{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "2ca5bbbf-142b-48ed-89f2-18c63eac1eb0", "metadata": {}, "outputs": [], "source": [ "import os\n", "from dotenv import load_dotenv, find_dotenv\n", "_ = load_dotenv(find_dotenv())\n", "openai_api_key = os.environ[\"OPENAI_API_KEY\"]" ] }, { "cell_type": "markdown", "id": "42f0647a-3384-4a8d-bc5a-446b58a9ec80", "metadata": {}, "source": [ "## Basic App: Question & Answering from a Document" ] }, { "cell_type": "code", "execution_count": 2, "id": "196e2414-39ff-4643-9c31-b130697e3074", "metadata": {}, "outputs": [], "source": [ "from langchain_openai import OpenAI" ] }, { "cell_type": "code", "execution_count": 3, "id": "b191eb7d-a9df-47a6-95ac-fdec0b0b1969", "metadata": {}, "outputs": [], "source": [ "llm = OpenAI()" ] }, { "cell_type": "markdown", "id": "567ecd8a-34b9-4489-9b6d-7b257919737a", "metadata": {}, "source": [ "**Load the text file**" ] }, { "cell_type": "code", "execution_count": 4, "id": "e9801a4d-ecd7-460a-a4db-f0a1711163f9", "metadata": {}, "outputs": [], "source": [ "from langchain.document_loaders import TextLoader" ] }, { "cell_type": "code", "execution_count": 5, "id": "e01cbe49-38ce-40d2-8e01-01052483fbe5", "metadata": {}, "outputs": [], "source": [ "loader = TextLoader(\"data/be-good.txt\")" ] }, { "cell_type": "code", "execution_count": 6, "id": "afff80c1-1cd1-408e-ac28-2a8594af2de6", "metadata": {}, "outputs": [], "source": [ "document = loader.load()" ] }, { "cell_type": "markdown", "id": "4f6ff8b1-c63c-48b4-acaf-b959b98e770d", "metadata": {}, "source": [ "**The document is loaded as a Python list with metadata**" ] }, { "cell_type": "code", "execution_count": 7, "id": "684f2ccb-9ec4-4384-b875-3f89608292f8", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n" ] } ], "source": [ "print(type(document))" ] }, { "cell_type": "code", "execution_count": 8, "id": "3f712992-beac-420c-b94e-1db729bd9508", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "1\n" ] } ], "source": [ "print(len(document))" ] }, { "cell_type": "code", "execution_count": 9, "id": "6cb6e6d1-765b-4762-8213-0c56e4829427", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "{'source': 'data/be-good.txt'}\n" ] } ], "source": [ "print(document[0].metadata)" ] }, { "cell_type": "code", "execution_count": 10, "id": "eef34dd2-aace-45c9-a87b-c3967370f44f", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "You have 1 document.\n" ] } ], "source": [ "print(f\"You have {len(document)} document.\")" ] }, { "cell_type": "code", "execution_count": 11, "id": "dfb653b8-8035-40bf-b73c-542c90499486", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Your document has 16706 characters\n" ] } ], "source": [ "print(f\"Your document has {len(document[0].page_content)} characters\")" ] }, { "cell_type": "markdown", "id": "7d8fbef1-4447-4ef5-ba21-9211b4486904", "metadata": {}, "source": [ "**Split the document in small chunks**" ] }, { "cell_type": "code", "execution_count": 12, "id": "18899367-8f8e-4d47-a61c-8041bafb4cd2", "metadata": {}, "outputs": [], "source": [ "from langchain.text_splitter import RecursiveCharacterTextSplitter" ] }, { "cell_type": "code", "execution_count": 13, "id": "65f31176-187b-4e0c-819a-dd35b7e61ee3", "metadata": {}, "outputs": [], "source": [ "text_splitter = RecursiveCharacterTextSplitter(\n", " chunk_size=3000,\n", " chunk_overlap=400\n", ")" ] }, { "cell_type": "code", "execution_count": 14, "id": "0147e8c9-70fb-4990-8bf6-c77ea283200a", "metadata": {}, "outputs": [], "source": [ "document_chunks = text_splitter.split_documents(document)" ] }, { "cell_type": "code", "execution_count": 15, "id": "86820a0a-e307-4bb9-9b69-24284d9f0754", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Now you have 8 chunks.\n" ] } ], "source": [ "print(f\"Now you have {len(document_chunks)} chunks.\")" ] }, { "cell_type": "markdown", "id": "1756c471-5af1-4ba4-8f90-cfc70e897155", "metadata": {}, "source": [ "**Convert text chunks in numeric vectors (called \"embeddings\")**" ] }, { "cell_type": "code", "execution_count": 16, "id": "2e40b2df-53ad-4984-8972-cf7258b762fb", "metadata": {}, "outputs": [], "source": [ "from langchain.embeddings.openai import OpenAIEmbeddings" ] }, { "cell_type": "code", "execution_count": 17, "id": "c1e7c4f6-2116-4ce1-8349-640fa6591970", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/Users/juliocolomer/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The class `langchain_community.embeddings.openai.OpenAIEmbeddings` was deprecated in langchain-community 0.1.0 and will be removed in 0.2.0. An updated version of the class exists in the langchain-openai package and should be used instead. To use it run `pip install -U langchain-openai` and import as `from langchain_openai import OpenAIEmbeddings`.\n", " warn_deprecated(\n" ] } ], "source": [ "embeddings = OpenAIEmbeddings()" ] }, { "cell_type": "markdown", "id": "67881eb4-7418-4423-b4b9-b750e4a579cf", "metadata": {}, "source": [ "**Load the embeddings to a vector database**" ] }, { "cell_type": "code", "execution_count": 18, "id": "75acf1fc-25a4-437c-bd1b-7310a83bae9e", "metadata": {}, "outputs": [], "source": [ "from langchain.vectorstores import FAISS" ] }, { "cell_type": "markdown", "id": "014dc49b-498a-49b0-883c-f323769320b3", "metadata": {}, "source": [ "*Careful: the next operation is expensive in OpenAI*" ] }, { "cell_type": "code", "execution_count": 19, "id": "8a2e4dbc-af28-497f-877a-933347c747ad", "metadata": {}, "outputs": [], "source": [ "stored_embeddings = FAISS.from_documents(document_chunks, embeddings)" ] }, { "cell_type": "markdown", "id": "40ae930c-5d99-45c5-8597-52457d22b6d1", "metadata": {}, "source": [ "**Create a Retrieval Question & Answering Chain**" ] }, { "cell_type": "code", "execution_count": 20, "id": "e30338bd-58ae-467d-a01e-8bef3ae435b5", "metadata": {}, "outputs": [], "source": [ "from langchain.chains import RetrievalQA" ] }, { "cell_type": "code", "execution_count": 21, "id": "d9bed1ac-d148-4fb1-9382-bc58db111d73", "metadata": {}, "outputs": [], "source": [ "QA_chain = RetrievalQA.from_chain_type(\n", " llm=llm,\n", " chain_type=\"stuff\",\n", " retriever=stored_embeddings.as_retriever()\n", ")" ] }, { "cell_type": "markdown", "id": "71a96c6d-a473-4ecc-885d-55f1618487d4", "metadata": {}, "source": [ "**Now we have a Question & Answering APP**" ] }, { "cell_type": "code", "execution_count": 22, "id": "c432c922-984b-49b9-b3c1-4a6c5d2ccd00", "metadata": {}, "outputs": [], "source": [ "question = \"\"\"\n", "What is this article about? \n", "Describe it in less than 100 words.\n", "\"\"\"" ] }, { "cell_type": "code", "execution_count": 23, "id": "7d407274-69c0-4d7f-8def-5e2275027a41", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/Users/juliocolomer/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The function `run` was deprecated in LangChain 0.1.0 and will be removed in 0.2.0. Use invoke instead.\n", " warn_deprecated(\n" ] }, { "data": { "text/plain": [ "'\\n\\nThis article is about the importance of being good in business, both as a moral principle and as a strategic advantage. The author argues that companies that prioritize making something people want and being good to their users over making money often end up being more successful in the long run. The article also discusses various examples, including Craigslist and Google, to support this idea. The author also suggests that being good can act as a compass for making decisions and can attract top talent.'" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "QA_chain.run(question)" ] }, { "cell_type": "code", "execution_count": 24, "id": "87459203-207e-4180-af54-1a48457143b2", "metadata": {}, "outputs": [], "source": [ "question2 = \"\"\"\n", "And how does it explain how to create somethin people want?\n", "\"\"\"" ] }, { "cell_type": "code", "execution_count": 25, "id": "86947fdc-3d59-465c-b1a9-a061421bccb6", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "' It explains that creating something people want can be achieved by following the motto of \"Make something people want\" and not worrying too much about the business model at first. By focusing on creating something that truly benefits and helps people, it can lead to a successful and desirable product. Additionally, being good and benevolent can attract investors, customers, and employees, and can act as a guiding compass for decision making.'" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "QA_chain.run(question2)" ] }, { "cell_type": "markdown", "id": "d643a907-1d84-4583-8c1d-f3062a7172eb", "metadata": {}, "source": [ "## Simple Agent" ] }, { "cell_type": "code", "execution_count": 26, "id": "c852a0af-e258-47c3-b40d-5298aed59ab6", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Collecting numexpr\n", " Downloading numexpr-2.9.0-cp311-cp311-macosx_11_0_arm64.whl (91 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m91.8/91.8 kB\u001b[0m \u001b[31m1.