Langchain integrates FAISS
1. FAISS
Facebook AI Similarity Search (Faiss) is a library for efficient similarity search and dense vector clustering. It contains algorithms that can search vector sets of arbitrary size, even vector sets that may not fit in RAM. It also contains supporting code for evaluation and parameter tuning.
The Faiss documentation address is here .
This notebook shows how to use FAISSfunctions related to vector databases.
sample code,
# !pip install faiss
# OR
# !pip install faiss-cpu
import os
import getpass
os.environ["COHERE_API_KEY"] = getpass.getpass("Cohere API Key:")
# 如果需要在没有 AVX2 优化的情况下初始化 FAISS，请取消注释以下一行
# os.environ['FAISS_NO_AVX2'] = '1'
# from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.embeddings.cohere import CohereEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.document_loaders import TextLoader
output result,
from langchain.document_loaders import TextLoader
loader = TextLoader("./state_of_the_union_en.txt", encoding="utf-8")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)
# embeddings = OpenAIEmbeddings
embeddings = CohereEmbeddings()
sample code,
db = FAISS.from_documents(docs, embeddings)
query = "What did the president say about Ketanji Brown Jackson"
docs = db.similarity_search(query)
print(docs[0].page_content)
output result,
Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections.
Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service.
One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.
And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.
2. Similarity Search with score
There are some FAISS specific methods. One of them is that similarity_search_with_scoreit allows you to return not only documents, but the distance score of the query to them. The distance score returned is the L2 distance. Therefore, the lower the score, the better.
sample code,
docs_and_scores = db.similarity_search_with_score(query)
docs_and_scores[0]
output result,
(Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', metadata={'source': './state_of_the_union_en.txt'}),
7172.888)
refer: https://python.langchain.com/docs/integrations/vectorstores/faiss The score of the documentation is 0.36913747,
(Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', metadata={'source': '../../../state_of_the_union.txt'}),
0.36913747)
It is also possible to similarity_search_by_vectorsearch for documents similar to a given embedding vector using , which accepts an embedding vector as an argument instead of a string.
sample code,
embedding_vector = embeddings.embed_query(query)
docs_and_scores = db.similarity_search_by_vector(embedding_vector)
docs_and_scores
The output is as follows,
[Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', metadata={'source': './state_of_the_union_en.txt'}),
Document(page_content='We can’t change how divided we’ve been. But we can change how we move forward—on COVID-19 and other issues we must face together. \n\nI recently visited the New York City Police Department days after the funerals of Officer Wilbert Mora and his partner, Officer Jason Rivera. \n\nThey were responding to a 9-1-1 call when a man shot and killed them with a stolen gun. \n\nOfficer Mora was 27 years old. \n\nOfficer Rivera was 22. \n\nBoth Dominican Americans who’d grown up on the same streets they later chose to patrol as police officers. \n\nI spoke with their families and told them that we are forever in debt for their sacrifice, and we will carry on their mission to restore the trust and safety every community deserves. \n\nI’ve worked on these issues a long time. \n\nI know what works: Investing in crime preventionand community police officers who’ll walk the beat, who’ll know the neighborhood, and who can restore trust and safety.', metadata={'source': './state_of_the_union_en.txt'}),
Document(page_content='And for our LGBTQ+ Americans, let’s finally get the bipartisan Equality Act to my desk. The onslaught of state laws targeting transgender Americans and their families is wrong. \n\nAs I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. \n\nWhile it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice. \n\nAnd soon, we’ll strengthen the Violence Against Women Act that I first wrote three decades ago. It is important for us to show the nation that we can come together and do big things. \n\nSo tonight I’m offering a Unity Agenda for the Nation. Four big things we can do together. \n\nFirst, beat the opioid epidemic.', metadata={'source': './state_of_the_union_en.txt'}),
Document(page_content='Tonight, I’m announcing a crackdown on these companies overcharging American businesses and consumers. \n\nAnd as Wall Street firms take over more nursing homes, quality in those homes has gone down and costs have gone up. \n\nThat ends on my watch. \n\nMedicare is going to set higher standards for nursing homes and make sure your loved ones get the care they deserve and expect. \n\nWe’ll also cut costs and keep the economy going strong by giving workers a fair shot, provide more training and apprenticeships, hire them based on their skills not degrees. \n\nLet’s pass the Paycheck Fairness Act and paid leave. \n\nRaise the minimum wage to $15 an hour and extend the Child Tax Credit, so no one has to raise a family in poverty. \n\nLet’s increase Pell Grants and increase our historic support of HBCUs, and invest in what Jill—our First Lady who teaches full-time—calls America’s best-kept secret: community colleges.', metadata={'source': './state_of_the_union_en.txt'})]
3. Saving and loading
You can also save and load FAISS indexes. This is useful so you don't have to recreate it every time you use it.
