LLMA .ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "cca48e23-a978-4c56-90bc-2bf81f1d67f6",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import os\n",
    "os.environ[\"SERPAPI_API_KEY\"] = \"4d53b517f564e2e847929c2659391de40ae0caa3c021a77555ec75d6adba6547\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "0aca263e-9b87-44fd-8e06-ab7a59461b8e",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: langchain in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (0.0.146)\n",
      "Collecting langchain\n",
      "  Downloading langchain-0.0.147-py3-none-any.whl (626 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m626.5/626.5 kB\u001b[0m \u001b[31m1.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: PyYAML>=5.4.1 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from langchain) (6.0)\n",
      "Requirement already satisfied: SQLAlchemy<2,>=1 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from langchain) (1.4.47)\n",
      "Requirement already satisfied: aiohttp<4.0.0,>=3.8.3 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from langchain) (3.8.4)\n",
      "Requirement already satisfied: dataclasses-json<0.6.0,>=0.5.7 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from langchain) (0.5.7)\n",
      "Requirement already satisfied: numexpr<3.0.0,>=2.8.4 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from langchain) (2.8.4)\n",
      "Requirement already satisfied: numpy<2,>=1 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from langchain) (1.24.0)\n",
      "Requirement already satisfied: openapi-schema-pydantic<2.0,>=1.2 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from langchain) (1.2.4)\n",
      "Requirement already satisfied: pydantic<2,>=1 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from langchain) (1.10.7)\n",
      "Requirement already satisfied: requests<3,>=2 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from langchain) (2.28.2)\n",
      "Requirement already satisfied: tenacity<9.0.0,>=8.1.0 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from langchain) (8.2.2)\n",
      "Requirement already satisfied: tqdm>=4.48.0 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from langchain) (4.65.0)\n",
      "Requirement already satisfied: attrs>=17.3.0 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (23.1.0)\n",
      "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (3.1.0)\n",
      "Requirement already satisfied: multidict<7.0,>=4.5 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (6.0.4)\n",
      "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (4.0.2)\n",
      "Requirement already satisfied: yarl<2.0,>=1.0 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.8.2)\n",
      "Requirement already satisfied: frozenlist>=1.1.1 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.3.3)\n",
      "Requirement already satisfied: aiosignal>=1.1.2 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.3.1)\n",
      "Requirement already satisfied: marshmallow<4.0.0,>=3.3.0 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from dataclasses-json<0.6.0,>=0.5.7->langchain) (3.19.0)\n",
      "Requirement already satisfied: marshmallow-enum<2.0.0,>=1.5.1 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from dataclasses-json<0.6.0,>=0.5.7->langchain) (1.5.1)\n",
      "Requirement already satisfied: typing-inspect>=0.4.0 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from dataclasses-json<0.6.0,>=0.5.7->langchain) (0.8.0)\n",
      "Requirement already satisfied: typing-extensions>=4.2.0 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from pydantic<2,>=1->langchain) (4.5.0)\n",
      "Requirement already satisfied: idna<4,>=2.5 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from requests<3,>=2->langchain) (3.4)\n",
      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from requests<3,>=2->langchain) (1.26.15)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from requests<3,>=2->langchain) (2022.12.7)\n",
      "Requirement already satisfied: packaging>=17.0 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from marshmallow<4.0.0,>=3.3.0->dataclasses-json<0.6.0,>=0.5.7->langchain) (23.1)\n",
      "Requirement already satisfied: mypy-extensions>=0.3.0 in /Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages (from typing-inspect>=0.4.0->dataclasses-json<0.6.0,>=0.5.7->langchain) (1.0.0)\n",
      "Installing collected packages: langchain\n",
      "  Attempting uninstall: langchain\n",
      "    Found existing installation: langchain 0.0.146\n",
      "    Uninstalling langchain-0.0.146:\n",
      "      Successfully uninstalled langchain-0.0.146\n",
      "Successfully installed langchain-0.0.147\n"
     ]
    }
   ],
   "source": [
    "!pip install --upgrade langchain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "b177e17a-358b-4b6b-bd68-3cfc90f7b987",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain.llms import LlamaCpp\n",