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mta \u001b[36m0:00:01\u001b[0m\n", "\u001b[?25hRequirement already satisfied: numpy>=1.13.3 in /Users/juliocolomer/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages (from numexpr) (1.26.3)\n", "Installing collected packages: numexpr\n", "Successfully installed numexpr-2.9.0\n", "\n", "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.1.2\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.3.2\u001b[0m\n", "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpython3.11 -m pip install --upgrade pip\u001b[0m\n" ] } ], "source": [ "#!pip install numexpr" ] }, { "cell_type": "code", "execution_count": 27, "id": "33694fdb-092c-49f4-a823-30dcae683e22", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/Users/juliocolomer/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The class `langchain_community.llms.openai.OpenAI` was deprecated in langchain-community 0.0.10 and will be removed in 0.2.0. An updated version of the class exists in the langchain-openai package and should be used instead. To use it run `pip install -U langchain-openai` and import as `from langchain_openai import OpenAI`.\n", " warn_deprecated(\n" ] }, { "data": { "text/plain": [ "[Tool(name='Calculator', description='Useful for when you need to answer questions about math.', func=, async_client=, openai_api_key='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', openai_proxy='')))>, coroutine=, async_client=, openai_api_key='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', openai_proxy='')))>)]" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from langchain.agents import load_tools\n", "from langchain.llms import OpenAI\n", "from langchain.agents import AgentType\n", "\n", "llm=OpenAI()\n", "\n", "tool_names = [\"llm-math\"]\n", "tools = load_tools(tool_names, llm=llm)\n", "tools" ] }, { "cell_type": "code", "execution_count": 28, "id": "fb773d04-eb42-44be-a790-096512b7618f", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/Users/juliocolomer/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The function `initialize_agent` was deprecated in LangChain 0.1.0 and will be removed in 0.2.0. Use Use new agent constructor methods like create_react_agent, create_json_agent, create_structured_chat_agent, etc. instead.\n", " warn_deprecated(\n" ] } ], "source": [ "from langchain.agents import initialize_agent\n", "\n", "agent = initialize_agent(tools,\n", " llm,\n", " agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n", " verbose=True,\n", " max_iterations=3)" ] }, { "cell_type": "code", "execution_count": 29, "id": "68206e03-0099-4f39-8b7b-30f18bcb63d9", "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 I should use a calculator to solve this problem.\n", "Action: Calculator\n", "Action Input: 133 * 142\u001b[0m\n", "Observation: \u001b[36;1m\u001b[1;3mAnswer: 18886\u001b[0m\n", "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n", "Final Answer: 18886\u001b[0m\n", "\n", "\u001b[1m> Finished chain.\u001b[0m\n" ] }, { "data": { "text/plain": [ "'18886'" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" } ], "source": [ "agent.run(\"What is 133 by 142?\")" ] }, { "cell_type": "markdown", "id": "cc06baea-c16e-4566-8f6d-ea9f473454d9", "metadata": {}, "source": [ "**Let's make the agent fail**" ] }, { "cell_type": "code", "execution_count": 30, "id": "d1f6740e-3c43-4e9f-b454-dc8ae5af7612", "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 I do not have access to the internet, so I cannot look up the answer.\n", "Action: I can use my knowledge of history to try to answer this question.\n", "Action Input: Napoleon Bonaparte\u001b[0m\n", "Observation: I can use my knowledge of history to try to answer this question. is not a valid tool, try one of [Calculator].\n", "Thought:\u001b[32;1m\u001b[1;3m I do not have access to the internet, so I cannot look up the answer.\n", "Action: I can use my knowledge of history to try to answer this question.\n", "Action Input: Napoleon Bonaparte\u001b[0m\n", "Observation: I can use my knowledge of history to try to answer this question. is not a valid tool, try one of [Calculator].\n", "Thought:\u001b[32;1m\u001b[1;3m I can use my knowledge of history to try to answer this question.\n", "Action: I can use the Calculator to perform a quick search.\n", "Action Input: Napoleon Bonaparte wife\u001b[0m\n", "Observation: I can use the Calculator to perform a quick search. is not a valid tool, try one of [Calculator].\n", "Thought:\u001b[32;1m\u001b[1;3m\u001b[0m\n", "\n", "\u001b[1m> Finished chain.\u001b[0m\n" ] }, { "data": { "text/plain": [ "'Agent stopped due to iteration limit or time limit.'" ] }, "execution_count": 30, "metadata": {}, "output_type": "execute_result" } ], "source": [ "agent.run(\"Who was the wife of Napoleon Bonaparte?\")" ] }, { "cell_type": "markdown", "id": "52aaefd6-fbf6-4fcc-a4e7-ff7327dac84b", "metadata": {}, "source": [ "## Custom Agent" ] }, { "cell_type": "code", "execution_count": 31, "id": "cfdf7465-83ca-4106-a1dd-26f5d7fca39b", "metadata": {}, "outputs": [], "source": [ "from typing import Optional\n", "from langchain.tools import BaseTool\n", "from langchain.callbacks.manager import AsyncCallbackManagerForToolRun\n", "from langchain.callbacks.manager import CallbackManagerForToolRun" ] }, { "cell_type": "code", "execution_count": 32, "id": "5a96d646-097f-4515-aea1-40b4e97a4f7c", "metadata": {}, "outputs": [], "source": [ "class CustomSearchTool(BaseTool):\n", " name = \"article search\"\n", " description = \"useful for when you need to answer questions about our article\"\n", "\n", " def _run(self, query: str, run_manager: Optional[CallbackManagerForToolRun] = None) -> str:\n", " store = stored_embeddings.as_retriever()\n", " docs = store.get_relevant_documents(query)\n", " text_list = [doc.page_content for doc in docs]\n", " return \"\\n\".join(text_list)\n", "\n", " async def _arun(self, query: str, run_manager: Optional[AsyncCallbackManagerForToolRun] = None) -> str:\n", " \"\"\"Use the tool asynchronously.\"\"\"\n", " raise NotImplementedError(\"custom_search does not support async\")" ] }, { "cell_type": "code", "execution_count": 33, "id": "4b5533be-1ca3-4bb9-bad7-8c7d3618525c", "metadata": {}, "outputs": [], "source": [ "from langchain.agents import AgentType\n", "\n", "tools = [CustomSearchTool()]\n", "\n", "agent = initialize_agent(\n", " tools, \n", " llm, \n", " agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, \n", " verbose=True, \n", " max_iterations=3\n", ")" ] }, { "cell_type": "code", "execution_count": 34, "id": "fcf94ee6-d553-4902-b366-b6a70b0da79c", "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 I should use the article search tool to find the article and read the abstract to get a general understanding of the topic.\n", "Action: article search\n", "Action Input: \"article about\"\u001b[0m\n", "Observation: \u001b[36;1m\u001b[1;3mBe good\n", "April 2008(This essay is derived from a talk at the 2008 Startup School.)About a month after we started Y Combinator we came up with the\n", "phrase that became our motto: Make something people want. We've\n", "learned a lot since then, but if I were choosing now that's still\n", "the one I'd pick.Another thing we tell founders is not to worry too much about the\n", "business model, at least at first. Not because making money is\n", "unimportant, but because it's so much easier than building something\n", "great.A couple weeks ago I realized that if you put those two ideas\n", "together, you get something surprising. Make something people want.\n", "Don't worry too much about making money. What you've got is a\n", "description of a charity.When you get an unexpected result like this, it could either be a\n", "bug or a new discovery. Either businesses aren't supposed to be\n", "like charities, and we've proven by reductio ad absurdum that one\n", "or both of the principles we began with is false. Or we have a new\n", "idea.I suspect it's the latter, because as soon as this thought occurred\n", "to me, a whole bunch of other things fell into place.ExamplesFor example, Craigslist. It's not a charity, but they run it like\n", "one. And they're astoundingly successful. When you scan down the\n", "list of most popular web sites, the number of employees at Craigslist\n", "looks like a misprint. Their revenues aren't as high as they could\n", "be, but most startups would be happy to trade places with them.In Patrick O'Brian's novels, his captains always try to get upwind\n", "of their opponents. If you're upwind, you decide when and if to\n", "engage the other ship. Craigslist is effectively upwind of enormous\n", "revenues. They'd face some challenges if they wanted to make more,\n", "but not the sort you face when you're tacking upwind, trying to\n", "force a crappy product on ambivalent users by spending ten times\n", "as much on sales as on development. [1]I'm not saying startups should aim to end up like Craigslist.\n", "They're a product of unusual circumstances. But they're a good\n", "model for the early phases.Google looked a lot like a charity in the beginning. They didn't\n", "have ads for over a year. At year 1, Google was indistinguishable\n", "from a nonprofit. If a nonprofit or government organization had\n", "started a project to index the web, Google at year 1 is the limit\n", "of what they'd have produced.Back when I was working on spam filters I thought it would be a\n", "good idea to have a web-based email service with good spam filtering.