Hello, I&#39;ve been creating various things in this series, although I&#39;m not sure how many times. This time, I&#39;m trying something that includes programming code. Learning to program quantum computers is challenging, isn&#39;t it? I&#39;d like to make the LLM remember all about it, but it might not remember everything, so I&#39;ll use references. This time, I&#39;ve used CSV. <pre class="ql-syntax" spellcheck="false">pip install --quiet transformers accelerate langchain langchain-community sentence-transformers faiss-gpu pypdf gradio
</pre> <pre class="ql-syntax" spellcheck="false">from transformers import AutoTokenizer, pipeline

model_id = &#34;mistralai/Mistral-7B-Instruct-v0.2&#34;
tokenizer = AutoTokenizer.from_pretrained(model_id)

pipe = pipeline(&#34;text-generation&#34;, model=model_id, tokenizer=tokenizer, device=0, max_new_tokens=300)
</pre> I used the Mistral7B model. The data is read using pandas from a CSV file. This time, the file &#39;list2.csv&#39; contains various explanations and codes. <pre class="ql-syntax" spellcheck="false">from langchain_community.document_loaders import DataFrameLoader
from langchain_community.vectorstores import FAISS
from langchain_community.embeddings.huggingface import HuggingFaceEmbeddings
from langchain_text_splitters import CharacterTextSplitter
import pandas as pd

df = pd.read_csv(&#34;list2.csv&#34;)
loader = DataFrameLoader(df)

documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

embeddings = HuggingFaceEmbeddings(
 model_name=&#34;intfloat/multilingual-e5-large&#34;
)

db = FAISS.from_documents(docs, embeddings)
retriever = db.as_retriever()
print(db.index.ntotal)
</pre> <pre class="ql-syntax" spellcheck="false">from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
from langchain.llms import HuggingFacePipeline

llm = HuggingFacePipeline(pipeline=pipe)

template = &#34;&#34;&#34;あなたは量子コンピュータプログラミングの先生です。次のコンテクストに含まれる説明とコードを参照して質問に答えてください:

{context}

Question: {question}
&#34;&#34;&#34;

prompt = ChatPromptTemplate.from_template(template)

chain = (
 {&#34;context&#34;: retriever, &#34;question&#34;: RunnablePassthrough()}
 | prompt
 | llm
 | StrOutputParser()
)
</pre> This area is familiar. I passed the LLM built with a pipeline to RAG. I specified the prompt carefully in Japanese. And finally, Gradio. <pre class="ql-syntax" spellcheck="false">import gradio as gr
import os

def add_text(history, text):
 history = history + [(text, None)]
 return history, gr.Textbox(value=&#34;&#34;, interactive=False)

def bot(history):
 query = history[-1][0]
 response = chain.invoke(query)  
 if &#34;Answer:&#34; in response:
  response = response.split(&#34;Answer:&#34;)[1]
 if &#34;Question:&#34; in response:
  response = response.split(&#34;Question:&#34;)[0]
 history[-1][1] = &#34;&#34;
 for character in response:
  history[-1][1] += character
  yield history

with gr.Blocks() as demo:
 chatbot = gr.Chatbot([])
 with gr.Row():
  txt = gr.Textbox(
   scale=4,
   show_label = False,
   container = False
  )
 clear = gr.Button(&#34;Clear&#34;) 

 txt_msg = txt.submit(add_text, [chatbot, txt], [chatbot, txt], queue = False).then(bot, chatbot, chatbot)
 txt_msg.then(lambda: gr.Textbox(interactive = True), None, [txt], queue = False)
 clear.click(lambda: None, None, chatbot, queue=False)

demo.queue()  
demo.launch(share=True)
</pre> You can do it by just reusing the minimal configuration in various ways. It works like this through the interface.Moreover, it properly presents the code and explains what&#39;s inside the code as well. <img src="https://assets.blueqat.com/public/uploads/us-east-2:4805ff4b-c3cc-4344-b165-86544c34d0bf/2024/04/13/Gradio.png"/> <img src="https://assets.blueqat.com/public/uploads/us-east-2:4805ff4b-c3cc-4344-b165-86544c34d0bf/2024/04/13/Gradio3.png"/>

Create an AI that teaches quantum computer programming with RAG

Yuichiro Minato