    "from langchain import PromptTemplate, LLMChain\n",
    "from langchain.agents import load_tools\n",
    "from langchain.agents import initialize_agent\n",
    "from langchain.agents import AgentType"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "a2943c38-7fe9-438f-903e-b3123cb3fc05",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "template = \"\"\"Question: {question}\n",
    "\n",
    "Answer: Let's think step by step.\"\"\"\n",
    "\n",
    "prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "34090fba-0334-4c7a-b0e4-3f46099694d6",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "llama.cpp: loading model from ./models/gpt4all-lora-quantized-ggml.bin\n",
      "llama.cpp: can't use mmap because tensors are not aligned; convert to new format to avoid this\n",
      "llama_model_load_internal: format     = ggmf v1 (old version with no mmap support)\n",
      "llama_model_load_internal: n_vocab    = 32001\n",
      "llama_model_load_internal: n_ctx      = 2048\n",
      "llama_model_load_internal: n_embd     = 4096\n",
      "llama_model_load_internal: n_mult     = 256\n",
      "llama_model_load_internal: n_head     = 32\n",
      "llama_model_load_internal: n_layer    = 32\n",
      "llama_model_load_internal: n_rot      = 128\n",
      "llama_model_load_internal: ftype      = 2 (mostly Q4_0)\n",
      "llama_model_load_internal: n_ff       = 11008\n",
      "llama_model_load_internal: n_parts    = 1\n",
      "llama_model_load_internal: model size = 7B\n",
      "llama_model_load_internal: ggml ctx size = 4113744.11 KB\n",
      "llama_model_load_internal: mem required  = 5809.33 MB (+ 2052.00 MB per state)\n",
      "...................................................................................................\n",
      ".\n",
      "llama_init_from_file: kv self size  = 2048.00 MB\n",
      "AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 0 | VSX = 0 | \n"
     ]
    }
   ],
   "source": [
    "llm = LlamaCpp(model_path=\"./models/gpt4all-lora-quantized-ggml.bin\",n_ctx=2048)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "761795b6-8d0d-433a-8598-deebf573190b",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "llama.cpp: loading model from ./models/gpt4all-lora-quantized-ggml.bin\n",
      "llama.cpp: can't use mmap because tensors are not aligned; convert to new format to avoid this\n",
      "llama_model_load_internal: format     = ggmf v1 (old version with no mmap support)\n",
      "llama_model_load_internal: n_vocab    = 32001\n",
      "llama_model_load_internal: n_ctx      = 1024\n",
      "llama_model_load_internal: n_embd     = 4096\n",
      "llama_model_load_internal: n_mult     = 256\n",
      "llama_model_load_internal: n_head     = 32\n",
      "llama_model_load_internal: n_layer    = 32\n",
      "llama_model_load_internal: n_rot      = 128\n",
      "llama_model_load_internal: ftype      = 2 (mostly Q4_0)\n",
      "llama_model_load_internal: n_ff       = 11008\n",
      "llama_model_load_internal: n_parts    = 1\n",
      "llama_model_load_internal: model size = 7B\n",
      "llama_model_load_internal: ggml ctx size = 4113744.11 KB\n",
      "llama_model_load_internal: mem required  = 5809.33 MB (+ 2052.00 MB per state)\n",
      "...................................................................................................\n",
      ".\n",
      "llama_init_from_file: kv self size  = 1024.00 MB\n",
      "AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 0 | VSX = 0 | \n"
     ]
    }
   ],
   "source": [
    "llm = LlamaCpp(model_path=\"./models/gpt4all-lora-quantized-ggml.bin\",n_ctx=1024)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "1a9bec3d-3969-4479-b939-0d64145e7e46",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "9aa39a0f-d7fd-4eac-9509-163fb49ea9e4",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "llama_print_timings:        load time =   808.40 ms\n",
      "llama_print_timings:      sample time =   102.92 ms /   116 runs   (    0.89 ms per run)\n",
      "llama_print_timings: prompt eval time =  1994.71 ms /    32 tokens (   62.33 ms per token)\n",
      "llama_print_timings:        eval time =  9985.44 ms /   115 runs   (   86.83 ms per run)\n",
      "llama_print_timings:       total time = 12091.50 ms\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\" Justin Bieber was born on March 1st, 1994. Therefore, he was already three months old when his team, the Cleveland Browns, played their final regular season game of the 1989 NFL season (November 5th). The Browns finished that season with a 2–14 record and were subsequently disbanded after the end of the 1996 season. Therefore, it is safe to say that Justin Bieber's team did not win any Super Bowl games in his lifetime.\""
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "question = \"What NFL team won the Super Bowl in the year Justin Bieber was born?\"\n",
    "\n",