\n", "I wasn't thinking of it as a company. I just wanted to keep people\n", "from getting spammed. But as I thought more about this project, I\n", "realized it would probably have to be a company. It would cost\n", "something to run, and it would be a pain to fund with grants and\n", "donations.That was a surprising realization. Companies often claim to be\n", "benevolent, but it was surprising to realize there were purely\n", "benevolent projects that had to be embodied as companies to work.I didn't want to start another company, so I didn't do it. But if\n", "it and they've been growing rapidly. And yet for most of Octopart's\n", "life, the biggest distributor, Digi-Key, has been trying to force\n", "them take their prices off the site. Octopart is sending them\n", "customers for free, and yet Digi-Key is trying to make that traffic\n", "stop. Why? Because their current business model depends on\n", "overcharging people who have incomplete information about prices.\n", "They don't want search to work.The Octoparts are the nicest guys in the world. They dropped out\n", "of the PhD program in physics at Berkeley to do this. They just\n", "wanted to fix a problem they encountered in their research. Imagine\n", "how much time you could save the world's engineers if they could\n", "do searches online. So when I hear that a big, evil company is\n", "trying to stop them in order to keep search broken, it makes me\n", "really want to help them. It makes me spend more time on the Octoparts\n", "than I do with most of the other startups we've funded. It just\n", "made me spend several minutes telling you how great they are. Why?\n", "Because they're good guys and they're trying to help the world.If you're benevolent, people will rally around you: investors,\n", "customers, other companies, and potential employees. In the long\n", "term the most important may be the potential employees. I think\n", "everyone knows now that \n", "good hackers are much better than mediocre\n", "ones. If you can attract the best hackers to work for you, as\n", "Google has, you have a big advantage. And the very best hackers\n", "tend to be idealistic. They're not desperate for a job. They can\n", "work wherever they want. So most want to work on things that will\n", "make the world better.CompassBut the most important advantage of being good is that it acts as\n", "a compass. One of the hardest parts of doing a startup is that you\n", "have so many choices. There are just two or three of you, and a\n", "thousand things you could do. How do you decide?Here's the answer: Do whatever's best for your users. You can hold\n", "onto this like a rope in a hurricane, and it will save you if\n", "anything can. Follow it and it will take you through everything\n", "you need to do.It's even the answer to questions that seem unrelated, like how to\n", "convince investors to give you money. If you're a good salesman,\n", "you could try to just talk them into it. But the more reliable\n", "route is to convince them through your users: if you make something\n", "users love enough to tell their friends, you grow exponentially,\n", "and that will convince any investor.Being good is a particularly useful strategy for making decisions\n", "in complex situations because it's stateless. It's like telling\n", "the truth. The trouble with lying is that you have to remember\n", "everything you've said in the past to make sure you don't contradict\n", "yourself. If you tell the truth you don't have to remember anything,\n", "and that's a really useful property in domains where things happen\n", "fast.For example, Y Combinator has now invested in 80 startups, 57 of\n", "which are still alive. (The rest have died or merged or been\n", "everything you've said in the past to make sure you don't contradict\n", "yourself. If you tell the truth you don't have to remember anything,\n", "and that's a really useful property in domains where things happen\n", "fast.For example, Y Combinator has now invested in 80 startups, 57 of\n", "which are still alive. (The rest have died or merged or been\n", "acquired.) When you're trying to advise 57 startups, it turns out\n", "you have to have a stateless algorithm. You can't have ulterior\n", "motives when you have 57 things going on at once, because you can't\n", "remember them. So our rule is just to do whatever's best for the\n", "founders. Not because we're particularly benevolent, but because\n", "it's the only algorithm that works on that scale.When you write something telling people to be good, you seem to be\n", "claiming to be good yourself. So I want to say explicitly that I\n", "am not a particularly good person. When I was a kid I was firmly\n", "in the camp of bad. The way adults used the word good, it seemed\n", "to be synonymous with quiet, so I grew up very suspicious of it.You know how there are some people whose names come up in conversation\n", "and everyone says \"He's such a great guy?\" People never say\n", "that about me. The best I get is \"he means well.\" I am not claiming\n", "to be good. At best I speak good as a second language.So I'm not suggesting you be good in the usual sanctimonious way.\n", "I'm suggesting it because it works. It will work not just as a\n", "statement of \"values,\" but as a guide to strategy,\n", "and even a design spec for software. Don't just not be evil. Be\n", "good.Notes[1] Fifty years ago\n", "it would have seemed shocking for a public company not to pay\n", "dividends. Now many tech companies don't. The markets seem to\n", "have figured out how to value potential dividends. Maybe that isn't\n", "the last step in this evolution. Maybe markets will eventually get\n", "comfortable with potential earnings. (VCs already are, and at least\n", "some of them consistently make money.)I realize this sounds like the stuff one used to hear about the\n", "\"new economy\" during the Bubble. Believe me, I was not drinking\n", "that kool-aid at the time. But I'm convinced there were some \n", "good\n", "ideas buried in Bubble thinking. For example, it's ok to focus on\n", "growth instead of profits—but only if the growth is genuine.\n", "You can't be buying users; that's a pyramid scheme. But a company\n", "with rapid, genuine growth is valuable, and eventually markets learn\n", "how to value valuable things.[2] The idea of starting\n", "a company with benevolent aims is currently undervalued, because\n", "the kind of people who currently make that their explicit goal don't\n", "usually do a very good job.It's one of the standard career paths of trustafarians to start\n", "some vaguely benevolent business. The problem with most of them\n", "is that they either have a bogus political agenda or are feebly\n", "executed. The trustafarians' ancestors didn't get rich by preserving\n", "their traditional culture; maybe people in Bolivia don't want to\u001b[0m\n", "Thought:\u001b[32;1m\u001b[1;3m After reading the abstract, I can see that this article is about the concept of being benevolent in business and how it can lead to success and growth. It also discusses the idea of making something people want and not focusing too much on profits in the early stages of a startup.\n", "Action: article search\n", "Action Input: \"benevolent business success\"\u001b[0m\n", "Observation: \u001b[36;1m\u001b[1;3mguarantees you'll fail.Here's where benevolence comes in. If you feel you're really helping\n", "people, you'll keep working even when it seems like your startup\n", "is doomed. Most of us have some amount of natural benevolence.\n", "The mere fact that someone needs you makes you want to help them.\n", "So if you start the kind of startup where users come back each day,\n", "you've basically built yourself a giant tamagotchi. You've made\n", "something you need to take care of.Blogger is a famous example of a startup that went through really\n", "low lows and survived. At one point they ran out of money and\n", "everyone left. Evan Williams came in to work the next day, and there\n", "was no one but him. What kept him going? Partly that users needed\n", "him. He was hosting thousands of people's blogs. He couldn't just\n", "let the site die.There are many advantages of launching quickly, but the most important\n", "may be that once you have users, the tamagotchi effect kicks in.\n", "Once you have users to take care of, you're forced to figure out\n", "what will make them happy, and that's actually very valuable\n", "information.The added confidence that comes from trying to help people can\n", "also help you with investors. One of the founders of \n", "Chatterous told \n", "me recently that he and his cofounder had decided that this service\n", "was something the world needed, so they were going to keep working\n", "on it no matter what, even if they had to move back to Canada and live\n", "in their parents' basements.Once they realized this, they stopped caring so much what investors thought\n", "about them. They still met with them, but they weren't going to\n", "die if they didn't get their money. And you know what? The investors\n", "got a lot more interested. They could sense that the Chatterouses\n", "were going to do this startup with or without them.If you're really committed and your startup is cheap to run, you\n", "become very hard to kill. And practically all startups, even the\n", "most successful, come close to death at some point. So if doing\n", "good for people gives you a sense of mission that makes you harder\n", "to kill, that alone more than compensates for whatever you lose by\n", "not choosing a more selfish project.HelpAnother advantage of being good is that it makes other people want\n", "to help you. This too seems to be an inborn trait in humans.One of the startups we've funded, Octopart, is currently locked in\n", "a classic battle of good versus evil. They're a search site for\n", "industrial components. A lot of people need to search for components,\n", "and before Octopart there was no good way to do it. That, it turned\n", "out, was no coincidence.Octopart built the right way to search for components. Users like\n", "it and they've been growing rapidly. And yet for most of Octopart's\n", "life, the biggest distributor, Digi-Key, has been trying to force\n", "them take their prices off the site. Octopart is sending them\n", "customers for free, and yet Digi-Key is trying to make that traffic\n", "stop. Why? Because their current business model depends on\n", "were going to make money selling hardware at high prices. But by\n", "gaining control of the PC standard, Microsoft opened up the market\n", "to any manufacturer. Hardware prices plummeted, and lots of people\n", "got to have computers who couldn't otherwise have afforded them.