Skip to main content
Open In ColabOpen on GitHub

Bittensor

Bittensor 是一个类似比特币的挖矿网络，它内置了激励机制，旨在鼓励矿工贡献算力 + 知识。

NIBittensorLLM 由 Neural Internet 开发，基于 Bittensor 提供支持。

这个 LLM 通过提供来自 Bittensor协议 的最佳响应，展示了去中心化 AI 的真正潜力。该协议包含各种 AI 模型，如 OpenAI、LLaMA2 等。

用户可以在 Validator Endpoint Frontend 上查看他们的日志、请求和 API 密钥。但是，目前禁止更改配置，否则用户的查询将被阻止。

如果您遇到任何困难或有任何疑问，请随时通过 GitHub、Discord 联系我们的开发者，或加入我们的 discord 服务器以获取最新更新和查询 Neural Internet。

NIBittensorLLM 的不同参数和响应处理​

Multiple parameters​

Bittensor LLM (like NIBittensorLLM) can be

import json
from pprint import pprint

from langchain.globals import set_debug
from langchain_community.llms import NIBittensorLLM

set_debug(True)

# System parameter in NIBittensorLLM is optional but you can set whatever you want to perform with model
llm_sys = NIBittensorLLM(
    system_prompt="Your task is to determine response based on user prompt.Explain me like I am technical lead of a project"
)
sys_resp = llm_sys(
    "What is bittensor and What are the potential benefits of decentralized AI?"
)
print(f"Response provided by LLM with system prompt set is : {sys_resp}")

# The top_responses parameter can give multiple responses based on its parameter value
# This below code retrieve top 10 miner's response all the response are in format of json

# Json response structure is
""" {
    "choices":  [
                    {"index": Bittensor's Metagraph index number,
                    "uid": Unique Identifier of a miner,
                    "responder_hotkey": Hotkey of a miner,
                    "message":{"role":"assistant","content": Contains actual response},
                    "response_ms": Time in millisecond required to fetch response from a miner} 
                ]
    } """

multi_response_llm = NIBittensorLLM(top_responses=10)
multi_resp = multi_response_llm.invoke("What is Neural Network Feeding Mechanism?")
json_multi_resp = json.loads(multi_resp)
pprint(json_multi_resp)
API Reference:set_debug | NIBittensorLLM

将 NIBittensorLLM 与 LLMChain 和 PromptTemplate 结合使用​

from langchain.chains import LLMChain
from langchain.globals import set_debug
from langchain_community.llms import NIBittensorLLM
from langchain_core.prompts import PromptTemplate

set_debug(True)

template = """Question: {question}

Answer: Let's think step by step."""


prompt = PromptTemplate.from_template(template)

# System parameter in NIBittensorLLM is optional but you can set whatever you want to perform with model
llm = NIBittensorLLM(
    system_prompt="Your task is to determine response based on user prompt."
)

llm_chain = LLMChain(prompt=prompt, llm=llm)
question = "What is bittensor?"

llm_chain.run(question)

将 NIBittensorLLM 与对话代理和谷歌搜索工具结合使用​

from langchain_community.utilities import GoogleSearchAPIWrapper
from langchain_core.tools import Tool

search = GoogleSearchAPIWrapper()

tool = Tool(
    name="Google Search",
    description="Search Google for recent results.",
    func=search.run,
)
from langchain import hub
from langchain.agents import (
    AgentExecutor,
    create_react_agent,
)
from langchain.memory import ConversationBufferMemory
from langchain_community.llms import NIBittensorLLM

tools = [tool]

prompt = hub.pull("hwchase17/react")


llm = NIBittensorLLM(
    system_prompt="Your task is to determine a response based on user prompt"
)

memory = ConversationBufferMemory(memory_key="chat_history")

agent = create_react_agent(llm, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools, memory=memory)

response = agent_executor.invoke({"input": prompt})