Skip to content

Commit

Permalink
agents
Browse files Browse the repository at this point in the history
  • Loading branch information
Gregory Kamradt committed Feb 14, 2023
1 parent 94d46c8 commit a619518
Show file tree
Hide file tree
Showing 3 changed files with 520 additions and 0 deletions.
Binary file added .DS_Store
View file
Binary file not shown.
260 changes: 260 additions & 0 deletions agents/.ipynb_checkpoints/Agents-checkpoint.ipynb
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,260 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "5170bf5b",
"metadata": {},
"source": [
"# Agents - Make OpenAI Do Things For you"
]
},
{
"cell_type": "markdown",
"id": "8d9faa06",
"metadata": {},
"source": [
"*[Source](https://langchain.readthedocs.io/en/latest/modules/agents/getting_started.html)*\n",
"* **Agent** - 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.\n",
"\n",
"Parameters when creating an agent:\n",
"* **Tool:** A function that performs a specific duty. This can be things like: Google Search, Database lookup, Python REPL, other chains. The interface for a tool is currently a function that is expected to have a string as an input, with a string as an output.\n",
"* **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)."
]
},
{
"cell_type": "code",
"execution_count": 57,
"id": "7f247903",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import load_tools\n",
"from langchain.agents import initialize_agent\n",
"from langchain.llms import OpenAI"
]
},
{
"cell_type": "markdown",
"id": "0bd3670a",
"metadata": {},
"source": [
"### List of Tools\n",
"1. **python_repl -** 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.\n",
"2. **serpapi [Complete] -** A search engine. Useful for when you need to answer questions about current events. Input should be a search query.\n",
"3. **wolfram-alpha [Complete] -** A wolfram alpha search engine. Useful for when you need to answer questions about Math, Science, Technology, Culture, Society and Everyday Life. Input should be a search query.\n",
"4. **requests -** 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.\n",
"5. **terminal -** Executes commands in a terminal. Input should be valid commands, and the output will be any output from running that command.\n",
"6. **pal-math -** A language model that is excellent at solving complex word math problems. Input should be a fully worded hard word math problem.\n",
"7. **pal-colored-objects -** A language model that is wonderful 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.\n",
"8. **llm-math -** Useful for when you need to answer questions about math.\n",
"9. **open-meteo-api -** 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.\n",
"10. **news-api -** 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.\n",
"11. **tmdb-api -** 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.\n",
"12. **google-search -** A wrapper around Google Search. Useful for when you need to answer questions about current events. Input should be a search query.\n"
]
},
{
"cell_type": "markdown",
"id": "83032dcf",
"metadata": {},
"source": [
"### 2. SERP API"
]
},
{
"cell_type": "code",
"execution_count": 60,
"id": "0c90ba74",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import load_tools\n",
"\n",
"# import os\n",
"# os.environ['OPENAI_API_KEY'] = \"...\"\n",
"# os.environ['SERPAPI_API_KEY'] = \"...\""
]
},
{
"cell_type": "code",
"execution_count": 61,
"id": "d0f2fd44",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)"
]
},
{
"cell_type": "code",
"execution_count": 62,
"id": "f26a0dd5",
"metadata": {},
"outputs": [],
"source": [
"tool_names = [\"serpapi\"]\n",
"tools = load_tools(tool_names)"
]
},
{
"cell_type": "code",
"execution_count": 65,
"id": "e8a35518",
"metadata": {},
"outputs": [],
"source": [
"agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 66,
"id": "829a2d67",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'LangChain is a platform that provides a standard interface for chains, lots of integrations with other tools, and end-to-end chains for common applications. Data Augmented Reality (DAR) is also supported.'"
]
},
"execution_count": 66,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"What is LangChain?\")"
]
},
{
"cell_type": "code",
"execution_count": 67,
"id": "b4cc45f6",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Luke Voiles is the CEO of Pipe.'"
]
},
"execution_count": 67,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Input should be a search query.\n",
"agent.run(\"who is the ceo of pipe?\")"
]
},
{
"cell_type": "markdown",
"id": "1869cabc",
"metadata": {},
"source": [
"### 3. Wolfram Alpha"
]
},
{
"cell_type": "code",
"execution_count": 68,
"id": "0fd02098",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import load_tools\n",
"\n",
"# import os\n",
"# pip install wolframalpha\n",
"# os.environ['OPENAI_API_KEY'] = \"...\"\n",
"# os.environ['WOLFRAM_ALPHA_APPID'] = \"..\""
]
},
{
"cell_type": "code",
"execution_count": 69,
"id": "7a96dfdd",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)"
]
},
{
"cell_type": "code",
"execution_count": 70,
"id": "1ba4200b",
"metadata": {},
"outputs": [],
"source": [
"tool_names = [\"wolfram-alpha\"]\n",
"tools = load_tools(tool_names)"
]
},
{
"cell_type": "code",
"execution_count": 74,
"id": "4716e3a8",
"metadata": {},
"outputs": [],
"source": [
"agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 75,
"id": "89e0d255",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'The asthenosphere is the lower layer of the crust.'"
]
},
"execution_count": 75,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Input should be a search query.\n",
"\n",
"agent.run(\"What is the asthenosphere?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "86c98c29",
"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": "3.9.13"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Loading

0 comments on commit a619518

Please sign in to comment.