del Canada è 38.553.548 al sabato 17 dicembre 2022, secondo l'elaborazione di Worldometer dei dati più recenti delle Nazioni Unite.\""
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(input=\"How many people live in canada?\", language=\"italian\")"
]
},
{
@@ -224,7 +332,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.6"
"version": "3.10.8"
}
},
"nbformat": 4,

81
docs/examples/agents/mrkl.ipynb
View File

@@ -46,7 +46,7 @@
" Tool(\n",
" name = \"Search\",\n",
" func=search.run,\n",
" description=\"useful for when you need to answer questions about current events\"\n",
" description=\"useful for when you need to answer questions about current events. You should ask targeted questions\"\n",
" ),\n",
" Tool(\n",
" name=\"Calculator\",\n",
@@ -56,7 +56,7 @@
" Tool(\n",
" name=\"FooBar DB\",\n",
" func=db_chain.run,\n",
" description=\"useful for when you need to answer questions about FooBar. Input should be in the form of a question\"\n",
" description=\"useful for when you need to answer questions about FooBar. Input should be in the form of a question containing full context\"\n",
" )\n",
"]"
]
@@ -81,40 +81,44 @@
"name": "stdout",
"output_type": "stream",
"text": [
"What is the age of Olivia Wilde's boyfriend raised to the 0.23 power?\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find the age of Olivia Wilde's boyfriend\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentWithTools chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.\n",
"Action: Search\n",
"Action Input: \"Olivia Wilde's boyfriend\"\u001b[0m\n",
"Action Input: \"Who is Olivia Wilde's boyfriend?\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mOlivia Wilde started dating Harry Styles after ending her years-long engagement to Jason Sudeikis — see their relationship timeline.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find the age of Harry Styles\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out Harry Styles' age.\n",
"Action: Search\n",
"Action Input: \"Harry Styles age\"\u001b[0m\n",
"Action Input: \"How old is Harry Styles?\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m28 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 28 to the 0.23 power\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 28 raised to the 0.23 power.\n",
"Action: Calculator\n",
"Action Input: 28^0.23\u001b[0m\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
"28^0.23\u001b[32;1m\u001b[1;3m\n",
"\n",
"```python\n",
"print(28**0.23)\n",
"import math\n",
"print(math.pow(28, 0.23))\n",
"```\n",
"\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3m2.1520202182226886\n",
"\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\u001b[1m> Finished LLMMathChain chain.\u001b[0m\n",
"\n",
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.1520202182226886\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 2.1520202182226886\u001b[0m"
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: Harry Styles, Olivia Wilde's boyfriend, is 28 years old and his age raised to the 0.23 power is 2.1520202182226886.\u001b[0m\n",
"\u001b[1m> Finished AgentWithTools chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'2.1520202182226886'"
"\"Harry Styles, Olivia Wilde's boyfriend, is 28 years old and his age raised to the 0.23 power is 2.1520202182226886.\""
]
},
"execution_count": 4,
@@ -123,7 +127,7 @@
}
],
"source": [
"mrkl.run(\"What is the age of Olivia Wilde's boyfriend raised to the 0.23 power?\")"
"mrkl.run(\"Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?\")"
]
},
{
@@ -136,43 +140,34 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find an album called 'The Storm Before the Calm'\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentWithTools chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to find out the artist's full name and then search the FooBar database for their albums.\n",
"Action: Search\n",
"Action Input: \"The Storm Before the Calm album\"\u001b[0m\n",
"Action Input: \"The Storm Before the Calm\" artist\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mThe Storm Before the Calm (stylized in all lowercase) is the tenth (and eighth international) studio album by Canadian-American singer-songwriter Alanis ...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to check if Alanis is in the FooBar database\n",
"Thought:\u001b[32;1m\u001b[1;3m I now need to search the FooBar database for Alanis Morissette's albums\n",
"Action: FooBar DB\n",
"Action Input: \"Does Alanis Morissette exist in the FooBar database?\"\u001b[0m\n",
"Action Input: What albums by Alanis Morissette are in the FooBar database?\u001b[0m\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"Does Alanis Morissette exist in the FooBar database?\n",
"SQLQuery:\u001b[32;1m\u001b[1;3m SELECT * FROM Artist WHERE Name = 'Alanis Morissette'\u001b[0m\n",
"SQLResult: \u001b[33;1m\u001b[1;3m[(4, 'Alanis Morissette')]\u001b[0m\n",
"Answer:\u001b[32;1m\u001b[1;3m Yes\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"Observation: \u001b[38;5;200m\u001b[1;3m Yes\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out what albums of Alanis's are in the FooBar database\n",
"Action: FooBar DB\n",
"Action Input: \"What albums by Alanis Morissette are in the FooBar database?\"\u001b[0m\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"What albums by Alanis Morissette are in the FooBar database?\n",
"SQLQuery:\u001b[32;1m\u001b[1;3m SELECT Album.Title FROM Album JOIN Artist ON Album.ArtistId = Artist.ArtistId WHERE Artist.Name = 'Alanis Morissette'\u001b[0m\n",
"\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
"What albums by Alanis Morissette are in the FooBar database? \n",
"SQLQuery:\u001b[32;1m\u001b[1;3m SELECT Title FROM Album WHERE ArtistId IN (SELECT ArtistId FROM Artist WHERE Name = 'Alanis Morissette');\u001b[0m\n",
"SQLResult: \u001b[33;1m\u001b[1;3m[('Jagged Little Pill',)]\u001b[0m\n",
"Answer:\u001b[32;1m\u001b[1;3m Jagged Little Pill\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"Answer:\u001b[32;1m\u001b[1;3m The album Jagged Little Pill by Alanis Morissette is in the FooBar database.\u001b[0m\n",
"\u001b[1m> Finished SQLDatabaseChain chain.\u001b[0m\n",
"\n",
"Observation: \u001b[38;5;200m\u001b[1;3m Jagged Little Pill\u001b[0m\n",
"Observation: \u001b[38;5;200m\u001b[1;3m The album Jagged Little Pill by Alanis Morissette is in the FooBar database.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The album is by Alanis Morissette and the albums in the FooBar database by her are Jagged Little Pill\u001b[0m"
"Final Answer: Alanis Morissette and Jagged Little Pill are in the FooBar database.\u001b[0m\n",
"\u001b[1m> Finished AgentWithTools chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The album is by Alanis Morissette and the albums in the FooBar database by her are Jagged Little Pill'"
"'Alanis Morissette and Jagged Little Pill are in the FooBar database.'"
]
},
"execution_count": 5,
@@ -181,13 +176,13 @@
}
],
"source": [
"mrkl.run(\"Who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\")"
"mrkl.run(\"What is the full name of the artist who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d7c2e6ac",
"id": "af016a70",
"metadata": {},
"outputs": [],
"source": []
@@ -209,7 +204,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.6"
"version": "3.10.8"
}
},
"nbformat": 4,

