idontcalculate

from llama_index.agent import FnRetrieverOpenAIAgent
from llama_index.llms import OpenAI

# Initialize the LLM
llm = OpenAI(model="gpt-3.5-turbo-0613")

# Initialize the FnRetrieverOpenAIAgent
top_agent = FnRetrieverOpenAIAgent.from_retriever(
   obj_index.as_retriever(similarity_top_k=4),
   system_prompt=""" \

idontcalculate

# Create vector_index instance
vector_index = VectorStoreIndex(nodes, service_context=service_context)

# Build the summary index
summary_index = SummaryIndex(nodes, service_context=service_context)

# Now you can safely define query engines since vector_index is defined
vector_query_engine = vector_index.as_query_engine()
summary_query_engine = summary_index.as_query_engine()

idontcalculate

from llama_index.agent import OpenAIAgent
from llama_index import load_index_from_storage, StorageContext
from llama_index.node_parser import SentenceSplitter

# Initialize the SentenceSplitter node parser
node_parser = SentenceSplitter()

#load documents and build vector index
for idx, patent_title in enumerate(patent_titles):
    file_path = os.path.join(patents_dir, f"{patent_title}.txt")

idontcalculate

query_engine_tools = [
    QueryEngineTool(
        query_engine=tesla_engine,
        metadata=ToolMetadata(
            name="tesla_tool",
            description=(
                "Provides information about Teslas predictions for future "
                "Use a detailed plain text question as input to the tool."
            ),
        ),

idontcalculate

import llama_index
from llama_index.tools import QueryEngineTool, ToolMetadata

from llama_index import (
    SimpleDirectoryReader,
    VectorStoreIndex,
    StorageContext,
    load_index_from_storage,
)
try:

idontcalculate

@bot.command()
async def dogsplain(ctx, *, question: str):
    print(f"User: {ctx.author.name}, Query: {question}")
    try:
        response = chat_bot.query(question)
        await send_response(ctx, response)
    except Exception as e:
        await send_response(ctx, "An error occurred. Please try again!")
        print("Error occurred during 'query' command:", e)

idontcalculate

answer = bench_bot.query('how to submit benchmarks?')
print(answer)

idontcalculate

#pdf data arxiv on bench
bench_bot.add('https://arxiv.org/pdf/2207.10062.pdf', data_type='pdf_file')

#notion page data
bench_bot.add('https://signalism.notion.site/MLCommons-An-In-Depth-Whitepaper-on-Benchmarking-Machine-Learning-Performance-d21aabe85304439fb5ae4ca7ac3826f7?pvs=4')

#docs
bench_bot.add('https://docs.google.com/spreadsheets/d/1bF4buOnEPQcwoqlaSeX4HxKx8jVRR0xHcOT_CaAL5Mk/pubhtml?gid=0&single=false&widget=false&headers=false&chrome=true', data_type="docs_site")

#github as page

idontcalculate

# takes the transcript and load it with yt_loader ;)
bench_bot.add('youtube_video', 'https://www.youtube.com/watch?v=uMNtTBRCHXA') 
bench_bot.add('youtube_video', 'https://www.youtube.com/watch?v=eyK-9UehYPo')
bench_bot.add('youtube_video', 'https://www.youtube.com/watch?v=woGaG3ZcTbU')
bench_bot.add('youtube_video', 'https://www.youtube.com/watch?v=woGaG3ZcTbU')
bench_bot.add('youtube_video', 'https://www.youtube.com/watch?v=txtvMhzEDu8')

idontcalculate

bench_bot.add('web_page', 'https://mlcommons.org/en/training-normal-30/')
bench_bot.add('web_page', 'https://mlcommons.org/en/training-hpc-20/')
bench_bot.add('web_page', 'https://mlcommons.org/en/inference-datacenter-30/')
bench_bot.add('web_page', 'https://mlcommons.org/en/inference-tiny-11/')
bench_bot.add('web_page', 'https://mlcommons.org/en/groups/datasets/')