\n", "It's the sort of thing you'd expect Google to do.Microsoft isn't so benevolent now. Now when one thinks of what\n", "Microsoft does to users, all the verbs that come to mind begin with\n", "F. [3] And yet it doesn't seem to pay.\n", "Their stock price has been flat for years. Back when they were\n", "Robin Hood, their stock price rose like Google's. Could there be\n", "a connection?You can see how there would be. When you're small, you can't bully\n", "customers, so you have to charm them. Whereas when you're big you\n", "can maltreat them at will, and you tend to, because it's easier\n", "than satisfying them. You grow big by being nice, but you can stay\n", "big by being mean.You get away with it till the underlying conditions change, and\n", "then all your victims escape. So \"Don't be evil\" may be the most\n", "valuable thing Paul Buchheit made for Google, because it may turn\n", "out to be an elixir of corporate youth. I'm sure they find it\n", "constraining, but think how valuable it will be if it saves them\n", "from lapsing into the fatal laziness that afflicted Microsoft and\n", "IBM.The curious thing is, this elixir is freely available to any other\n", "company. Anyone can adopt \"Don't be evil.\" The catch is that\n", "people will hold you to it. So I don't think you're going to see\n", "record labels or tobacco companies using this discovery.MoraleThere's a lot of external evidence that benevolence works. But how\n", "does it work? One advantage of investing in a large number of\n", "startups is that you get a lot of data about how they work. From\n", "what we've seen, being good seems to help startups in three ways:\n", "it improves their morale, it makes other people want to help them,\n", "and above all, it helps them be decisive.Morale is tremendously important to a startup—so important\n", "that morale alone is almost enough to determine success. Startups\n", "are often described as emotional roller-coasters. One minute you're\n", "going to take over the world, and the next you're doomed. The\n", "problem with feeling you're doomed is not just that it makes you\n", "unhappy, but that it makes you stop working. So the downhills\n", "of the roller-coaster are more of a self fulfilling prophecy than\n", "the uphills. If feeling you're going to succeed makes you work\n", "harder, that probably improves your chances of succeeding, but if\n", "feeling you're going to fail makes you stop working, that practically\n", "guarantees you'll fail.Here's where benevolence comes in. If you feel you're really helping\n", "people, you'll keep working even when it seems like your startup\n", "is doomed. Most of us have some amount of natural benevolence.\n", "The mere fact that someone needs you makes you want to help them.\n", "So if you start the kind of startup where users come back each day,\n", "usually do a very good job.It's one of the standard career paths of trustafarians to start\n", "some vaguely benevolent business. The problem with most of them\n", "is that they either have a bogus political agenda or are feebly\n", "executed. The trustafarians' ancestors didn't get rich by preserving\n", "their traditional culture; maybe people in Bolivia don't want to\n", "either. And starting an organic farm, though it's at least\n", "straightforwardly benevolent, doesn't help people on the scale that\n", "Google does.Most explicitly benevolent projects don't hold themselves sufficiently\n", "accountable. They act as if having good intentions were enough to\n", "guarantee good effects.[3] Users dislike their\n", "new operating system so much that they're starting petitions to\n", "save the old one. And the old one was nothing special. The hackers\n", "within Microsoft must know in their hearts that if the company\n", "really cared about users they'd just advise them to switch to OSX.Thanks to Trevor Blackwell, Paul Buchheit, Jessica Livingston,\n", "and Robert Morris for reading drafts of this.\n", "everything you've said in the past to make sure you don't contradict\n", "yourself. If you tell the truth you don't have to remember anything,\n", "and that's a really useful property in domains where things happen\n", "fast.For example, Y Combinator has now invested in 80 startups, 57 of\n", "which are still alive. (The rest have died or merged or been\n", "acquired.) When you're trying to advise 57 startups, it turns out\n", "you have to have a stateless algorithm. You can't have ulterior\n", "motives when you have 57 things going on at once, because you can't\n", "remember them. So our rule is just to do whatever's best for the\n", "founders. Not because we're particularly benevolent, but because\n", "it's the only algorithm that works on that scale.When you write something telling people to be good, you seem to be\n", "claiming to be good yourself. So I want to say explicitly that I\n", "am not a particularly good person. When I was a kid I was firmly\n", "in the camp of bad. The way adults used the word good, it seemed\n", "to be synonymous with quiet, so I grew up very suspicious of it.You know how there are some people whose names come up in conversation\n", "and everyone says \"He's such a great guy?\" People never say\n", "that about me. The best I get is \"he means well.\" I am not claiming\n", "to be good. At best I speak good as a second language.So I'm not suggesting you be good in the usual sanctimonious way.\n", "I'm suggesting it because it works. It will work not just as a\n", "statement of \"values,\" but as a guide to strategy,\n", "and even a design spec for software. Don't just not be evil. Be\n", "good.Notes[1] Fifty years ago\n", "it would have seemed shocking for a public company not to pay\n", "dividends. Now many tech companies don't. The markets seem to\n", "have figured out how to value potential dividends. Maybe that isn't\n", "the last step in this evolution. Maybe markets will eventually get\n", "comfortable with potential earnings. (VCs already are, and at least\n", "some of them consistently make money.)I realize this sounds like the stuff one used to hear about the\n", "\"new economy\" during the Bubble. Believe me, I was not drinking\n", "that kool-aid at the time. But I'm convinced there were some \n", "good\n", "ideas buried in Bubble thinking. For example, it's ok to focus on\n", "growth instead of profits—but only if the growth is genuine.\n", "You can't be buying users; that's a pyramid scheme. But a company\n", "with rapid, genuine growth is valuable, and eventually markets learn\n", "how to value valuable things.[2] The idea of starting\n", "a company with benevolent aims is currently undervalued, because\n", "the kind of people who currently make that their explicit goal don't\n", "usually do a very good job.It's one of the standard career paths of trustafarians to start\n", "some vaguely benevolent business. The problem with most of them\n", "is that they either have a bogus political agenda or are feebly\n", "executed. The trustafarians' ancestors didn't get rich by preserving\n", "their traditional culture; maybe people in Bolivia don't want to\u001b[0m\n", "Thought:" ] }, { "ename": "BadRequestError", "evalue": "Error code: 400 - {'error': {'message': \"This model's maximum context length is 4097 tokens, however you requested 4979 tokens (4723 in your prompt; 256 for the completion). Please reduce your prompt; or completion length.\", 'type': 'invalid_request_error', 'param': None, 'code': None}}", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mBadRequestError\u001b[0m Traceback (most recent call last)", "Cell \u001b[0;32mIn[34], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43magent\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mWhat is this article about? Describe it in less than 100 words.\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain_core/_api/deprecation.py:145\u001b[0m, in \u001b[0;36mdeprecated..deprecate..warning_emitting_wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 143\u001b[0m warned \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m 144\u001b[0m emit_warning()\n\u001b[0;32m--> 145\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mwrapped\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain/chains/base.py:538\u001b[0m, in \u001b[0;36mChain.run\u001b[0;34m(self, callbacks, tags, metadata, *args, **kwargs)\u001b[0m\n\u001b[1;32m 536\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(args) \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m 537\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m`run` supports only one positional argument.