langchain/docs/modules/agents/implementations/self_ask_with_search.ipynb
Ankush Gola 82baecc892
Add a SQL agent for interacting with SQL Databases and JSON Agent for interacting with large JSON blobs (#1150)
This PR adds 

* `ZeroShotAgent.as_sql_agent`, which returns an agent for interacting
with a sql database. This builds off of `SQLDatabaseChain`. The main
advantages are 1) answering general questions about the db, 2) access to
a tool for double checking queries, and 3) recovering from errors
* `ZeroShotAgent.as_json_agent` which returns an agent for interacting
with json blobs.
* Several examples in notebooks

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-02-28 19:44:39 -08:00

91 lines
2.4 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"id": "0c3f1df8",
"metadata": {},
"source": [
"# Self Ask With Search\n",
"\n",
"This notebook showcases the Self Ask With Search chain."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "7e3b513e",
"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 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 won the 2022 Men's single title while Poland's Iga Swiatek won the Women's single title defeating Tunisian's Ons Jabeur.\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 AgentExecutor chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'El Palmar, Spain'"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain import OpenAI, SerpAPIWrapper\n",
"from langchain.agents import initialize_agent, Tool\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"search = SerpAPIWrapper()\n",
"tools = [\n",
" Tool(\n",
" name=\"Intermediate Answer\",\n",
" func=search.run\n",
" )\n",
"]\n",
"\n",
"self_ask_with_search = initialize_agent(tools, llm, agent=\"self-ask-with-search\", verbose=True)\n",
"self_ask_with_search.run(\"What is the hometown of the reigning men's U.S. Open champion?\")"
]
}
],
"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": "3.10.9"
},
"vscode": {
"interpreter": {
"hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}