mirror of
https://github.com/hwchase17/langchain.git
synced 2025-05-19 05:51:16 +00:00
10dab053b4
This pull request adds an enum class for the various types of agents used in the project, located in the `agent_types.py` file. Currently, the project is using hardcoded strings for the initialization of these agents, which can lead to errors and make the code harder to maintain. With the introduction of the new enums, the code will be more readable and less error-prone. The new enum members include: - ZERO_SHOT_REACT_DESCRIPTION - REACT_DOCSTORE - SELF_ASK_WITH_SEARCH - CONVERSATIONAL_REACT_DESCRIPTION - CHAT_ZERO_SHOT_REACT_DESCRIPTION - CHAT_CONVERSATIONAL_REACT_DESCRIPTION In this PR, I have also replaced the hardcoded strings with the appropriate enum members throughout the codebase, ensuring a smooth transition to the new approach.
134 lines
3.6 KiB
Plaintext
134 lines
3.6 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Human as a tool\n",
|
|
"\n",
|
|
"Human are AGI so they can certainly be used as a tool to help out AI agent \n",
|
|
"when it is confused."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import sys\n",
|
|
"from langchain.chat_models import ChatOpenAI\n",
|
|
"from langchain.llms import OpenAI\n",
|
|
"from langchain.agents import load_tools, initialize_agent\n",
|
|
"from langchain.agents.agent_types import AgentType\n",
|
|
"\n",
|
|
"llm = ChatOpenAI(temperature=0.0)\n",
|
|
"math_llm = OpenAI(temperature=0.0)\n",
|
|
"tools = load_tools(\n",
|
|
" [\"human\", \"llm-math\"], \n",
|
|
" llm=math_llm,\n",
|
|
")\n",
|
|
"\n",
|
|
"agent_chain = initialize_agent(\n",
|
|
" tools,\n",
|
|
" llm,\n",
|
|
" agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
|
|
" verbose=True,\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"In the above code you can see the tool takes input directly from command line.\n",
|
|
"You can customize `prompt_func` and `input_func` according to your need."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\n",
|
|
"\n",
|
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
|
"\u001b[32;1m\u001b[1;3mI don't know Eric Zhu, so I should ask a human for guidance.\n",
|
|
"Action: Human\n",
|
|
"Action Input: \"Do you know when Eric Zhu's birthday is?\"\u001b[0m\n",
|
|
"\n",
|
|
"Do you know when Eric Zhu's birthday is?\n",
|
|
"last week\n",
|
|
"\n",
|
|
"Observation: \u001b[36;1m\u001b[1;3mlast week\u001b[0m\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3mThat's not very helpful. I should ask for more information.\n",
|
|
"Action: Human\n",
|
|
"Action Input: \"Do you know the specific date of Eric Zhu's birthday?\"\u001b[0m\n",
|
|
"\n",
|
|
"Do you know the specific date of Eric Zhu's birthday?\n",
|
|
"august 1st\n",
|
|
"\n",
|
|
"Observation: \u001b[36;1m\u001b[1;3maugust 1st\u001b[0m\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3mNow that I have the date, I can check if it's a leap year or not.\n",
|
|
"Action: Calculator\n",
|
|
"Action Input: \"Is 2021 a leap year?\"\u001b[0m\n",
|
|
"Observation: \u001b[33;1m\u001b[1;3mAnswer: False\n",
|
|
"\u001b[0m\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3mI have all the information I need to answer the original question.\n",
|
|
"Final Answer: Eric Zhu's birthday is on August 1st and it is not a leap year in 2021.\u001b[0m\n",
|
|
"\n",
|
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"\"Eric Zhu's birthday is on August 1st and it is not a leap year in 2021.\""
|
|
]
|
|
},
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"\n",
|
|
"agent_chain.run(\"What is Eric Zhu's birthday?\")\n",
|
|
"# Answer with \"last week\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"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": "3.9.1"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|