diff --git a/docs/modules/agents/agents/examples/structured_chat.ipynb b/docs/modules/agents/agents/examples/structured_chat.ipynb index 5153f044..6a03c0d9 100644 --- a/docs/modules/agents/agents/examples/structured_chat.ipynb +++ b/docs/modules/agents/agents/examples/structured_chat.ipynb @@ -14,6 +14,17 @@ "This functionality is natively available in the (`structured-chat-zero-shot-react-description` or `AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION`)." ] }, + { + "cell_type": "code", + "execution_count": null, + "id": "ccc8ff98", + "metadata": {}, + "outputs": [], + "source": [ + "import os\n", + "os.environ[\"LANGCHAIN_TRACING\"] = \"true\" # If you want to trace the execution of the program, set to \"true\"" + ] + }, { "cell_type": "code", "execution_count": 1, @@ -85,18 +96,6 @@ "agent_chain = initialize_agent(tools, llm, agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)" ] }, - { - "cell_type": "code", - "execution_count": 5, - "id": "c4a45575-f3ef-46ba-a943-475584073984", - "metadata": { - "tags": [] - }, - "outputs": [], - "source": [ - "from langchain.callbacks import tracing_enabled # This is used to configure tracing for our runs." - ] - }, { "cell_type": "code", "execution_count": 6, @@ -119,8 +118,7 @@ } ], "source": [ - "with tracing_enabled(): # If you want to see the traces in the UI\n", - " response = await agent_chain.arun(input=\"Hi I'm Erica.\")\n", + "response = await agent_chain.arun(input=\"Hi I'm Erica.\")\n", "print(response)" ] }, @@ -146,8 +144,7 @@ } ], "source": [ - "with tracing_enabled(): # If you want to see the traces in the UI\n", - " response = await agent_chain.arun(input=\"Don't need help really just chatting.\")\n", + "response = await agent_chain.arun(input=\"Don't need help really just chatting.\")\n", "print(response)" ] }, @@ -222,8 +219,7 @@ } ], "source": [ - "with tracing_enabled(): # If you want to see the traces in the UI\n", - " response = await agent_chain.arun(input=\"Browse to blog.langchain.dev and summarize the text, please.\")\n", + "response = await agent_chain.arun(input=\"Browse to blog.langchain.dev and summarize the text, please.\")\n", "print(response)" ] }, @@ -274,8 +270,7 @@ } ], "source": [ - "with tracing_enabled(): # If you want to see the traces in the UI\n", - " response = await agent_chain.arun(input=\"What's the latest xkcd comic about?\")\n", + "response = await agent_chain.arun(input=\"What's the latest xkcd comic about?\")\n", "print(response)" ] }, diff --git a/docs/modules/agents/tools/multi_input_tool.ipynb b/docs/modules/agents/tools/multi_input_tool.ipynb index e786d8e5..62ccbdb0 100644 --- a/docs/modules/agents/tools/multi_input_tool.ipynb +++ b/docs/modules/agents/tools/multi_input_tool.ipynb @@ -1,23 +1,144 @@ { "cells": [ { - "attachments": {}, "cell_type": "markdown", "id": "87455ddb", "metadata": {}, "source": [ "# Multi-Input Tools\n", "\n", - "This notebook shows how to use a tool that requires multiple inputs with an agent.\n", - "\n", - "The difficulty in doing so comes from the fact that an agent decides its next step from a language model, which outputs a string. So if that step requires multiple inputs, they need to be parsed from that. Therefore, the currently supported way to do this is to write a smaller wrapper function that parses a string into multiple inputs.\n", - "\n", - "For a concrete example, let's work on giving an agent access to a multiplication function, which takes as input two integers. In order to use this, we will tell the agent to generate the \"Action Input\" as a comma-separated list of length two. We will then write a thin wrapper that takes a string, splits it into two around a comma, and passes both parsed sides as integers to the multiplication function." + "This notebook shows how to use a tool that requires multiple inputs with an agent. The recommended way to do so is with the `StructuredTool` class.\n", + "\n" ] }, { "cell_type": "code", "execution_count": 1, + "id": "113c8805", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import os\n", + "os.environ[\"LANGCHAIN_TRACING\"] = \"true\"" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "9c257017", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "from langchain import OpenAI\n", + "from langchain.agents import initialize_agent, AgentType\n", + "\n", + "llm = OpenAI(temperature=0)" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "21623e8f", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "from langchain.tools import StructuredTool\n", + "\n", + "def multiplier(a: float, b: float) -> float:\n", + " \"\"\"Multiply the provided floats.\"\"\"\n", + " return a * b\n", + "\n", + "tool = StructuredTool.from_function(multiplier)" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "ae7e8e07", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "# Structured tools are compatible with the STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION agent type. \n", + "agent_executor = initialize_agent([tool], llm, agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "6cfa22d7", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "\n", + "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n", + "\u001b[32;1m\u001b[1;3m\n", + "Thought: I need to multiply 3 and 4\n", + "Action:\n", + "```\n", + "{\n", + " \"action\": \"multiplier\",\n", + " \"action_input\": {\"a\": 3, \"b\": 4}\n", + "}\n", + "```\n", + "\u001b[0m\n", + "Observation: \u001b[36;1m\u001b[1;3m12\u001b[0m\n", + "Thought:\u001b[32;1m\u001b[1;3m I know what to respond\n", + "Action:\n", + "```\n", + "{\n", + " \"action\": \"Final Answer\",\n", + " \"action_input\": \"3 times 4 is 12\"\n", + "}\n", + "```\u001b[0m\n", + "\n", + "\u001b[1m> Finished chain.\u001b[0m\n" + ] + }, + { + "data": { + "text/plain": [ + "'3 times 4 is 12'" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "agent_executor.run(\"What is 3 times 4\")" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "e643b307", + "metadata": {}, + "source": [ + "## Multi-Input Tools with a string format\n", + "\n", + "An alternative to the structured tool would be to use the regular `Tool` class and accept a single string. The tool would then have to handle the parsing logic to extract the relavent values from the text, which tightly couples the tool representation to the agent prompt. This is still useful if the underlying language model can't reliabl generate structured schema. \n", + "\n", + "Let's take the multiplication function as an example. In order to use this, we will tell the agent to generate the \"Action Input\" as a comma-separated list of length two. We will then write a thin wrapper that takes a string, splits it into two around a comma, and passes both parsed sides as integers to the multiplication function." + ] + }, + { + "cell_type": "code", + "execution_count": 6, "id": "291149b6", "metadata": {}, "outputs": [], @@ -37,7 +158,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 7, "id": "f0b82020", "metadata": {}, "outputs": [], @@ -52,7 +173,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 8, "id": "6db1d43f", "metadata": {}, "outputs": [], @@ -70,7 +191,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 9, "id": "aa25d0ca", "metadata": {}, "outputs": [ @@ -97,7 +218,7 @@ "'3 times 4 is 12'" ] }, - "execution_count": 4, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } @@ -131,7 +252,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.1" + "version": "3.11.2" }, "vscode": { "interpreter": {