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 538\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43margs\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtags\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtags\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmetadata\u001b[49m\u001b[43m)\u001b[49m[\n\u001b[1;32m 539\u001b[0m _output_key\n\u001b[1;32m 540\u001b[0m ]\n\u001b[1;32m 542\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m kwargs \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m args:\n\u001b[1;32m 543\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m(kwargs, callbacks\u001b[38;5;241m=\u001b[39mcallbacks, tags\u001b[38;5;241m=\u001b[39mtags, metadata\u001b[38;5;241m=\u001b[39mmetadata)[\n\u001b[1;32m 544\u001b[0m _output_key\n\u001b[1;32m 545\u001b[0m ]\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain_core/_api/deprecation.py:145\u001b[0m, in \u001b[0;36mdeprecated..deprecate..warning_emitting_wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 143\u001b[0m warned \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m 144\u001b[0m emit_warning()\n\u001b[0;32m--> 145\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mwrapped\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain/chains/base.py:363\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks, tags, metadata, run_name, include_run_info)\u001b[0m\n\u001b[1;32m 331\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Execute the chain.\u001b[39;00m\n\u001b[1;32m 332\u001b[0m \n\u001b[1;32m 333\u001b[0m \u001b[38;5;124;03mArgs:\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 354\u001b[0m \u001b[38;5;124;03m `Chain.output_keys`.\u001b[39;00m\n\u001b[1;32m 355\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 356\u001b[0m config \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m 357\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcallbacks\u001b[39m\u001b[38;5;124m\"\u001b[39m: callbacks,\n\u001b[1;32m 358\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtags\u001b[39m\u001b[38;5;124m\"\u001b[39m: tags,\n\u001b[1;32m 359\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmetadata\u001b[39m\u001b[38;5;124m\"\u001b[39m: metadata,\n\u001b[1;32m 360\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_name\u001b[39m\u001b[38;5;124m\"\u001b[39m: run_name,\n\u001b[1;32m 361\u001b[0m }\n\u001b[0;32m--> 363\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 364\u001b[0m \u001b[43m \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 365\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast\u001b[49m\u001b[43m(\u001b[49m\u001b[43mRunnableConfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m{\u001b[49m\u001b[43mk\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mk\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mitems\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mis\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m}\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 366\u001b[0m \u001b[43m \u001b[49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 367\u001b[0m \u001b[43m \u001b[49m\u001b[43minclude_run_info\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minclude_run_info\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 368\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain/chains/base.py:162\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m 160\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 161\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n\u001b[0;32m--> 162\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m 163\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_end(outputs)\n\u001b[1;32m 164\u001b[0m final_outputs: Dict[\u001b[38;5;28mstr\u001b[39m, Any] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprep_outputs(\n\u001b[1;32m 165\u001b[0m inputs, outputs, return_only_outputs\n\u001b[1;32m 166\u001b[0m )\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain/chains/base.py:156\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m 149\u001b[0m run_manager \u001b[38;5;241m=\u001b[39m callback_manager\u001b[38;5;241m.\u001b[39mon_chain_start(\n\u001b[1;32m 150\u001b[0m dumpd(\u001b[38;5;28mself\u001b[39m),\n\u001b[1;32m 151\u001b[0m inputs,\n\u001b[1;32m 152\u001b[0m name\u001b[38;5;241m=\u001b[39mrun_name,\n\u001b[1;32m 153\u001b[0m )\n\u001b[1;32m 154\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 155\u001b[0m outputs \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m--> 156\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 157\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported\n\u001b[1;32m 158\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call(inputs)\n\u001b[1;32m 159\u001b[0m )\n\u001b[1;32m 160\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 161\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain/agents/agent.py:1391\u001b[0m, in \u001b[0;36mAgentExecutor._call\u001b[0;34m(self, inputs, run_manager)\u001b[0m\n\u001b[1;32m 1389\u001b[0m \u001b[38;5;66;03m# We now enter the agent loop (until it returns something).\u001b[39;00m\n\u001b[1;32m 1390\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_continue(iterations, time_elapsed):\n\u001b[0;32m-> 1391\u001b[0m next_step_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_take_next_step\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1392\u001b[0m \u001b[43m \u001b[49m\u001b[43mname_to_tool_map\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1393\u001b[0m \u001b[43m \u001b[49m\u001b[43mcolor_mapping\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1394\u001b[0m \u001b[43m \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1395\u001b[0m \u001b[43m \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1396\u001b[0m \u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1397\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1398\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(next_step_output, AgentFinish):\n\u001b[1;32m 1399\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_return(\n\u001b[1;32m 1400\u001b[0m next_step_output, intermediate_steps, run_manager\u001b[38;5;241m=\u001b[39mrun_manager\n\u001b[1;32m 1401\u001b[0m )\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain/agents/agent.py:1097\u001b[0m, in \u001b[0;36mAgentExecutor._take_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m 1088\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_take_next_step\u001b[39m(\n\u001b[1;32m 1089\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 1090\u001b[0m name_to_tool_map: Dict[\u001b[38;5;28mstr\u001b[39m, BaseTool],\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1094\u001b[0m run_manager: Optional[CallbackManagerForChainRun] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m 1095\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Union[AgentFinish, List[Tuple[AgentAction, \u001b[38;5;28mstr\u001b[39m]]]:\n\u001b[1;32m 1096\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_consume_next_step(\n\u001b[0;32m-> 1097\u001b[0m \u001b[43m[\u001b[49m\n\u001b[1;32m 1098\u001b[0m \u001b[43m \u001b[49m\u001b[43ma\u001b[49m\n\u001b[1;32m 1099\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43ma\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_iter_next_step\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1100\u001b[0m \u001b[43m \u001b[49m\u001b[43mname_to_tool_map\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1101\u001b[0m \u001b[43m \u001b[49m\u001b[43mcolor_mapping\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1102\u001b[0m \u001b[43m \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1103\u001b[0m \u001b[43m \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1104\u001b[0m \u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1105\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1106\u001b[0m \u001b[43m \u001b[49m\u001b[43m]\u001b[49m\n\u001b[1;32m 1107\u001b[0m )\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain/agents/agent.py:1097\u001b[0m, in \u001b[0;36m\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 1088\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_take_next_step\u001b[39m(\n\u001b[1;32m 1089\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 1090\u001b[0m name_to_tool_map: Dict[\u001b[38;5;28mstr\u001b[39m, BaseTool],\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1094\u001b[0m run_manager: Optional[CallbackManagerForChainRun] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m 1095\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Union[AgentFinish, List[Tuple[AgentAction, \u001b[38;5;28mstr\u001b[39m]]]:\n\u001b[1;32m 1096\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_consume_next_step(\n\u001b[0;32m-> 1097\u001b[0m \u001b[43m[\u001b[49m\n\u001b[1;32m 1098\u001b[0m \u001b[43m \u001b[49m\u001b[43ma\u001b[49m\n\u001b[1;32m 1099\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43ma\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_iter_next_step\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1100\u001b[0m \u001b[43m \u001b[49m\u001b[43mname_to_tool_map\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1101\u001b[0m \u001b[43m \u001b[49m\u001b[43mcolor_mapping\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1102\u001b[0m \u001b[43m \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1103\u001b[0m \u001b[43m \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1104\u001b[0m \u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1105\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1106\u001b[0m \u001b[43m \u001b[49m\u001b[43m]\u001b[49m\n\u001b[1;32m 1107\u001b[0m )\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain/agents/agent.py:1125\u001b[0m, in \u001b[0;36mAgentExecutor._iter_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m 1122\u001b[0m intermediate_steps \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_prepare_intermediate_steps(intermediate_steps)\n\u001b[1;32m 1124\u001b[0m \u001b[38;5;66;03m# Call the LLM to see what to do.