19
docs/examples/agents/react.ipynb
View File

@@ -12,7 +12,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 1,
"id": "4e272b47",
"metadata": {},
"outputs": [],
@@ -38,7 +38,7 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 2,
"id": "8078c8f1",
"metadata": {},
"outputs": [
@@ -48,18 +48,17 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ReActDocstoreAgent chain...\u001b[0m\n",
"Author David Chanoff has collaborated with a U.S. Navy admiral who served as the ambassador to the United Kingdom under which President?\n",
"Thought 1:\u001b[32;1m\u001b[1;3m I need to search David Chanoff and find the U.S. Navy admiral he collaborated\n",
"with.\n",
"\u001b[1m> Entering new AgentWithTools chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"Thought 1: I need to search David Chanoff and find the U.S. Navy admiral he collaborated with.\n",
"Action 1: Search[David Chanoff]\u001b[0m\n",
"Observation 1: \u001b[36;1m\u001b[1;3mDavid Chanoff is a noted author of non-fiction work. His work has typically involved collaborations with the principal protagonist of the work concerned. His collaborators have included; Augustus A. White, Joycelyn Elders, Đoàn Văn Toại, William J. Crowe, Ariel Sharon, Kenneth Good and Felix Zandman. He has also written about a wide range of subjects including literary history, education and foreign for The Washington Post, The New Republic and The New York Times Magazine. He has published more than twelve books.\u001b[0m\n",
"Thought 2:\u001b[32;1m\u001b[1;3m The U.S. Navy admiral David Chanoff collaborated with is William J. Crowe.\n",
"Action 2: Search[William J. Crowe]\u001b[0m\n",
"Observation 2: \u001b[36;1m\u001b[1;3mWilliam James Crowe Jr. (January 2, 1925 – October 18, 2007) was a United States Navy admiral and diplomat who served as the 11th chairman of the Joint Chiefs of Staff under Presidents Ronald Reagan and George H. W. Bush, and as the ambassador to the United Kingdom and Chair of the Intelligence Oversight Board under President Bill Clinton.\u001b[0m\n",
"Thought 3:\u001b[32;1m\u001b[1;3m William J. Crowe served as the ambassador to the United Kingdom under President Bill Clinton.\n",
"Thought 3:\u001b[32;1m\u001b[1;3m The President William J. Crowe served as the ambassador to the United Kingdom under is Bill Clinton.\n",
"Action 3: Finish[Bill Clinton]\u001b[0m\n",
"\u001b[1m> Finished ReActDocstoreAgent chain.\u001b[0m\n"
"\u001b[1m> Finished AgentWithTools chain.\u001b[0m\n"
]
},
{
@@ -68,7 +67,7 @@
"'Bill Clinton'"
]
},
"execution_count": 7,
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
@@ -81,7 +80,7 @@
{
"cell_type": "code",
"execution_count": null,
"id": "4ff64e81",
"id": "75f914ba",
"metadata": {},
"outputs": [],
"source": []

