Pinecone ve OpenAI ile RAG sohbet botu

Pinecone ile Vektör Veritabanları ve Embeddings

James Chapman

Curriculum Manager, DataCamp

Getirme Destekli Üretim (RAG)

Kullanıcı sorgusunu göm
Benzer belgeleri getir
Belgeleri isteme ekle

getirme destekli üretim

Pinecone ve OpenAI’yi başlatma

from openai import OpenAI
from pinecone import Pinecone
import pandas as pd
from uuid import uuid4


client = OpenAI(api_key="OPENAI_API_KEY")
pc = Pinecone(api_key="PINECONE_API_KEY")


index = pc.Index("semantic-search-datacamp")

YouTube dökümleri

youtube_df = pd.read_csv('youtube_rag_data.csv')

| id | blob | channel_id | end | published | start | text | title | url |
|----|------|------------|-----|-----------|-------|------|-------|-----|
|int | dict | str        | int | datetime  | int   | str  | str   | str |

Belgeleri içe aktarma

batch_limit = 100


for batch in np.array_split(youtube_df, len(youtube_df) / batch_limit):

    metadatas = [{"text_id": row['id'], "text": row['text'],
      "title": row['title'], "url": row['url'], 
      "published": row['published']} for  _, row in batch.iterrows()]

    texts = batch['text'].tolist()

    ids = [str(uuid4()) for _ in range(len(texts))]


    response = client.embeddings.create(input=texts, model="text-embedding-3-small")
    embeds = [np.array(x.embedding) for x in response.data]


    index.upsert(vectors=zip(ids, embeds, metadatas), namespace='youtube_rag_dataset')

Getirme işlevi

def retrieve(query, top_k, namespace, emb_model):

    query_response = client.embeddings.create(input=query, model=emb_model)
    query_emb = query_response.data[0].embedding


    retrieved_docs = []
    sources = []
    docs = index.query(vector=query_emb, top_k=top_k,
                       namespace='youtube_rag_dataset', include_metadata=True)


    for doc in docs['matches']:
        retrieved_docs.append(doc['metadata']['text'])
        sources.append((doc['metadata']['title'], doc['metadata']['url']))

    return retrieved_docs, sources

Getirme çıktısı

query = "How to build next-level Q&A with OpenAI"
documents, sources = retrieve(query, top_k=3, namespace='youtube_rag_dataset',
                              emb_model="text-embedding-3-small")

Document: Genel Alan Soru-Cevap için kullanmak üzere. Başlayacağız...
Source: How to build a Q&A AI in Python [...], https://youtu.be/w1dMEWm7jBc

Document: Burada Google var ve Google'a sorular sorabiliriz...
Source: How to build next-level Q&A with OpenAI, https://youtu.be/coaaSxys5so

Document: Soru-cevap sistemlerinin kalitesini artırmak için vektör veritabanına ihtiyacımız var...
Source: How to Build Custom Q&A Transfo [...], https://youtu.be/ZIRmXKHp0-c

Bağlamlı istem oluşturucu işlevi

def prompt_with_context_builder(query, docs):
    delim = '\n\n---\n\n'
    prompt_start = 'Answer the question based on the context below.\n\nContext:\n'
    prompt_end = f'\n\nQuestion: {query}\nAnswer:'

    prompt = prompt_start + delim.join(docs) + prompt_end
    return prompt

Bağlamlı istem çıktısı

query = "How to build next-level Q&A with OpenAI"
context_prompt = prompt_with_context_builder(query, documents)

prompt_with_context_builder işlevinin çıktısı

Soru-cevap işlevi

def question_answering(prompt, sources, chat_model):

    sys_prompt = "You are a helpful assistant that always answers questions."

    res = client.chat.completions.create(
        model=chat_model,
        messages=[{"role": "system", "content": sys_prompt},
            {"role": "user", "content": prompt}
        ], temperature=0)

    answer = res.choices[0].message.content.strip()
    answer += "\n\nSources:"
    for source in sources:
        answer += "\n" + source[0] + ": " + source[1]
    return answer

Soru-cevap çıktısı

query = "How to build next-level Q&A with OpenAI"
answer = question_answering(prompt_with_context, sources,
                            chat_model='gpt-4o-mini')

question_answering işlevinin çıktısı

Hepsini bir araya getirme

query = "How to build next-level Q&A with OpenAI"
documents, sources = retrieve(query, top_k=3, 
                              namespace='youtube_rag_dataset', 
                              emb_model="text-embedding-3-small")
prompt_with_context = prompt_with_context_builder(query, documents)
answer = question_answering(prompt_with_context, sources,
                            chat_model='gpt-4o-mini')

Hadi pratik yapalım!

Pinecone ile Vektör Veritabanları ve Embeddings