    "llm_chain.run(question)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "b1e74a8c-fbd0-4c97-81a0-88e5daa13fdc",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "e7a0adc6-523a-4d77-9b7a-eba0c2187674",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "f0c759ef-bb33-4cfd-9e1a-15b3d261980b",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m It might be useful to search for information on Leo DiCaprio and his girlfriends, but I don't have time to do that right now.\n",
      "Action: Input \"Leo DiCaprio\" into Calculator.\n",
      "Action Input: Type in the number of characters in the word \"girlfriend\".\u001b[0m\n",
      "Observation: Input \"Leo DiCaprio\" into Calculator. is not a valid tool, try another one.\n",
      "Thought:"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "llama_print_timings:        load time =   808.40 ms\n",
      "llama_print_timings:      sample time =    62.62 ms /    70 runs   (    0.89 ms per run)\n",
      "llama_print_timings: prompt eval time = 10459.34 ms /   208 tokens (   50.29 ms per token)\n",
      "llama_print_timings:        eval time =  6744.52 ms /    69 runs   (   97.75 ms per run)\n",
      "llama_print_timings:       total time = 17271.75 ms\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32;1m\u001b[1;3m The current age of Leo's girlfriend is not readily available to calculate.\n",
      "Action: Search for information on Leo DiCaprio and his girlfriends. \n",
      "Action Input: Type in the keywords \"Leo DiCaprio girlfriend\" into search engine.\u001b[0m\n",
      "Observation: Search for information on Leo DiCaprio and his girlfriends. is not a valid tool, try another one.\n",
      "Thought:"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "llama_print_timings:        load time =   808.40 ms\n",
      "llama_print_timings:      sample time =    53.99 ms /    60 runs   (    0.90 ms per run)\n",
      "llama_print_timings: prompt eval time = 16175.07 ms /   304 tokens (   53.21 ms per token)\n",
      "llama_print_timings:        eval time =  6007.38 ms /    59 runs   (  101.82 ms per run)\n",
      "llama_print_timings:       total time = 22241.18 ms\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32;1m\u001b[1;3m I will need to input the number of characters in the word \"girlfriend\" again. \n",
      "Action: Input \"Leo DiCaprio\" into Calculator.\n",
      "Action Input: Type in the number of characters in the word \"girlfriend\".\u001b[0m\n",
      "Observation: Input \"Leo DiCaprio\" into Calculator. is not a valid tool, try another one.\n",
      "Thought:"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "llama_print_timings:        load time =   808.40 ms\n",
      "llama_print_timings:      sample time =    51.95 ms /    58 runs   (    0.90 ms per run)\n",
      "llama_print_timings: prompt eval time = 22263.47 ms /   392 tokens (   56.79 ms per token)\n",
      "llama_print_timings:        eval time =  5948.99 ms /    57 runs   (  104.37 ms per run)\n",
      "llama_print_timings:       total time = 28269.15 ms\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32;1m\u001b[1;3m I will need to search for more information on Leo DiCaprio and his girlfriends. \n",
      "Action: Search for information on Leo DiCaprio and his girlfriends. \n",
      "Action Input: Type in the keywords \"Leo DiCaprio girlfriend\" into search engine.\u001b[0m\n",
      "Observation: Search for information on Leo DiCaprio and his girlfriends. is not a valid tool, try another one.\n",
      "Thought:"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "llama_print_timings:        load time =   808.40 ms\n",
      "llama_print_timings:      sample time =    57.46 ms /    64 runs   (    0.90 ms per run)\n",
      "llama_print_timings: prompt eval time = 27879.77 ms /   476 tokens (   58.57 ms per token)\n",
      "llama_print_timings:        eval time =  6732.76 ms /    63 runs   (  106.87 ms per run)\n",
      "llama_print_timings:       total time = 34675.69 ms\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32;1m\u001b[1;3m I will need to input the number of characters in the word \"girlfriend\" again. \n",
      "Action: Input \"Leo DiCaprio\" into Calculator.\n",
      "Action Input: Type in the number of characters in the word \"girlfriend\".\u001b[0m\n",
      "Observation: Input \"Leo DiCaprio\" into Calculator. is not a valid tool, try another one.\n",
      "Thought:"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "llama_print_timings:        load time =   808.40 ms\n",
      "llama_print_timings:      sample time =    51.97 ms /    58 runs   (    0.90 ms per run)\n",
      "llama_print_timings: prompt eval time = 32334.38 ms /   568 tokens (   56.93 ms per token)\n",
      "llama_print_timings:        eval time =  6238.66 ms /    57 runs   (  109.45 ms per run)\n",
      "llama_print_timings:       total time = 38630.42 ms\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32;1m\u001b[1;3m I will need to search for more information on Leo DiCaprio and his girlfriends. \n",