10
docs/examples/agents/self_ask_with_search.ipynb
View File

@@ -22,15 +22,14 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new SelfAskWithSearchAgent chain...\u001b[0m\n",
"What is the hometown of the reigning men's U.S. Open champion?\n",
"Are follow up questions needed here:\u001b[32;1m\u001b[1;3m Yes.\n",
"\u001b[1m> Entering new AgentWithTools chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m Yes.\n",
"Follow up: Who is the reigning men's U.S. Open champion?\u001b[0m\n",
"Intermediate answer: \u001b[36;1m\u001b[1;3mCarlos Alcaraz\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mFollow up: Where is Carlos Alcaraz from?\u001b[0m\n",
"Intermediate answer: \u001b[36;1m\u001b[1;3mEl Palmar, Spain\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mSo the final answer is: El Palmar, Spain\u001b[0m\n",
"\u001b[1m> Finished SelfAskWithSearchAgent chain.\u001b[0m\n"
"\u001b[1m> Finished AgentWithTools chain.\u001b[0m\n"
]
},
{
@@ -58,7 +57,6 @@
"]\n",
"\n",
"self_ask_with_search = initialize_agent(tools, llm, agent=\"self-ask-with-search\", verbose=True)\n",
"\n",
"self_ask_with_search.run(\"What is the hometown of the reigning men's U.S. Open champion?\")"
]
},
@@ -87,7 +85,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.6"
"version": "3.10.8"
}
},
"nbformat": 4,

2
docs/examples/chains/pal.ipynb
View File

@@ -172,7 +172,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.7"
"version": "3.10.8"
}
},
"nbformat": 4,

1
docs/explanation/agents.md
View File

@@ -2,6 +2,7 @@
Agents use an LLM to determine which actions to take and in what order.
An action can either be using a tool and observing its output, or returning to the user.
For a list of easily loadable tools, see [here](tools.md).
Here are the agents available in LangChain.
For a tutorial on how to load agents, see [here](/getting_started/agents.ipynb).

