11  Vector Store and Retriver (Basic)

From: vector store and retriver

from langchain_core.documents import Document

11.1 Documents

documents = [
    Document(
        page_content="Dogs are great companions, known for their loyalty and friendliness.",
        metadata={"source": "mammal-pets-doc"},
    ),
    Document(
        page_content="Cats are independent pets that often enjoy their own space.",
        metadata={"source": "mammal-pets-doc"},
    ),
    Document(
        page_content="Goldfish are popular pets for beginners, requiring relatively simple care.",
        metadata={"source": "fish-pets-doc"},
    ),
    Document(
        page_content="Parrots are intelligent birds capable of mimicking human speech.",
        metadata={"source": "bird-pets-doc"},
    ),
    Document(
        page_content="Rabbits are social animals that need plenty of space to hop around.",
        metadata={"source": "mammal-pets-doc"},
    ),
]

11.2 Vector Store

from langchain_chroma import Chroma
from langchain_openai import OpenAIEmbeddings

vectorstore = Chroma.from_documents(
    documents,
    embedding=OpenAIEmbeddings(),
)

type(vectorstore)

langchain_chroma.vectorstores.Chroma

11.2.1 Similarity Search

• Synchronously and asynchronously;
• By string query and by vector;
• With and without returning similarity scores;
• By similarity

vectorstore.similarity_search("cat")

[Document(page_content='Cats are independent pets that often enjoy their own space.', metadata={'source': 'mammal-pets-doc'}),
 Document(page_content='Dogs are great companions, known for their loyalty and friendliness.', metadata={'source': 'mammal-pets-doc'}),
 Document(page_content='Rabbits are social animals that need plenty of space to hop around.', metadata={'source': 'mammal-pets-doc'}),
 Document(page_content='Parrots are intelligent birds capable of mimicking human speech.', metadata={'source': 'bird-pets-doc'})]

Async

await vectorstore.asimilarity_search("cat")

[Document(page_content='Cats are independent pets that often enjoy their own space.', metadata={'source': 'mammal-pets-doc'}),
 Document(page_content='Dogs are great companions, known for their loyalty and friendliness.', metadata={'source': 'mammal-pets-doc'}),
 Document(page_content='Rabbits are social animals that need plenty of space to hop around.', metadata={'source': 'mammal-pets-doc'}),
 Document(page_content='Parrots are intelligent birds capable of mimicking human speech.', metadata={'source': 'bird-pets-doc'})]

Return scores:

# Note that providers implement different scores; Chroma here
# returns a distance metric that should vary inversely with
# similarity.

vectorstore.similarity_search_with_score("cat")

[(Document(page_content='Cats are independent pets that often enjoy their own space.', metadata={'source': 'mammal-pets-doc'}),
  0.37532728910446167),
 (Document(page_content='Dogs are great companions, known for their loyalty and friendliness.', metadata={'source': 'mammal-pets-doc'}),
  0.4833085536956787),
 (Document(page_content='Rabbits are social animals that need plenty of space to hop around.', metadata={'source': 'mammal-pets-doc'}),
  0.49588823318481445),
 (Document(page_content='Parrots are intelligent birds capable of mimicking human speech.', metadata={'source': 'bird-pets-doc'}),
  0.49741730093955994)]

Return documents based on similarity to a embedded query:

embedding = OpenAIEmbeddings().embed_query("cat")

vectorstore.similarity_search_by_vector(embedding)

[Document(page_content='Cats are independent pets that often enjoy their own space.', metadata={'source': 'mammal-pets-doc'}),
 Document(page_content='Dogs are great companions, known for their loyalty and friendliness.', metadata={'source': 'mammal-pets-doc'}),
 Document(page_content='Rabbits are social animals that need plenty of space to hop around.', metadata={'source': 'mammal-pets-doc'}),
 Document(page_content='Parrots are intelligent birds capable of mimicking human speech.', metadata={'source': 'bird-pets-doc'})]

11.3 Retrievers

from typing import List

from langchain_core.documents import Document
from langchain_core.runnables import RunnableLambda

retriever = RunnableLambda(vectorstore.similarity_search).bind(k=1)  # select top result

retriever.batch(["cat", "shark"])

[[Document(page_content='Cats are independent pets that often enjoy their own space.', metadata={'source': 'mammal-pets-doc'})],
 [Document(page_content='Goldfish are popular pets for beginners, requiring relatively simple care.', metadata={'source': 'fish-pets-doc'})]]

retriever = vectorstore.as_retriever(
    search_type="similarity",
    search_kwargs={"k": 1},
)

retriever.batch(["cat", "shark"])

[[Document(page_content='Cats are independent pets that often enjoy their own space.', metadata={'source': 'mammal-pets-doc'})],
 [Document(page_content='Goldfish are popular pets for beginners, requiring relatively simple care.', metadata={'source': 'fish-pets-doc'})]]

11.4 Full Example of Retriver

from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough

llm = ChatOpenAI(model="gpt-3.5-turbo-0125")

message = """
Answer this question using the provided context only.

{question}

Context:
{context}
"""

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

print(prompt.invoke({"question": "your question", 
                     "context": "your context",  
                     "message": "HI"}).to_string())

Human: 
Answer this question using the provided context only.

your question

Context:
your context

rag_chain = {"context": retriever, "question": RunnablePassthrough()} | prompt | llm

response = rag_chain.invoke("tell me about cats")

print(response.content)

Cats are independent pets that often enjoy their own space.

response2 = rag_chain.invoke("What's special about cats?")
print(response2.content)

Cats are special because they are independent pets that often enjoy their own space.