      "Action: Search for information on Leo DiCaprio and his girlfriends. \n",
      "Action Input: Type in the keywords \"Leo DiCaprio girlfriend\" into search engine.\u001b[0m\n",
      "Observation: Search for information on Leo DiCaprio and his girlfriends. is not a valid tool, try another one.\n",
      "Thought:"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "llama_print_timings:        load time =   808.40 ms\n",
      "llama_print_timings:      sample time =    57.87 ms /    64 runs   (    0.90 ms per run)\n",
      "llama_print_timings: prompt eval time = 37222.29 ms /   652 tokens (   57.09 ms per token)\n",
      "llama_print_timings:        eval time =  7402.18 ms /    63 runs   (  117.49 ms per run)\n",
      "llama_print_timings:       total time = 44688.82 ms\n",
      "\n",
      "llama_print_timings:        load time =   808.40 ms\n",
      "llama_print_timings:      sample time =    51.86 ms /    58 runs   (    0.89 ms per run)\n",
      "llama_print_timings: prompt eval time = 42971.93 ms /   744 tokens (   57.76 ms per token)\n",
      "llama_print_timings:        eval time =  6549.40 ms /    57 runs   (  114.90 ms per run)\n",
      "llama_print_timings:       total time = 49579.37 ms\n",
      "Exception ignored in: <function Llama.__del__ at 0x10bbc85e0>\n",
      "Traceback (most recent call last):\n",
      "  File \"/Users/friendsoncode/jupyterlab_env/lib/python3.11/site-packages/llama_cpp/llama.py\", line 804, in __del__\n",
      "    if self.ctx is not None:\n",
      "       ^^^^^^^^\n",
      "AttributeError: 'Llama' object has no attribute 'ctx'\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32;1m\u001b[1;3m I will need to input the number of characters in the word \"girlfriend\" again. \n",
      "Action: Input \"Leo DiCaprio\" into Calculator.\n",
      "Action Input: Type in the number of characters in the word \"girlfriend\".\u001b[0m\n",
      "Observation: Input \"Leo DiCaprio\" into Calculator. is not a valid tool, try another one.\n",
      "Thought:"
     ]
    },
    {
     "ename": "ValueError",
     "evalue": "Requested tokens exceed context window of 1024",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[19], 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;43mWho is Leo DiCaprio\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43ms girlfriend? What is her current age raised to the 0.43 power?\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/langchain/chains/base.py:213\u001b[0m, in \u001b[0;36mChain.run\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m    211\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    212\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--> 213\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[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_keys[\u001b[38;5;241m0\u001b[39m]]\n\u001b[1;32m    215\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    216\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m(kwargs)[\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_keys[\u001b[38;5;241m0\u001b[39m]]\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/langchain/chains/base.py:116\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs)\u001b[0m\n\u001b[1;32m    114\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mKeyboardInterrupt\u001b[39;00m, \u001b[38;5;167;01mException\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    115\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcallback_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e, verbose\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose)\n\u001b[0;32m--> 116\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    117\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcallback_manager\u001b[38;5;241m.\u001b[39mon_chain_end(outputs, verbose\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose)\n\u001b[1;32m    118\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprep_outputs(inputs, outputs, return_only_outputs)\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/langchain/chains/base.py:113\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs)\u001b[0m\n\u001b[1;32m    107\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcallback_manager\u001b[38;5;241m.\u001b[39mon_chain_start(\n\u001b[1;32m    108\u001b[0m     {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mname\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m},\n\u001b[1;32m    109\u001b[0m     inputs,\n\u001b[1;32m    110\u001b[0m     verbose\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose,\n\u001b[1;32m    111\u001b[0m )\n\u001b[1;32m    112\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 113\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m \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\n\u001b[1;32m    114\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mKeyboardInterrupt\u001b[39;00m, \u001b[38;5;167;01mException\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    115\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcallback_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e, verbose\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose)\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/langchain/agents/agent.py:792\u001b[0m, in \u001b[0;36mAgentExecutor._call\u001b[0;34m(self, inputs)\u001b[0m\n\u001b[1;32m    790\u001b[0m \u001b[38;5;66;03m# We now enter the agent loop (until it returns something).