\u001b[39;00m\n\u001b[0;32m-> 1125\u001b[0m output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43magent\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mplan\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1126\u001b[0m \u001b[43m \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1127\u001b[0m \u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_child\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 1128\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1129\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1130\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m OutputParserException \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 1131\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandle_parsing_errors, \u001b[38;5;28mbool\u001b[39m):\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain/agents/agent.py:694\u001b[0m, in \u001b[0;36mAgent.plan\u001b[0;34m(self, intermediate_steps, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m 682\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Given input, decided what to do.\u001b[39;00m\n\u001b[1;32m 683\u001b[0m \n\u001b[1;32m 684\u001b[0m \u001b[38;5;124;03mArgs:\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 691\u001b[0m \u001b[38;5;124;03m Action specifying what tool to use.\u001b[39;00m\n\u001b[1;32m 692\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 693\u001b[0m full_inputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mget_full_inputs(intermediate_steps, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m--> 694\u001b[0m full_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mllm_chain\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpredict\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mfull_inputs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 695\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_parser\u001b[38;5;241m.\u001b[39mparse(full_output)\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain/chains/llm.py:293\u001b[0m, in \u001b[0;36mLLMChain.predict\u001b[0;34m(self, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m 278\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mpredict\u001b[39m(\u001b[38;5;28mself\u001b[39m, callbacks: Callbacks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28mstr\u001b[39m:\n\u001b[1;32m 279\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Format prompt with kwargs and pass to LLM.\u001b[39;00m\n\u001b[1;32m 280\u001b[0m \n\u001b[1;32m 281\u001b[0m \u001b[38;5;124;03m Args:\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 291\u001b[0m \u001b[38;5;124;03m completion = llm.predict(adjective=\"funny\")\u001b[39;00m\n\u001b[1;32m 292\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 293\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m)\u001b[49m[\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_key]\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain_core/_api/deprecation.py:145\u001b[0m, in \u001b[0;36mdeprecated..deprecate..warning_emitting_wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 143\u001b[0m warned \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m 144\u001b[0m emit_warning()\n\u001b[0;32m--> 145\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mwrapped\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain/chains/base.py:363\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks, tags, metadata, run_name, include_run_info)\u001b[0m\n\u001b[1;32m 331\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Execute the chain.\u001b[39;00m\n\u001b[1;32m 332\u001b[0m \n\u001b[1;32m 333\u001b[0m \u001b[38;5;124;03mArgs:\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 354\u001b[0m \u001b[38;5;124;03m `Chain.output_keys`.\u001b[39;00m\n\u001b[1;32m 355\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 356\u001b[0m config \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m 357\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcallbacks\u001b[39m\u001b[38;5;124m\"\u001b[39m: callbacks,\n\u001b[1;32m 358\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtags\u001b[39m\u001b[38;5;124m\"\u001b[39m: tags,\n\u001b[1;32m 359\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmetadata\u001b[39m\u001b[38;5;124m\"\u001b[39m: metadata,\n\u001b[1;32m 360\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_name\u001b[39m\u001b[38;5;124m\"\u001b[39m: run_name,\n\u001b[1;32m 361\u001b[0m }\n\u001b[0;32m--> 363\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 364\u001b[0m \u001b[43m \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 365\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast\u001b[49m\u001b[43m(\u001b[49m\u001b[43mRunnableConfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m{\u001b[49m\u001b[43mk\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mk\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mitems\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mis\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m}\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 366\u001b[0m \u001b[43m \u001b[49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 367\u001b[0m \u001b[43m \u001b[49m\u001b[43minclude_run_info\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minclude_run_info\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 368\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain/chains/base.py:162\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m 160\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 161\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n\u001b[0;32m--> 162\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m 163\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_end(outputs)\n\u001b[1;32m 164\u001b[0m final_outputs: Dict[\u001b[38;5;28mstr\u001b[39m, Any] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprep_outputs(\n\u001b[1;32m 165\u001b[0m inputs, outputs, return_only_outputs\n\u001b[1;32m 166\u001b[0m )\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain/chains/base.py:156\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m 149\u001b[0m run_manager \u001b[38;5;241m=\u001b[39m callback_manager\u001b[38;5;241m.\u001b[39mon_chain_start(\n\u001b[1;32m 150\u001b[0m dumpd(\u001b[38;5;28mself\u001b[39m),\n\u001b[1;32m 151\u001b[0m inputs,\n\u001b[1;32m 152\u001b[0m name\u001b[38;5;241m=\u001b[39mrun_name,\n\u001b[1;32m 153\u001b[0m )\n\u001b[1;32m 154\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 155\u001b[0m outputs \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m--> 156\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 157\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported\n\u001b[1;32m 158\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call(inputs)\n\u001b[1;32m 159\u001b[0m )\n\u001b[1;32m 160\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 161\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain/chains/llm.py:103\u001b[0m, in \u001b[0;36mLLMChain._call\u001b[0;34m(self, inputs, run_manager)\u001b[0m\n\u001b[1;32m 98\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_call\u001b[39m(\n\u001b[1;32m 99\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 100\u001b[0m inputs: Dict[\u001b[38;5;28mstr\u001b[39m, Any],\n\u001b[1;32m 101\u001b[0m run_manager: Optional[CallbackManagerForChainRun] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m 102\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Dict[\u001b[38;5;28mstr\u001b[39m, \u001b[38;5;28mstr\u001b[39m]:\n\u001b[0;32m--> 103\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[43m[\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 104\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcreate_outputs(response)[\u001b[38;5;241m0\u001b[39m]\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain/chains/llm.py:115\u001b[0m, in \u001b[0;36mLLMChain.generate\u001b[0;34m(self, input_list, run_manager)\u001b[0m\n\u001b[1;32m 113\u001b[0m callbacks \u001b[38;5;241m=\u001b[39m run_manager\u001b[38;5;241m.\u001b[39mget_child() \u001b[38;5;28;01mif\u001b[39;00m run_manager \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 114\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm, BaseLanguageModel):\n\u001b[0;32m--> 115\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mllm\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate_prompt\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 116\u001b[0m \u001b[43m \u001b[49m\u001b[43mprompts\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 117\u001b[0m \u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 118\u001b[0m \u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 119\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mllm_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 120\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 121\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 122\u001b[0m results \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm\u001b[38;5;241m.