LangChain

from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_chroma import Chroma
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
 
llm = ChatOpenAI(model="gpt-4o-mini")
retriever = Chroma(embedding_function=OpenAIEmbeddings()).as_retriever()

"""langchain.py - Cadeia RAG com LCEL."""
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_chroma import Chroma
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_text_splitters import RecursiveCharacterTextSplitter
 
docs = ["pytest executa testes com fixtures.", "FastAPI usa Pydantic para validação."]
splits = RecursiveCharacterTextSplitter(chunk_size=200).split_text("\n".join(docs))
vectorstore = Chroma.from_texts(splits, OpenAIEmbeddings())
retriever = vectorstore.as_retriever(search_kwargs={"k": 2})
 
prompt = ChatPromptTemplate.from_template(
    "Responda apenas com base no contexto:\n{context}\n\nPergunta: {question}"
)
 
def format_docs(docs):
    return "\n---\n".join(d.page_content for d in docs)
 
chain = (
    {"context": retriever | format_docs, "question": RunnablePassthrough()}
    | prompt
    | ChatOpenAI(model="gpt-4o-mini", temperature=0)
    | StrOutputParser()
)
 
print(chain.invoke("Como o pytest funciona?"))