LlamaIndex vs LangChain comparison

import os
from llama_index import SimpleDirectoryReader, GPTVectorStoreIndex

# Load documents from a directory
documents = SimpleDirectoryReader('docs').load_data()

# Build vector index
index = GPTVectorStoreIndex.from_documents(documents)

# Query the index
query = "What are the main benefits of AI?"
response = index.query(query)
print(response.response)

import os
from langchain_openai import ChatOpenAI
from langchain_community.vectorstores import FAISS
from langchain_community.document_loaders import TextLoader
from langchain.chains import RetrievalQA
from langchain_openai import OpenAIEmbeddings

# Load documents
loader = TextLoader('docs/sample.txt')
docs = loader.load()

# Create embeddings and FAISS vector store
embeddings = OpenAIEmbeddings()
vectorstore = FAISS.from_documents(docs, embeddings)

# Setup LLM and retrieval QA chain
llm = ChatOpenAI(model='gpt-4o', api_key=os.environ['OPENAI_API_KEY'])
qa = RetrievalQA.from_chain_type(llm=llm, retriever=vectorstore.as_retriever())

# Query
query = "What are the main benefits of AI?"
answer = qa.run(query)
print(answer)