\u001b[39mbind(stop\u001b[38;5;241m=\u001b[39mstop, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm_kwargs)\u001b[38;5;241m.\u001b[39mbatch(\n\u001b[1;32m 123\u001b[0m cast(List, prompts), {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcallbacks\u001b[39m\u001b[38;5;124m\"\u001b[39m: callbacks}\n\u001b[1;32m 124\u001b[0m )\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain_core/language_models/llms.py:530\u001b[0m, in \u001b[0;36mBaseLLM.generate_prompt\u001b[0;34m(self, prompts, stop, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m 522\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mgenerate_prompt\u001b[39m(\n\u001b[1;32m 523\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 524\u001b[0m prompts: List[PromptValue],\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 527\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m 528\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m LLMResult:\n\u001b[1;32m 529\u001b[0m prompt_strings \u001b[38;5;241m=\u001b[39m [p\u001b[38;5;241m.\u001b[39mto_string() \u001b[38;5;28;01mfor\u001b[39;00m p \u001b[38;5;129;01min\u001b[39;00m prompts]\n\u001b[0;32m--> 530\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[43mprompt_strings\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain_core/language_models/llms.py:703\u001b[0m, in \u001b[0;36mBaseLLM.generate\u001b[0;34m(self, prompts, stop, callbacks, tags, metadata, run_name, **kwargs)\u001b[0m\n\u001b[1;32m 687\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 688\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mAsked to cache, but no cache found at `langchain.cache`.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 689\u001b[0m )\n\u001b[1;32m 690\u001b[0m run_managers \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m 691\u001b[0m callback_manager\u001b[38;5;241m.\u001b[39mon_llm_start(\n\u001b[1;32m 692\u001b[0m dumpd(\u001b[38;5;28mself\u001b[39m),\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 701\u001b[0m )\n\u001b[1;32m 702\u001b[0m ]\n\u001b[0;32m--> 703\u001b[0m output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_generate_helper\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 704\u001b[0m \u001b[43m \u001b[49m\u001b[43mprompts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_managers\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mbool\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mnew_arg_supported\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\n\u001b[1;32m 705\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 706\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m output\n\u001b[1;32m 707\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(missing_prompts) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m:\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain_core/language_models/llms.py:567\u001b[0m, in \u001b[0;36mBaseLLM._generate_helper\u001b[0;34m(self, prompts, stop, run_managers, new_arg_supported, **kwargs)\u001b[0m\n\u001b[1;32m 565\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m run_manager \u001b[38;5;129;01min\u001b[39;00m run_managers:\n\u001b[1;32m 566\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_llm_error(e, response\u001b[38;5;241m=\u001b[39mLLMResult(generations\u001b[38;5;241m=\u001b[39m[]))\n\u001b[0;32m--> 567\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m 568\u001b[0m flattened_outputs \u001b[38;5;241m=\u001b[39m output\u001b[38;5;241m.\u001b[39mflatten()\n\u001b[1;32m 569\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m manager, flattened_output \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mzip\u001b[39m(run_managers, flattened_outputs):\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain_core/language_models/llms.py:554\u001b[0m, in \u001b[0;36mBaseLLM._generate_helper\u001b[0;34m(self, prompts, stop, run_managers, new_arg_supported, **kwargs)\u001b[0m\n\u001b[1;32m 544\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_generate_helper\u001b[39m(\n\u001b[1;32m 545\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 546\u001b[0m prompts: List[\u001b[38;5;28mstr\u001b[39m],\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 550\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m 551\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m LLMResult:\n\u001b[1;32m 552\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 553\u001b[0m output \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m--> 554\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_generate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 555\u001b[0m \u001b[43m \u001b[49m\u001b[43mprompts\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 556\u001b[0m \u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 557\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# TODO: support multiple run managers\u001b[39;49;00m\n\u001b[1;32m 558\u001b[0m \u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_managers\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mrun_managers\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 559\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 560\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 561\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported\n\u001b[1;32m 562\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_generate(prompts, stop\u001b[38;5;241m=\u001b[39mstop)\n\u001b[1;32m 563\u001b[0m )\n\u001b[1;32m 564\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 565\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m run_manager \u001b[38;5;129;01min\u001b[39;00m run_managers:\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain_community/llms/openai.py:460\u001b[0m, in \u001b[0;36mBaseOpenAI._generate\u001b[0;34m(self, prompts, stop, run_manager, **kwargs)\u001b[0m\n\u001b[1;32m 448\u001b[0m choices\u001b[38;5;241m.\u001b[39mappend(\n\u001b[1;32m 449\u001b[0m {\n\u001b[1;32m 450\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtext\u001b[39m\u001b[38;5;124m\"\u001b[39m: generation\u001b[38;5;241m.\u001b[39mtext,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 457\u001b[0m }\n\u001b[1;32m 458\u001b[0m )\n\u001b[1;32m 459\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 460\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[43mcompletion_with_retry\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 461\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mprompt\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m_prompts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mparams\u001b[49m\n\u001b[1;32m 462\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 463\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(response, \u001b[38;5;28mdict\u001b[39m):\n\u001b[1;32m 464\u001b[0m \u001b[38;5;66;03m# V1 client returns the response in an PyDantic object instead of\u001b[39;00m\n\u001b[1;32m 465\u001b[0m \u001b[38;5;66;03m# dict. For the transition period, we deep convert it to dict.\u001b[39;00m\n\u001b[1;32m 466\u001b[0m response \u001b[38;5;241m=\u001b[39m response\u001b[38;5;241m.\u001b[39mdict()\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/langchain_community/llms/openai.py:115\u001b[0m, in \u001b[0;36mcompletion_with_retry\u001b[0;34m(llm, run_manager, **kwargs)\u001b[0m\n\u001b[1;32m 113\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Use tenacity to retry the completion call.\"\"\"\u001b[39;00m\n\u001b[1;32m 114\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_openai_v1():\n\u001b[0;32m--> 115\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mllm\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mclient\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcreate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 117\u001b[0m retry_decorator \u001b[38;5;241m=\u001b[39m _create_retry_decorator(llm, run_manager\u001b[38;5;241m=\u001b[39mrun_manager)\n\u001b[1;32m 119\u001b[0m \u001b[38;5;129m@retry_decorator\u001b[39m\n\u001b[1;32m 120\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_completion_with_retry\u001b[39m(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Any:\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/openai/_utils/_utils.py:271\u001b[0m, in \u001b[0;36mrequired_args..inner..wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 269\u001b[0m msg \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mMissing required argument: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mquote(missing[\u001b[38;5;241m0\u001b[39m])\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 270\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(msg)\n\u001b[0;32m--> 271\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/openai/resources/completions.py:506\u001b[0m, in \u001b[0;36mCompletions.create\u001b[0;34m(self, model, prompt, best_of, echo, frequency_penalty, logit_bias, logprobs, max_tokens, n, presence_penalty, seed, stop, stream, suffix, temperature, top_p, user, extra_headers, extra_query, extra_body, timeout)\u001b[0m\n\u001b[1;32m 478\u001b[0m \u001b[38;5;129m@required_args\u001b[39m([\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodel\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mprompt\u001b[39m\u001b[38;5;124m\"\u001b[39m], [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodel\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mprompt\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstream\u001b[39m\u001b[38;5;124m\"\u001b[39m])\n\u001b[1;32m 479\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcreate\u001b[39m(\n\u001b[1;32m 480\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 504\u001b[0m timeout: \u001b[38;5;28mfloat\u001b[39m \u001b[38;5;241m|\u001b[39m httpx\u001b[38;5;241m.