RAG from Scratch

!pip install -q sentence-transformers
!pip install -q wikipedia-api
!pip install -q numpy
!pip install -q scipy

from sentence_transformers import SentenceTransformer
model = SentenceTransformer("Alibaba-NLP/gte-base-en-v1.5", trust_remote_code=True)

from wikipediaapi import Wikipedia
wiki = Wikipedia('RAGBot/0.0', 'en')
doc = wiki.page('Hayao_Miyazaki').text
paragraphs = doc.split('\n\n') # chunking

import textwrap

for i, p in enumerate(paragraphs):
  wrapped_text = textwrap.fill(p, width=100)

  print("-----------------------------------------------------------------")
  print(wrapped_text)
  print("-----------------------------------------------------------------")

docs_embed = model.encode(paragraphs, normalize_embeddings=True)

docs_embed.shape

docs_embed[0]

query = "What was Studio Ghibli's first film?"
query_embed = model.encode(query, normalize_embeddings=True)

query_embed.shape

import numpy as np
similarities = np.dot(docs_embed, query_embed.T)

similarities.shape

similarities

top_3_idx = np.argsort(similarities, axis=0)[-3:][::-1].tolist()

top_3_idx

most_similar_documents = [paragraphs[idx] for idx in top_3_idx]

CONTEXT = ""
for i, p in enumerate(most_similar_documents):
  wrapped_text = textwrap.fill(p, width=100)

  print("-----------------------------------------------------------------")
  print(wrapped_text)
  print("-----------------------------------------------------------------")
  CONTEXT += wrapped_text + "\n\n"

query = "What was Studio Ghibli's first film?"

prompt = f"""
use the following CONTEXT to answer the QUESTION at the end.
If you don't know the answer, just say that you don't know, don't try to make up an answer.

CONTEXT: {CONTEXT}
QUESTION: {query}

"""

!pip install -q openai

# prompt: write python code to make calls to openai api
from google.colab import userdata
userdata.get('openai')

import openai

from openai import OpenAI
client = OpenAI(api_key=userdata.get('openai'))

response = client.chat.completions.create(
  model="gpt-4o",
  messages=[
    {"role": "user", "content": prompt},
  ]
)

print(response.choices[0].message.content)