Shared memory across agents and tools.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "id": "0YZvkrpjOZnx"
   },
   "outputs": [],
   "source": [
    "from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n",
    "from langchain.memory import ConversationBufferMemory, ReadOnlySharedMemory\n",
    "from langchain import OpenAI, LLMChain, PromptTemplate\n",
    "from langchain import SerpAPIWrapper"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "id": "rRXOevZNOeUt"
   },
   "outputs": [],
   "source": [
    "template = \"\"\"This is a conversation between a human and a bot:\n",
    "\n",
    "{chat_history}\n",
    "\n",
    "Write a summary of the conversation for {input}:\n",
    "\"\"\"\n",
    "\n",
    "prompt = PromptTemplate(input_variables=[\"input\", \"chat_history\"], template=template)\n",
    "memory = ConversationBufferMemory(memory_key=\"chat_history\")\n",
    "readonlymemory = ReadOnlySharedMemory(memory=memory)\n",
    "summry_chain = LLMChain(\n",
    "    llm=OpenAI(),\n",
    "    prompt=prompt,\n",
    "    verbose=True,\n",
    "    memory=readonlymemory,  # use the read-only memory to prevent the tool from modifying the memory\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "id": "iK4GP4OGOfZn"
   },
   "outputs": [],
   "source": [
    "search = SerpAPIWrapper()\n",
    "tools = [\n",
    "    Tool(\n",
    "        name=\"Search\",\n",
    "        func=search.run,\n",
    "        description=\"useful for when you need to answer questions about current events\",\n",
    "    ),\n",
    "    Tool(\n",
    "        name=\"Summary\",\n",
    "        func=summry_chain.run,\n",
    "        description=\"useful for when you summarize a conversation. The input to this tool should be a string, representing who will read this summary.\",\n",
    "    ),\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "id": "FtMcjo0zOhRG"
   },
   "outputs": [],
   "source": [
    "prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
    "suffix = \"\"\"Begin!\"\n",
    "\n",
    "{chat_history}\n",
    "Question: {input}\n",
    "{agent_scratchpad}\"\"\"\n",
    "\n",
    "prompt = ZeroShotAgent.create_prompt(\n",
    "    tools,\n",
    "    prefix=prefix,\n",
    "    suffix=suffix,\n",
    "    input_variables=[\"input\", \"chat_history\", \"agent_scratchpad\"],\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "id": "V1HjNYatOix6"
   },
   "outputs": [],
   "source": [
    "llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)\n",
    "agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)\n",
    "agent_chain = AgentExecutor.from_agent_and_tools(\n",
    "    agent=agent, tools=tools, verbose=True, memory=memory\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "id": "zJ7JjmqROkUp"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mThought: I should research ChatGPT to answer this question.\n",
      "Action: Search\n",
      "Action Input: \"ChatGPT\"\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched on November 30, 2022. It is notable for enabling users to refine and steer a conversation towards a desired length, format, style, level of detail, and language used.\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the answer to the question.\n",
      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched on November 30, 2022. It is notable for enabling users to refine and steer a conversation towards a desired length, format, style, level of detail, and language used.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched on November 30, 2022. It is notable for enabling users to refine and steer a conversation towards a desired length, format, style, level of detail, and language used.'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_chain.run(input=\"What is ChatGPT?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "id": "ifkbqtsFOmpS"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mThought: I need to find out who developed ChatGPT\n",
      "Action: Search\n",
      "Action Input: Who developed ChatGPT\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mOpenAI\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the answer\n",
      "Final Answer: ChatGPT was developed by OpenAI.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'ChatGPT was developed by OpenAI.'"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_chain.run(input=\"Who developed it?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "2lt6AbOTOn6-"
   },
   "outputs": [],
   "source": [
    "agent_chain.run(\n",
    "    input=\"Thanks. Summarize the conversation, for my daughter 5 years old.\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "0VCNf-7ROpvY"
   },
   "outputs": [],
   "source": [
    "print(agent_chain.memory.buffer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "DC60DdlzOrKD"
   },
   "outputs": [],
   "source": [
    "## This is a bad practice for using the memory.\n",
    "## Use the ReadOnlySharedMemory class, as shown above.\n",
    "\n",
    "template = \"\"\"This is a conversation between a human and a bot:\n",
    "\n",
    "{chat_history}\n",
    "\n",
    "Write a summary of the conversation for {input}:\n",
    "\"\"\"\n",
    "\n",
    "prompt = PromptTemplate(input_variables=[\"input\", \"chat_history\"], template=template)\n",
    "memory = ConversationBufferMemory(memory_key=\"chat_history\")\n",
    "summry_chain = LLMChain(\n",
    "    llm=OpenAI(),\n",
    "    prompt=prompt,\n",
    "    verbose=True,\n",
    "    memory=memory,  # <--- this is the only change\n",
    ")\n",
    "\n",
    "search = GoogleSearchAPIWrapper()\n",
    "tools = [\n",
    "    Tool(\n",
    "        name=\"Search\",\n",
    "        func=search.run,\n",
    "        description=\"useful for when you need to answer questions about current events\",\n",
    "    ),\n",
    "    Tool(\n",
    "        name=\"Summary\",\n",
    "        func=summry_chain.run,\n",
    "        description=\"useful for when you summarize a conversation. The input to this tool should be a string, representing who will read this summary.\",\n",
    "    ),\n",
    "]\n",
    "\n",
    "prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
    "suffix = \"\"\"Begin!\"\n",
    "\n",
    "{chat_history}\n",
    "Question: {input}\n",
    "{agent_scratchpad}\"\"\"\n",
    "\n",
    "prompt = ZeroShotAgent.create_prompt(\n",
    "    tools,\n",
    "    prefix=prefix,\n",
    "    suffix=suffix,\n",
    "    input_variables=[\"input\", \"chat_history\", \"agent_scratchpad\"],\n",
    ")\n",
    "\n",
    "llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)\n",
    "agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)\n",
    "agent_chain = AgentExecutor.from_agent_and_tools(\n",
    "    agent=agent, tools=tools, verbose=True, memory=memory\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "jJbnQpHHOrue"
   },
   "outputs": [],
   "source": [
    "agent_chain.run(input=\"What is ChatGPT?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "IZrDXBpaOtG0"
   },
   "outputs": [],
   "source": [
    "agent_chain.run(input=\"Who developed it?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "6hXEA0DWOva0"
   },
   "outputs": [],
   "source": [
    "agent_chain.run(\n",
    "    input=\"Thanks. Summarize the conversation, for my daughter 5 years old.\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "FaLS-yG0OxK5"
   },
   "outputs": [],
   "source": [
    "print(agent_chain.memory.buffer)"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "authorship_tag": "ABX9TyOKx28zG2CUEL5s6LfMIaZl",
   "provenance": []
  },
  "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"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}