Archiviazione e recupero RAG con database vettoriali

Sviluppare applicazioni LLM con LangChain

Jonathan Bennion

AI Engineer & LangChain Contributor

Fasi di sviluppo RAG

Il flusso RAG generale: loader, splitter, e processo di archiviazione/recupero.

Focus di questo video: archiviazione e recupero

Cos’è un database vettoriale e perché serve?

Un tipico workflow RAG.

Quale database vettoriale usare?

Il panorama dei vari database vettoriali, divisi per open/closed source e per dedicati vs. con supporto.

Da considerare:

Open source vs. closed source (licenza)
Cloud vs. on-premise
Leggero vs. potente

¹ Crediti immagine: Yingjun Wu

Conosci i documenti...

docs

[
    Document(
        page_content="In all marketing copy, TechStack should always be written with the T and S
        capitalized. Incorrect: techstack, Techstack, etc.",
        metadata={"guideline": "brand-capitalization"}
    ),
    Document(
        page_content="Our users should be referred to as techies in both internal and external
        communications.",
        metadata={"guideline": "referring-to-users"}
    )
]

Configurare un database vettoriale Chroma

from langchain_openai import OpenAIEmbeddings
from langchain_chroma import Chroma

embedding_function = OpenAIEmbeddings(api_key=openai_api_key, model='text-embedding-3-small')


vectorstore = Chroma.from_documents(
    docs,
    embedding=embedding_function,
    persist_directory="path/to/directory"
)


retriever = vectorstore.as_retriever(
    search_type="similarity",
    search_kwargs={"k": 2}
)

Creare un prompt template

from langchain_core.prompts import ChatPromptTemplate

message = """
Review and fix the following TechStack marketing copy with the following guidelines in consideration:

Guidelines:
{guidelines}

Copy:
{copy}

Fixed Copy:
"""

prompt_template = ChatPromptTemplate.from_messages([("human", message)])

Collegare tutto insieme!

from langchain_core.runnables import RunnablePassthrough

rag_chain = ({"guidelines": retriever, "copy": RunnablePassthrough()}
             | prompt_template
             | llm)


response = rag_chain.invoke("Here at techstack, our users are the best in the world!")

print(response.content)

Here at TechStack, our techies are the best in the world!

Ayo berlatih!

Sviluppare applicazioni LLM con LangChain