\u001b[39;00m\n\u001b[1;32m    791\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--> 792\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    793\u001b[0m \u001b[43m        \u001b[49m\u001b[43mname_to_tool_map\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcolor_mapping\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mintermediate_steps\u001b[49m\n\u001b[1;32m    794\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    795\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(next_step_output, AgentFinish):\n\u001b[1;32m    796\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_return(next_step_output, intermediate_steps)\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/langchain/agents/agent.py:672\u001b[0m, in \u001b[0;36mAgentExecutor._take_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps)\u001b[0m\n\u001b[1;32m    667\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Take a single step in the thought-action-observation loop.\u001b[39;00m\n\u001b[1;32m    668\u001b[0m \n\u001b[1;32m    669\u001b[0m \u001b[38;5;124;03mOverride this to take control of how the agent makes and acts on choices.\u001b[39;00m\n\u001b[1;32m    670\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    671\u001b[0m \u001b[38;5;66;03m# Call the LLM to see what to do.\u001b[39;00m\n\u001b[0;32m--> 672\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\u001b[43mintermediate_steps\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[43minputs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    673\u001b[0m \u001b[38;5;66;03m# If the tool chosen is the finishing tool, then we end and return.\u001b[39;00m\n\u001b[1;32m    674\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(output, AgentFinish):\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/langchain/agents/agent.py:384\u001b[0m, in \u001b[0;36mAgent.plan\u001b[0;34m(self, intermediate_steps, **kwargs)\u001b[0m\n\u001b[1;32m    373\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    374\u001b[0m \n\u001b[1;32m    375\u001b[0m \u001b[38;5;124;03mArgs:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    381\u001b[0m \u001b[38;5;124;03m    Action specifying what tool to use.\u001b[39;00m\n\u001b[1;32m    382\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    383\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--> 384\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[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    385\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~/jupyterlab_env/lib/python3.11/site-packages/langchain/chains/llm.py:151\u001b[0m, in \u001b[0;36mLLMChain.predict\u001b[0;34m(self, **kwargs)\u001b[0m\n\u001b[1;32m    137\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mpredict\u001b[39m(\u001b[38;5;28mself\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 \u001b[38;5;28mstr\u001b[39m:\n\u001b[1;32m    138\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    139\u001b[0m \n\u001b[1;32m    140\u001b[0m \u001b[38;5;124;03m    Args:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    149\u001b[0m \u001b[38;5;124;03m            completion = llm.predict(adjective=\"funny\")\u001b[39;00m\n\u001b[1;32m    150\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[0;32m--> 151\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[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_key]\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/langchain/chains/base.py:116\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs)\u001b[0m\n\u001b[1;32m    114\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mKeyboardInterrupt\u001b[39;00m, \u001b[38;5;167;01mException\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    115\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcallback_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e, verbose\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose)\n\u001b[0;32m--> 116\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    117\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcallback_manager\u001b[38;5;241m.\u001b[39mon_chain_end(outputs, verbose\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose)\n\u001b[1;32m    118\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprep_outputs(inputs, outputs, return_only_outputs)\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/langchain/chains/base.py:113\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs)\u001b[0m\n\u001b[1;32m    107\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcallback_manager\u001b[38;5;241m.