forked from Archives/langchain
985496f4be
Big docs refactor! Motivation is to make it easier for people to find resources they are looking for. To accomplish this, there are now three main sections: - Getting Started: steps for getting started, walking through most core functionality - Modules: these are different modules of functionality that langchain provides. Each part here has a "getting started", "how to", "key concepts" and "reference" section (except in a few select cases where it didnt easily fit). - Use Cases: this is to separate use cases (like summarization, question answering, evaluation, etc) from the modules, and provide a different entry point to the code base. There is also a full reference section, as well as extra resources (glossary, gallery, etc) Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
91 lines
2.4 KiB
Plaintext
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 3.9.0 64-bit ('llm-env')",
|
|
"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": "3.9.0"
|
|
},
|
|
"vscode": {
|
|
"interpreter": {
|
|
"hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
|
|
}
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|