sample code,
db.save_local("faiss_index")
new_db = FAISS.load_local("faiss_index", embeddings)
docs = new_db.similarity_search(query)
docs[0]
output result,
Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', metadata={'source': './state_of_the_union_en.txt'})
4. Merging
You can also merge two FAISS vector stores.
sample code,
db1 = FAISS.from_texts(["foo"], embeddings)
db2 = FAISS.from_texts(["bar"], embeddings)
db1.docstore._dict
output result,
{'43f79c6d-6bb3-4a62-979d-58e011dcb086': Document(page_content='foo', metadata={})}
sample code,
db1.docstore._dict
output result,
{'43f79c6d-6bb3-4a62-979d-58e011dcb086': Document(page_content='foo', metadata={})}
sample code,
db2.docstore._dict
output result,
{'8dcb4556-8eb5-43be-9eaa-0bff9a6e7997': Document(page_content='bar', metadata={})}
sample code,
db1.docstore._dict
output result,
{'43f79c6d-6bb3-4a62-979d-58e011dcb086': Document(page_content='foo', metadata={})}
sample code,
db1.merge_from(db2)
output result,
db1.docstore._dict
output result,
{'43f79c6d-6bb3-4a62-979d-58e011dcb086': Document(page_content='foo', metadata={}),
'8dcb4556-8eb5-43be-9eaa-0bff9a6e7997': Document(page_content='bar', metadata={})}
5. Similarity Search with filtering
FAISS vectorstore can also support filtering, since FAISS itself does not support filtering, we have to do it manually. This is done by first fetching more than k results and then filtering them. You can filter documents based on metadata. You can also set the fetch_k parameter when calling any of the search methods to set the number of documents to fetch before filtering. Here's a small example:
sample code,
from langchain.schema import Document
list_of_documents = [
Document(page_content="foo", metadata=dict(page=1)),
Document(page_content="bar", metadata=dict(page=1)),
Document(page_content="foo", metadata=dict(page=2)),
Document(page_content="barbar", metadata=dict(page=2)),
Document(page_content="foo", metadata=dict(page=3)),
Document(page_content="bar burr", metadata=dict(page=3)),
Document(page_content="foo", metadata=dict(page=4)),
Document(page_content="bar bruh", metadata=dict(page=4)),
]
db = FAISS.from_documents(list_of_documents, embeddings)
results_with_scores = db.similarity_search_with_score("foo")
for doc, score in results_with_scores:
print(f"Content: {doc.page_content}, Metadata: {doc.metadata}, Score: {score}")
output result,
Content: foo, Metadata: {'page': 1}, Score: 0.018019594252109528
Content: foo, Metadata: {'page': 2}, Score: 0.018019594252109528
Content: foo, Metadata: {'page': 3}, Score: 0.018019594252109528
Content: foo, Metadata: {'page': 4}, Score: 0.018019594252109528
Now we make the same query call, but we only filter page = 1,
results_with_scores = db.similarity_search_with_score("foo", filter=dict(page=1))
for doc, score in results_with_scores:
print(f"Content: {doc.page_content}, Metadata: {doc.metadata}, Score: {score}")
output result,
Content: foo, Metadata: {'page': 1}, Score: 0.018019594252109528
Content: bar, Metadata: {'page': 1}, Score: 10266.8544921875
The same thing can be max_marginal_relevance_searchdone with .
sample code,
results = db.max_marginal_relevance_search("foo", filter=dict(page=1))
for doc in results:
print(f"Content: {doc.page_content}, Metadata: {doc.metadata}")
output result,
Content: foo, Metadata: {'page': 1}
Content: bar, Metadata: {'page': 1}
Here is an example of similarity_searchhow to set fetch_kthe parameter when calling . Usually you want fetch_kParameters >> kParameters. This is because fetch_kthe parameter is the number of documents that will be fetched before filtering. If you fetch_kset to a low number, you may not get enough documents to filter.
sample code,
results = db.similarity_search("foo", filter=dict(page=1), k=1, fetch_k=4)
for doc in results:
print(f"Content: {doc.page_content}, Metadata: {doc.metadata}")
output result,
Content: foo, Metadata: {'page': 1}
end!