\u001b[39mon_chain_start(\n\u001b[1;32m    108\u001b[0m     {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mname\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m},\n\u001b[1;32m    109\u001b[0m     inputs,\n\u001b[1;32m    110\u001b[0m     verbose\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose,\n\u001b[1;32m    111\u001b[0m )\n\u001b[1;32m    112\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 113\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m \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\n\u001b[1;32m    114\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mKeyboardInterrupt\u001b[39;00m, \u001b[38;5;167;01mException\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    115\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcallback_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e, verbose\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose)\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/langchain/chains/llm.py:57\u001b[0m, in \u001b[0;36mLLMChain._call\u001b[0;34m(self, inputs)\u001b[0m\n\u001b[1;32m     56\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_call\u001b[39m(\u001b[38;5;28mself\u001b[39m, inputs: Dict[\u001b[38;5;28mstr\u001b[39m, Any]) \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---> 57\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[43mapply\u001b[49m\u001b[43m(\u001b[49m\u001b[43m[\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m[\u001b[38;5;241m0\u001b[39m]\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/langchain/chains/llm.py:118\u001b[0m, in \u001b[0;36mLLMChain.apply\u001b[0;34m(self, input_list)\u001b[0m\n\u001b[1;32m    116\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mapply\u001b[39m(\u001b[38;5;28mself\u001b[39m, input_list: List[Dict[\u001b[38;5;28mstr\u001b[39m, Any]]) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m List[Dict[\u001b[38;5;28mstr\u001b[39m, \u001b[38;5;28mstr\u001b[39m]]:\n\u001b[1;32m    117\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"Utilize the LLM generate method for speed gains.\"\"\"\u001b[39;00m\n\u001b[0;32m--> 118\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[43minput_list\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    119\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcreate_outputs(response)\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/langchain/chains/llm.py:62\u001b[0m, in \u001b[0;36mLLMChain.generate\u001b[0;34m(self, input_list)\u001b[0m\n\u001b[1;32m     60\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Generate LLM result from inputs.\"\"\"\u001b[39;00m\n\u001b[1;32m     61\u001b[0m prompts, stop \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprep_prompts(input_list)\n\u001b[0;32m---> 62\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\u001b[43mprompts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/langchain/llms/base.py:107\u001b[0m, in \u001b[0;36mBaseLLM.generate_prompt\u001b[0;34m(self, prompts, stop)\u001b[0m\n\u001b[1;32m    103\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mgenerate_prompt\u001b[39m(\n\u001b[1;32m    104\u001b[0m     \u001b[38;5;28mself\u001b[39m, prompts: List[PromptValue], stop: Optional[List[\u001b[38;5;28mstr\u001b[39m]] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m    105\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m LLMResult:\n\u001b[1;32m    106\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--> 107\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\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/langchain/llms/base.py:140\u001b[0m, in \u001b[0;36mBaseLLM.generate\u001b[0;34m(self, prompts, stop)\u001b[0m\n\u001b[1;32m    138\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mKeyboardInterrupt\u001b[39;00m, \u001b[38;5;167;01mException\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    139\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcallback_manager\u001b[38;5;241m.\u001b[39mon_llm_error(e, verbose\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose)\n\u001b[0;32m--> 140\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    141\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcallback_manager\u001b[38;5;241m.\u001b[39mon_llm_end(output, verbose\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose)\n\u001b[1;32m    142\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m output\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/langchain/llms/base.py:137\u001b[0m, in \u001b[0;36mBaseLLM.generate\u001b[0;34m(self, prompts, stop)\u001b[0m\n\u001b[1;32m    133\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcallback_manager\u001b[38;5;241m.