94
docs/explanation/tools.md Normal file
View File

@@ -0,0 +1,94 @@
# Tools
Tools are functions that agents can use to interact with the world.
These tools can be generic utilities (eg search), other chains, or even other agents.
Currently, tools can be loaded with the following snippet:
```python
from langchain.agents import load_tools
tool_names = [...]
tools = load_tools(tool_names)
```
Some tools (eg chains, agents) may require a base LLM to use to initialize them.
In that case, you can pass in an LLM as well:
```python
from langchain.agents import load_tools
tool_names = [...]
llm = ...
tools = load_tools(tool_names, llm=llm)
```
Below is a list of all supported tools and relevant information:
- Tool Name: The name the LLM refers to the tool by.
- Tool Description: The description of the tool that is passed to the LLM.
- Notes: Notes about the tool that are NOT passed to the LLM.
- Requires LLM: Whether this tool requires an LLM to be initialized.
- (Optional) Extra Parameters: What extra parameters are required to initialize this tool.
### List of Tools
**python_repl**
- Tool Name: Python REPL
- Tool Description: A Python shell. Use this to execute python commands. Input should be a valid python command. If you expect output it should be printed out.
- Notes: Maintains state.
- Requires LLM: No
**serpapi**
- Tool Name: Search
- Tool Description: A search engine. Useful for when you need to answer questions about current events. Input should be a search query.
- Notes: Calls the Serp API and then parses results.
- Requires LLM: No
**requests**
- Tool Name: Requests
- Tool Description: A portal to the internet. Use this when you need to get specific content from a site. Input should be a specific url, and the output will be all the text on that page.
- Notes: Uses the Python requests module.
- Requires LLM: No
**terminal**
- Tool Name: Terminal
- Tool Description: Executes commands in a terminal. Input should be valid commands, and the output will be any output from running that command.
- Notes: Executes commands with subprocess.
- Requires LLM: No
**pal-math**
- Tool Name: PAL-MATH
- Tool Description: A language model that is really good at solving complex word math problems. Input should be a fully worded hard word math problem.
- Notes: Based on [this paper](https://arxiv.org/pdf/2211.10435.pdf).
- Requires LLM: Yes
**pal-colored-objects**
- Tool Name: PAL-COLOR-OBJ
- Tool Description: A language model that is really good at reasoning about position and the color attributes of objects. Input should be a fully worded hard reasoning problem. Make sure to include all information about the objects AND the final question you want to answer.
- Notes: Based on [this paper](https://arxiv.org/pdf/2211.10435.pdf).
- Requires LLM: Yes
**llm-math**
- Tool Name: Calculator
- Tool Description: Useful for when you need to answer questions about math.
- Notes: An instance of the `LLMMath` chain.
- Requires LLM: Yes
**open-meteo-api**
- Tool Name: Open Meteo API
- Tool Description: Useful for when you want to get weather information from the OpenMeteo API. The input should be a question in natural language that this API can answer.
- Notes: A natural language connection to the Open Meteo API (`https://api.open-meteo.com/`), specifically the `/v1/forecast` endpoint.
- Requires LLM: Yes
**news-api**
- Tool Name: News API
- Tool Description: Use this when you want to get information about the top headlines of current news stories. The input should be a question in natural language that this API can answer.
- Notes: A natural language connection to the News API (`https://newsapi.org`), specifically the `/v2/top-headlines` endpoint.
- Requires LLM: Yes
- Extra Parameters: `news_api_key` (your API key to access this endpoint)
**tmdb-api**
- Tool Name: TMDB API
- Tool Description: Useful for when you want to get information from The Movie Database. The input should be a question in natural language that this API can answer.
- Notes: A natural language connection to the TMDB API (`https://api.themoviedb.org/3`), specifically the `/search/movie` endpoint.
- Requires LLM: Yes
- Extra Parameters: `tmdb_bearer_token` (your Bearer Token to access this endpoint - note that this is different than the API key)

