langchain/docs/docs/integrations/llms/bittensor.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Bittensor\n",
    "\n",
    ">[Bittensor](https://bittensor.com/) is a mining network, similar to Bitcoin, that includes built-in incentives designed to encourage miners to contribute compute + knowledge.\n",
    ">\n",
    ">`NIBittensorLLM` is developed by [Neural Internet](https://neuralinternet.ai/), powered by `Bittensor`.\n",
    "\n",
    ">This LLM showcases true potential of decentralized AI by giving you the best response(s) from the `Bittensor protocol`, which consist of various AI models such as `OpenAI`, `LLaMA2` etc.\n",
    "\n",
    "Users can view their logs, requests, and API keys on the [Validator Endpoint Frontend](https://api.neuralinternet.ai/). However, changes to the configuration are currently prohibited; otherwise, the user's queries will be blocked.\n",
    "\n",
    "If you encounter any difficulties or have any questions, please feel free to reach out to our developer on [GitHub](https://github.com/Kunj-2206), [Discord](https://discordapp.com/users/683542109248159777) or join our discord server for latest update and queries [Neural Internet](https://discord.gg/neuralinternet).\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Different Parameter and response handling for NIBittensorLLM "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "from pprint import pprint\n",
    "\n",
    "from langchain.globals import set_debug\n",
    "from langchain_community.llms import NIBittensorLLM\n",
    "\n",
    "set_debug(True)\n",
    "\n",
    "# System parameter in NIBittensorLLM is optional but you can set whatever you want to perform with model\n",
    "llm_sys = NIBittensorLLM(\n",
    "    system_prompt=\"Your task is to determine response based on user prompt.Explain me like I am technical lead of a project\"\n",
    ")\n",
    "sys_resp = llm_sys(\n",
    "    \"What is bittensor and What are the potential benefits of decentralized AI?\"\n",
    ")\n",
    "print(f\"Response provided by LLM with system prompt set is : {sys_resp}\")\n",
    "\n",
    "# The top_responses parameter can give multiple responses based on its parameter value\n",
    "# This below code retrive top 10 miner's response all the response are in format of json\n",
    "\n",
    "# Json response structure is\n",
    "\"\"\" {\n",
    "    \"choices\":  [\n",
    "                    {\"index\": Bittensor's Metagraph index number,\n",
    "                    \"uid\": Unique Identifier of a miner,\n",
    "                    \"responder_hotkey\": Hotkey of a miner,\n",
    "                    \"message\":{\"role\":\"assistant\",\"content\": Contains actual response},\n",
    "                    \"response_ms\": Time in millisecond required to fetch response from a miner} \n",
    "                ]\n",
    "    } \"\"\"\n",
    "\n",
    "multi_response_llm = NIBittensorLLM(top_responses=10)\n",
    "multi_resp = multi_response_llm.invoke(\"What is Neural Network Feeding Mechanism?\")\n",
    "json_multi_resp = json.loads(multi_resp)\n",
    "pprint(json_multi_resp)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##  Using NIBittensorLLM with LLMChain and PromptTemplate"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.chains import LLMChain\n",
    "from langchain.globals import set_debug\n",
    "from langchain_community.llms import NIBittensorLLM\n",
    "from langchain_core.prompts import PromptTemplate\n",
    "\n",
    "set_debug(True)\n",
    "\n",
    "template = \"\"\"Question: {question}\n",
    "\n",
    "Answer: Let's think step by step.\"\"\"\n",
    "\n",
    "\n",
    "prompt = PromptTemplate.from_template(template)\n",
    "\n",
    "# System parameter in NIBittensorLLM is optional but you can set whatever you want to perform with model\n",
    "llm = NIBittensorLLM(\n",
    "    system_prompt=\"Your task is to determine response based on user prompt.\"\n",
    ")\n",
    "\n",
    "llm_chain = LLMChain(prompt=prompt, llm=llm)\n",
    "question = \"What is bittensor?\"\n",
    "\n",
    "llm_chain.run(question)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##  Using NIBittensorLLM with Conversational Agent and Google Search Tool"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_community.utilities import GoogleSearchAPIWrapper\n",
    "from langchain_core.tools import Tool\n",
    "\n",
    "search = GoogleSearchAPIWrapper()\n",
    "\n",
    "tool = Tool(\n",
    "    name=\"Google Search\",\n",
    "    description=\"Search Google for recent results.\",\n",
    "    func=search.run,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain import hub\n",
    "from langchain.agents import (\n",
    "    AgentExecutor,\n",
    "    create_react_agent,\n",
    ")\n",
    "from langchain.memory import ConversationBufferMemory\n",
    "from langchain_community.llms import NIBittensorLLM\n",
    "\n",
    "tools = [tool]\n",
    "\n",
    "prompt = hub.pull(\"hwchase17/react\")\n",
    "\n",
    "\n",
    "llm = NIBittensorLLM(\n",
    "    system_prompt=\"Your task is to determine a response based on user prompt\"\n",
    ")\n",
    "\n",
    "memory = ConversationBufferMemory(memory_key=\"chat_history\")\n",
    "\n",
    "agent = create_react_agent(llm, tools, prompt)\n",
    "agent_executor = AgentExecutor(agent=agent, tools=tools, memory=memory)\n",
    "\n",
    "response = agent_executor.invoke({\"input\": prompt})"
   ]
  }
 ],
 "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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}