\u001b[39mon_llm_start(\n\u001b[1;32m    134\u001b[0m     {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mname\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m}, prompts, verbose\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose\n\u001b[1;32m    135\u001b[0m )\n\u001b[1;32m    136\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 137\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\u001b[49m\u001b[43m(\u001b[49m\u001b[43mprompts\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\n\u001b[1;32m    138\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mKeyboardInterrupt\u001b[39;00m, \u001b[38;5;167;01mException\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    139\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcallback_manager\u001b[38;5;241m.\u001b[39mon_llm_error(e, verbose\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose)\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/langchain/llms/base.py:324\u001b[0m, in \u001b[0;36mLLM._generate\u001b[0;34m(self, prompts, stop)\u001b[0m\n\u001b[1;32m    322\u001b[0m generations \u001b[38;5;241m=\u001b[39m []\n\u001b[1;32m    323\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m prompt \u001b[38;5;129;01min\u001b[39;00m prompts:\n\u001b[0;32m--> 324\u001b[0m     text \u001b[38;5;241m=\u001b[39m \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[43mprompt\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\n\u001b[1;32m    325\u001b[0m     generations\u001b[38;5;241m.\u001b[39mappend([Generation(text\u001b[38;5;241m=\u001b[39mtext)])\n\u001b[1;32m    326\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m LLMResult(generations\u001b[38;5;241m=\u001b[39mgenerations)\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/langchain/llms/llamacpp.py:186\u001b[0m, in \u001b[0;36mLlamaCpp._call\u001b[0;34m(self, prompt, stop)\u001b[0m\n\u001b[1;32m    183\u001b[0m     params[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstop_sequences\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m []\n\u001b[1;32m    185\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Call the Llama model and return the output.\"\"\"\u001b[39;00m\n\u001b[0;32m--> 186\u001b[0m text \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mclient\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    187\u001b[0m \u001b[43m    \u001b[49m\u001b[43mprompt\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mprompt\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    188\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmax_tokens\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparams\u001b[49m\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\n\u001b[1;32m    189\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtemperature\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparams\u001b[49m\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\n\u001b[1;32m    190\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtop_p\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparams\u001b[49m\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\n\u001b[1;32m    191\u001b[0m \u001b[43m    \u001b[49m\u001b[43mlogprobs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparams\u001b[49m\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\n\u001b[1;32m    192\u001b[0m \u001b[43m    \u001b[49m\u001b[43mecho\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparams\u001b[49m\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\n\u001b[1;32m    193\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparams\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstop_sequences\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    194\u001b[0m \u001b[43m    \u001b[49m\u001b[43mrepeat_penalty\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparams\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrepeat_penalty\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    195\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtop_k\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparams\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtop_k\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    196\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    197\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m text[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mchoices\u001b[39m\u001b[38;5;124m\"\u001b[39m][\u001b[38;5;241m0\u001b[39m][\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtext\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/llama_cpp/llama.py:681\u001b[0m, in \u001b[0;36mLlama.__call__\u001b[0;34m(self, prompt, suffix, max_tokens, temperature, top_p, logprobs, echo, stop, repeat_penalty, top_k, stream)\u001b[0m\n\u001b[1;32m    645\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__call__\u001b[39m(\n\u001b[1;32m    646\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    647\u001b[0m     prompt: \u001b[38;5;28mstr\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    657\u001b[0m     stream: \u001b[38;5;28mbool\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[1;32m    658\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Union[Completion, Iterator[CompletionChunk]]:\n\u001b[1;32m    659\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"Generate text from a prompt.