259
docs/getting_started/agents.ipynb
View File

@@ -10,7 +10,7 @@
"Agents use an LLM to determine which actions to take and in what order.\n",
"An action can either be using a tool and observing its output, or returning to the user.\n",
"\n",
"When used correctly agents can be extremely powerful. The purpose of this notebook is to show you how to easily use agents through the simplest, highest level API. If you want more low level control over various components, check out the documentation for custom agents (coming soon)."
"When used correctly agents can be extremely powerful. The purpose of this notebook is to show you how to easily use agents through the simplest, highest level API. If you want more low level control over various components, check out the documentation for [custom agents](../examples/agents/custom_agents.ipynb)."
]
},
{
@@ -26,7 +26,9 @@
"- LLM: The language model powering the agent.\n",
"- Agent: The agent to use. This should be a string that references a support agent class. Because this notebook focuses on the simplest, highest level API, this only covers using the standard supported agents. If you want to implement a custom agent, see the documentation for custom agents (coming soon).\n",
"\n",
"**For a list of supported agents and their specifications, see [here](../explanation/agents.md)**"
"**Agents**: For a list of supported agents and their specifications, see [here](../explanation/agents.md).\n",
"\n",
"**Tools**: For a list of predefined tools and their specifications, see [here](../explanation/tools.md)."
]
},
{
@@ -46,7 +48,9 @@
" description: Optional[str] = None\n",
"```\n",
"\n",
"The two required components of a Tool are the name and then the tool itself. A tool description is optional, as it is needed for some agents but not all."
"The two required components of a Tool are the name and then the tool itself. A tool description is optional, as it is needed for some agents but not all.\n",
"\n",
"Besides defining tools yourself, you can also take advantage of predefined tools. For instructions on how to do that, please see later on in this notebook."
]
},
{
@@ -110,7 +114,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 11,
"id": "6f96a891",
"metadata": {},
"outputs": [
@@ -118,55 +122,270 @@
"name": "stdout",
"output_type": "stream",
"text": [
"What is the age of Olivia Wilde's boyfriend raised to the 0.23 power?\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find the age of Olivia Wilde's boyfriend\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentWithTools chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.\n",
"Action: Search\n",
"Action Input: \"Olivia Wilde's boyfriend\"\u001b[0m\n",
"Action Input: Olivia Wilde's boyfriend\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mOlivia Wilde started dating Harry Styles after ending her years-long engagement to Jason Sudeikis — see their relationship timeline.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find the age of Harry Styles\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out Harry Styles' age.\n",
"Action: Search\n",
"Action Input: \"Harry Styles age\"\u001b[0m\n",
"Action Input: Harry Styles age\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m28 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 28 to the 0.23 power\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 28 raised to the 0.23 power.\n",
"Action: Calculator\n",
"Action Input: 28^0.23\u001b[0m\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
"28^0.23\u001b[32;1m\u001b[1;3m\n",
"\n",
"```python\n",
"print(28**0.23)\n",
"import math\n",
"print(math.pow(28, 0.23))\n",
"```\n",
"\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3m2.1520202182226886\n",
"\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\u001b[1m> Finished LLMMathChain chain.\u001b[0m\n",
"\n",
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.1520202182226886\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 2.1520202182226886\u001b[0m"
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: Harry Styles, Olivia Wilde's boyfriend, is 28 years old and his age raised to the 0.23 power is 2.1520202182226886.\u001b[0m\n",
"\u001b[1m> Finished AgentWithTools chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'2.1520202182226886'"
"\"Harry Styles, Olivia Wilde's boyfriend, is 28 years old and his age raised to the 0.23 power is 2.1520202182226886.\""
]
},
"execution_count": 4,
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"How old is Olivia Wilde's boyfriend? What is that number raised to the 0.23 power?\")"
"agent.run(\"Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?\")"
]
},
{
"cell_type": "markdown",
"id": "0a70f2fc",
"metadata": {},
"source": [
"## Intermediate Steps\n",
"In order to get more visibility into what an agent is doing, we can also return intermediate steps. This comes in the form of an extra key in the return value, which is a list of (action, observation) tuples."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "2f0852ff",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)\n",
"agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True, return_intermediate_steps=True)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "837211e8",
"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 I need to find out how old Olivia Wilde's boyfriend is, and then use a calculator to calculate the power.\n",
"Action: Search\n",