\u001b[39mTimeout \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m|\u001b[39m NotGiven \u001b[38;5;241m=\u001b[39m NOT_GIVEN,\n\u001b[1;32m 505\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Completion \u001b[38;5;241m|\u001b[39m Stream[Completion]:\n\u001b[0;32m--> 506\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_post\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 507\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/completions\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 508\u001b[0m \u001b[43m \u001b[49m\u001b[43mbody\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmaybe_transform\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 509\u001b[0m \u001b[43m \u001b[49m\u001b[43m{\u001b[49m\n\u001b[1;32m 510\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmodel\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 511\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mprompt\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mprompt\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 512\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mbest_of\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mbest_of\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 513\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mecho\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mecho\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 514\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfrequency_penalty\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfrequency_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 515\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mlogit_bias\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogit_bias\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 516\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mlogprobs\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogprobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 517\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmax_tokens\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 518\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mn\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mn\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 519\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mpresence_penalty\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mpresence_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 520\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mseed\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mseed\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 521\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstop\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 522\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstream\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 523\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msuffix\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43msuffix\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 524\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtemperature\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtemperature\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 525\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtop_p\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtop_p\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 526\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43muser\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43muser\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 527\u001b[0m \u001b[43m \u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 528\u001b[0m \u001b[43m \u001b[49m\u001b[43mcompletion_create_params\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mCompletionCreateParams\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 529\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 530\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmake_request_options\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 531\u001b[0m \u001b[43m \u001b[49m\u001b[43mextra_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_headers\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_query\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_query\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_body\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_body\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\n\u001b[1;32m 532\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 533\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mCompletion\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 534\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 535\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mStream\u001b[49m\u001b[43m[\u001b[49m\u001b[43mCompletion\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 536\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/openai/_base_client.py:1180\u001b[0m, in \u001b[0;36mSyncAPIClient.post\u001b[0;34m(self, path, cast_to, body, options, files, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1166\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mpost\u001b[39m(\n\u001b[1;32m 1167\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 1168\u001b[0m path: \u001b[38;5;28mstr\u001b[39m,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1175\u001b[0m stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m 1176\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ResponseT \u001b[38;5;241m|\u001b[39m _StreamT:\n\u001b[1;32m 1177\u001b[0m opts \u001b[38;5;241m=\u001b[39m FinalRequestOptions\u001b[38;5;241m.\u001b[39mconstruct(\n\u001b[1;32m 1178\u001b[0m method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpost\u001b[39m\u001b[38;5;124m\"\u001b[39m, url\u001b[38;5;241m=\u001b[39mpath, json_data\u001b[38;5;241m=\u001b[39mbody, files\u001b[38;5;241m=\u001b[39mto_httpx_files(files), \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39moptions\n\u001b[1;32m 1179\u001b[0m )\n\u001b[0;32m-> 1180\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m cast(ResponseT, \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mopts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m)\u001b[49m)\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/openai/_base_client.py:869\u001b[0m, in \u001b[0;36mSyncAPIClient.request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m 860\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mrequest\u001b[39m(\n\u001b[1;32m 861\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 862\u001b[0m cast_to: Type[ResponseT],\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 867\u001b[0m stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m 868\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ResponseT \u001b[38;5;241m|\u001b[39m _StreamT:\n\u001b[0;32m--> 869\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 870\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 871\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 872\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 873\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 874\u001b[0m \u001b[43m \u001b[49m\u001b[43mremaining_retries\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mremaining_retries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 875\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/venv020124/lib/python3.11/site-packages/openai/_base_client.py:960\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m 957\u001b[0m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mread()\n\u001b[1;32m 959\u001b[0m log\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRe-raising status error\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 960\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_make_status_error_from_response(err\u001b[38;5;241m.\u001b[39mresponse) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 962\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_process_response(\n\u001b[1;32m 963\u001b[0m cast_to\u001b[38;5;241m=\u001b[39mcast_to,\n\u001b[1;32m 964\u001b[0m options\u001b[38;5;241m=\u001b[39moptions,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 967\u001b[0m stream_cls\u001b[38;5;241m=\u001b[39mstream_cls,\n\u001b[1;32m 968\u001b[0m )\n", "\u001b[0;31mBadRequestError\u001b[0m: Error code: 400 - {'error': {'message': \"This model's maximum context length is 4097 tokens, however you requested 4979 tokens (4723 in your prompt; 256 for the completion). Please reduce your prompt; or completion length.\", 'type': 'invalid_request_error', 'param': None, 'code': None}}" ] } ], "source": [ "agent.run(\"What is this article about? Describe it in less than 100 words.\")" ] }, { "cell_type": "code", "execution_count": null, "id": "a16a3845-4867-4411-919e-cdda06365fe8", "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": "3.11.4" } }, "nbformat": 4, "nbformat_minor": 5 }