\u001b[39;00m\n\u001b[1;32m    660\u001b[0m \n\u001b[1;32m    661\u001b[0m \u001b[38;5;124;03m    Args:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    679\u001b[0m \u001b[38;5;124;03m        Response object containing the generated text.\u001b[39;00m\n\u001b[1;32m    680\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[0;32m--> 681\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[43mcreate_completion\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    682\u001b[0m \u001b[43m        \u001b[49m\u001b[43mprompt\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mprompt\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    683\u001b[0m \u001b[43m        \u001b[49m\u001b[43msuffix\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msuffix\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    684\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmax_tokens\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmax_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    685\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtemperature\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtemperature\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    686\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtop_p\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtop_p\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    687\u001b[0m \u001b[43m        \u001b[49m\u001b[43mlogprobs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlogprobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    688\u001b[0m \u001b[43m        \u001b[49m\u001b[43mecho\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mecho\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    689\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    690\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrepeat_penalty\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepeat_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    691\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtop_k\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtop_k\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    692\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    693\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/llama_cpp/llama.py:642\u001b[0m, in \u001b[0;36mLlama.create_completion\u001b[0;34m(self, prompt, suffix, max_tokens, temperature, top_p, logprobs, echo, stop, repeat_penalty, top_k, stream)\u001b[0m\n\u001b[1;32m    640\u001b[0m     chunks: Iterator[CompletionChunk] \u001b[38;5;241m=\u001b[39m completion_or_chunks\n\u001b[1;32m    641\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m chunks\n\u001b[0;32m--> 642\u001b[0m completion: Completion \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mnext\u001b[39m(completion_or_chunks)  \u001b[38;5;66;03m# type: ignore\u001b[39;00m\n\u001b[1;32m    643\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m completion\n",
      "File \u001b[0;32m~/jupyterlab_env/lib/python3.11/site-packages/llama_cpp/llama.py:406\u001b[0m, in \u001b[0;36mLlama._create_completion\u001b[0;34m(self, prompt, suffix, max_tokens, temperature, top_p, logprobs, echo, stop, repeat_penalty, top_k, stream)\u001b[0m\n\u001b[1;32m    403\u001b[0m     llama_cpp\u001b[38;5;241m.\u001b[39mllama_reset_timings(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mctx)\n\u001b[1;32m    405\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(prompt_tokens) \u001b[38;5;241m+\u001b[39m max_tokens \u001b[38;5;241m>\u001b[39m \u001b[38;5;28mint\u001b[39m(llama_cpp\u001b[38;5;241m.\u001b[39mllama_n_ctx(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mctx)):\n\u001b[0;32m--> 406\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m    407\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRequested tokens exceed context window of \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mllama_cpp\u001b[38;5;241m.\u001b[39mllama_n_ctx(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mctx)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    408\u001b[0m     )\n\u001b[1;32m    410\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m stop \u001b[38;5;241m!=\u001b[39m []:\n\u001b[1;32m    411\u001b[0m     stop_sequences \u001b[38;5;241m=\u001b[39m [s\u001b[38;5;241m.\u001b[39mencode(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mutf-8\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01mfor\u001b[39;00m s \u001b[38;5;129;01min\u001b[39;00m stop]\n",
      "\u001b[0;31mValueError\u001b[0m: Requested tokens exceed context window of 1024"
     ]
    }
   ],
   "source": [
    "agent.run(\"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f68e8288-bdf6-4c33-863e-e3410532e3c5",
   "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": "3.11.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}