"Action Input: Olivia Wilde's boyfriend age\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mWhile Wilde, 37, and Styles, 27, have both kept a low profile when it comes to talking about their relationship, Wilde did address their ...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m Olivia Wilde's boyfriend is 27 years old.\n",
"Action: Calculator\n",
"Action Input: 27^0.23\u001b[0m\n",
"\n",
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
"27^0.23\u001b[32;1m\u001b[1;3m\n",
"\n",
"```python\n",
"import math\n",
"print(math.pow(27, 0.23))\n",
"```\n",
"\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3m2.1340945944237553\n",
"\u001b[0m\n",
"\u001b[1m> Finished LLMMathChain chain.\u001b[0m\n",
"\n",
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.1340945944237553\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: 2.1340945944237553\u001b[0m\n",
"\u001b[1m> Finished AgentExecutor chain.\u001b[0m\n"
]
}
],
"source": [
"response = agent({\"input\":\"How old is Olivia Wilde's boyfriend? What is that number raised to the 0.23 power?\"})"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "e1a39a23",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[(AgentAction(tool='Search', tool_input=\"Olivia Wilde's boyfriend age\", log=\" I need to find out how old Olivia Wilde's boyfriend is, and then use a calculator to calculate the power.\\nAction: Search\\nAction Input: Olivia Wilde's boyfriend age\"), 'While Wilde, 37, and Styles, 27, have both kept a low profile when it comes to talking about their relationship, Wilde did address their ...'), (AgentAction(tool='Calculator', tool_input='27^0.23', log=\" Olivia Wilde's boyfriend is 27 years old.\\nAction: Calculator\\nAction Input: 27^0.23\"), 'Answer: 2.1340945944237553\\n')]\n"
]
}
],
"source": [
"# The actual return type is a NamedTuple for the agent action, and then an observation\n",
"print(response[\"intermediate_steps\"])"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "6365bb69",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[\n",
" [\n",
" [\n",
" \"Search\",\n",
" \"Olivia Wilde's boyfriend age\",\n",
" \" I need to find out how old Olivia Wilde's boyfriend is, and then use a calculator to calculate the power.\\nAction: Search\\nAction Input: Olivia Wilde's boyfriend age\"\n",
" ],\n",
" \"While Wilde, 37, and Styles, 27, have both kept a low profile when it comes to talking about their relationship, Wilde did address their ...\"\n",
" ],\n",
" [\n",
" [\n",
" \"Calculator\",\n",
" \"27^0.23\",\n",
" \" Olivia Wilde's boyfriend is 27 years old.\\nAction: Calculator\\nAction Input: 27^0.23\"\n",
" ],\n",
" \"Answer: 2.1340945944237553\\n\"\n",
" ]\n",
"]\n"
]
}
],
"source": [
"import json\n",
"print(json.dumps(response[\"intermediate_steps\"], indent=2))"
]
},
{
"cell_type": "markdown",
"id": "d20f9358",
"metadata": {},
"source": [
"## Predefined Tools\n",
"In addition to letting you define arbitrary tools, LangChain also provides some predefined tools. These can be either generic utility functions, chains, or other agents. You can easily load these tools by name (optionally specifying an LLM to use, if the tool requires it). For a list of all possible tools, please see [here](../explanation/tools.md).\n",
"\n",
"Let's recreate the above example loading tools by name. Because the LLMMath chain needs an LLM, we need to specify one."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "ba4e7618",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import load_tools\n",
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "03208e2b",
"metadata": {},
"outputs": [],
"source": [
"agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "244ee75c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentWithTools chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.\n",
"Action: Search\n",
"Action Input: Olivia Wilde's boyfriend\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mOlivia Wilde started dating Harry Styles after ending her years-long engagement to Jason Sudeikis — see their relationship timeline.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out Harry Styles' age.\n",
"Action: Search\n",
"Action Input: Harry Styles age\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m28 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 28 raised to the 0.23 power.\n",
"Action: Calculator\n",
"Action Input: 28^0.23\u001b[0m\n",
"\n",
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
"28^0.23\u001b[32;1m\u001b[1;3m\n",
"\n",
"```python\n",
"import math\n",
"print(math.pow(28, 0.23))\n",
"```\n",
"\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3m2.1520202182226886\n",
"\u001b[0m\n",
"\u001b[1m> Finished LLMMathChain chain.\u001b[0m\n",
"\n",
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.1520202182226886\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: Harry Styles, Olivia Wilde's boyfriend, is 28 years old and his age raised to the 0.23 power is 2.1520202182226886.\u001b[0m\n",
"\u001b[1m> Finished AgentWithTools chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Harry Styles, Olivia Wilde's boyfriend, is 28 years old and his age raised to the 0.23 power is 2.1520202182226886.\""
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2f0852ff",
"id": "e7776981",
"metadata": {},
"outputs": [],
"source": []
@@ -188,7 +407,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.6"
"version": "3.10.8"
}
},
"nbformat": 4,

1
docs/index.rst
View File

@@ -161,6 +161,7 @@ see detailed information about the various classes, methods, and APIs.
explanation/core_concepts.md
explanation/combine_docs.md
explanation/agents.md
explanation/tools.md
explanation/glossary.md
explanation/cool_demos.md
Discord <https://discord.gg/6adMQxSpJS>