Retrieval-Augmented Generation with LangChain
Heads up... You’re accessing parts of this content for free, with some sections shown as text.
Heads up... You’re accessing parts of this content for free, with some sections shown as text.
Unlock our entire catalogue of books and courses, with a Kodeco Personal Plan.
Unlock now
In this demo, we’ll implement a hybrid search using sparse vector embedding algorithms from LangChain. Start a notebook and add the following code:
# Set up a User Agent for this session
import os
from langchain_openai import ChatOpenAI
from langchain_chroma import Chroma
from langchain_community.document_loaders import WikipediaLoader
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter
os.environ['USER_AGENT'] = 'sports-buddy-advanced'
llm = ChatOpenAI(model="gpt-4o-mini")
loader = WikipediaLoader("2024_Summer_Olympics",)
docs = loader.load()
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000,
chunk_overlap=0)
splits = text_splitter.split_documents(docs)
database = Chroma.from_documents(documents=splits,
embedding=OpenAIEmbeddings())
retriever = database.as_retriever()
from langchain.retrievers import BM25Retriever, EnsembleRetriever
keyword_retriever = BM25Retriever.from_documents(splits)
keyword_retriever.k = 3
ensemble_retriever = EnsembleRetriever(retrievers=[retriever,
keyword_retriever], weights=[0.3, 0.7])
from langchain.chains import RetrievalQA
dense_chain = RetrievalQA.from_chain_type(
llm=llm, chain_type="stuff", retriever=retriever
)
sparse_chain = RetrievalQA.from_chain_type(
llm=llm, chain_type="stuff", retriever=ensemble_retriever
)
normal_response = normal_chain.invoke("What happened at the opening
ceremony of the 2024 Summer Olympics")
print(normal_response['result'])
Athletes were paraded by boat along the Seine River in Paris.
sparse_response = sparse_chain.invoke("What happened at the
opening ceremony of the 2024 Summer Olympics")
print(hybrid_response['result'])
Olympic history.
Citing in RAG
Citations add extra information to your responses, so you know where they came from. Open a new notebook to learn how to add citations to SportsBuddy. In the notebook, start with the following code:
from langchain_community.retrievers import WikipediaRetriever
from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI
import os
llm = ChatOpenAI(model="gpt-4o-mini")
system_prompt = (
"You're a helpful AI assistant. Given a user question "
"and some Wikipedia article snippets, answer the user "
"question. If none of the articles answer the question, "
"just say you don't know."
"\n\nHere are the Wikipedia articles: "
"{context}"
)
retriever = WikipediaRetriever(top_k_results=6, doc_content_chars_max=2000)
prompt = ChatPromptTemplate.from_messages(
[
("system", system_prompt),
("human", "{input}"),
]
)
from typing import List
from langchain_core.documents import Document
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
def format_docs(docs: List[Document]):
return "\n\n".join(doc.page_content for doc in docs)
rag_chain = (
RunnablePassthrough.assign(context=(lambda x: format_docs(x["context"])))
| prompt
| llm
| StrOutputParser()
)
retrieve_docs = (lambda x: x["input"]) | retriever
chain = RunnablePassthrough.assign(context=retrieve_docs).assign(
answer=rag_chain
)
result = chain.invoke({"input": "How did the USA fair at the 2024
Summer Olympics"})
print(result.keys())
dict_keys(['input', 'context', 'answer'])
from typing import List
from langchain_core.pydantic_v1 import BaseModel, Field
class CitedAnswer(BaseModel):
"""Answer the user question based only on the given sources, and cite
the sources used."""
answer: str = Field(
...,
description="The answer to the user question, which is based only on
the given sources.",
)
citations: List[int] = Field(
...,
description="The integer IDs of the SPECIFIC sources which justify
the answer.",
)
structured_llm = llm.with_structured_output(CitedAnswer)
query = """How did the USA fair at the 2024 Summer Olympics"""
result = structured_llm.invoke(query)
result
citations: List[str] = Field(
...,
description="The string URLs of the SPECIFIC sources which justify
the answer.",
)
class Citation(BaseModel):
source_id: int = Field(
...,
description="The integer ID of a SPECIFIC source which
justifies the answer.",
)
quote: str = Field(
...,
description="The VERBATIM quote from the specified source that
justifies the answer.",
)
class QuotedAnswer(BaseModel):
"""Answer the user question based only on the given sources, and
cite the sources used."""
answer: str = Field(
...,
description="The answer to the user question, which is based
only on the given sources.",
)
citations: List[Citation] = Field(
..., description="Citations from the given sources that
justify the answer."
)
rag_chain = (
RunnablePassthrough.assign(context=(lambda x:
format_docs_with_id(x["context"])))
| prompt
| llm.with_structured_output(QuotedAnswer)
)
retrieve_docs = (lambda x: x["input"]) | retriever
chain = RunnablePassthrough.assign(context=retrieve_docs).assign(
answer=rag_chain
)
chain.invoke({"input": "How did the USA fair at the 2024 Summer
Olympics"})