Couchbase

pip install -qU langchain-couchbase

import getpass

COUCHBASE_CONNECTION_STRING = getpass.getpass(
    "Enter the connection string for the Couchbase cluster: "
)
DB_USERNAME = getpass.getpass("Enter the username for the Couchbase cluster: ")
DB_PASSWORD = getpass.getpass("Enter the password for the Couchbase cluster: ")

Enter the connection string for the Couchbase cluster:  ········
Enter the username for the Couchbase cluster:  ········
Enter the password for the Couchbase cluster:  ········

os.environ["LANGSMITH_TRACING"] = "true"
# os.environ["LANGSMITH_API_KEY"] = getpass.getpass()

from datetime import timedelta

from couchbase.auth import PasswordAuthenticator
from couchbase.cluster import Cluster
from couchbase.options import ClusterOptions

auth = PasswordAuthenticator(DB_USERNAME, DB_PASSWORD)
options = ClusterOptions(auth)
cluster = Cluster(COUCHBASE_CONNECTION_STRING, options)

# Wait until the cluster is ready for use.
cluster.wait_until_ready(timedelta(seconds=5))

BUCKET_NAME = "langchain_bucket"
SCOPE_NAME = "_default"
COLLECTION_NAME = "_default"
SEARCH_INDEX_NAME = "langchain-test-index"

# | output: false
# | echo: false
from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(model="text-embedding-3-large")

from langchain_couchbase.vectorstores import CouchbaseSearchVectorStore

vector_store = CouchbaseSearchVectorStore(
    cluster=cluster,
    bucket_name=BUCKET_NAME,
    scope_name=SCOPE_NAME,
    collection_name=COLLECTION_NAME,
    embedding=embeddings,
    index_name=SEARCH_INDEX_NAME,
)

vector_store_specific = CouchbaseSearchVectorStore(
    cluster=cluster,
    bucket_name=BUCKET_NAME,
    scope_name=SCOPE_NAME,
    collection_name=COLLECTION_NAME,
    embedding=embeddings,
    index_name=SEARCH_INDEX_NAME,
    text_key="text",
    embedding_key="embedding",
)

from uuid import uuid4

from langchain_core.documents import Document

document_1 = Document(
    page_content="I had chocolate chip pancakes and scrambled eggs for breakfast this morning.",
    metadata={"source": "tweet"},
)

document_2 = Document(
    page_content="The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees.",
    metadata={"source": "news"},
)

document_3 = Document(
    page_content="Building an exciting new project with LangChain - come check it out!",
    metadata={"source": "tweet"},
)

document_4 = Document(
    page_content="Robbers broke into the city bank and stole $1 million in cash.",
    metadata={"source": "news"},
)

document_5 = Document(
    page_content="Wow! That was an amazing movie. I can't wait to see it again.",
    metadata={"source": "tweet"},
)

document_6 = Document(
    page_content="Is the new iPhone worth the price? Read this review to find out.",
    metadata={"source": "website"},
)

document_7 = Document(
    page_content="The top 10 soccer players in the world right now.",
    metadata={"source": "website"},
)

document_8 = Document(
    page_content="LangGraph is the best framework for building stateful, agentic applications!",
    metadata={"source": "tweet"},
)

document_9 = Document(
    page_content="The stock market is down 500 points today due to fears of a recession.",
    metadata={"source": "news"},
)

document_10 = Document(
    page_content="I have a bad feeling I am going to get deleted :(",
    metadata={"source": "tweet"},
)

documents = [
    document_1,
    document_2,
    document_3,
    document_4,
    document_5,
    document_6,
    document_7,
    document_8,
    document_9,
    document_10,
]
uuids = [str(uuid4()) for _ in range(len(documents))]

vector_store.add_documents(documents=documents, ids=uuids)

['f125b836-f555-4449-98dc-cbda4e77ae3f',
 'a28fccde-fd32-4775-9ca8-6cdb22ca7031',
 'b1037c4b-947f-497f-84db-63a4def5080b',
 'c7082b74-b385-4c4b-bbe5-0740909c01db',
 'a7e31f62-13a5-4109-b881-8631aff7d46c',
 '9fcc2894-fdb1-41bd-9a93-8547747650f4',
 'a5b0632d-abaf-4802-99b3-df6b6c99be29',
 '0475592e-4b7f-425d-91fd-ac2459d48a36',
 '94c6db4e-ba07-43ff-aa96-3a5d577db43a',
 'd21c7feb-ad47-4e7d-84c5-785afb189160']

vector_store.delete(ids=[uuids[-1]])

True

results = vector_store.similarity_search(
    "LangChain provides abstractions to make working with LLMs easy",
    k=2,
)
for res in results:
    print(f"* {res.page_content} [{res.metadata}]")

* Building an exciting new project with LangChain - come check it out! [{'source': 'tweet'}]
* LangGraph is the best framework for building stateful, agentic applications! [{'source': 'tweet'}]

results = vector_store.similarity_search_with_score("Will it be hot tomorrow?", k=1)
for res, score in results:
    print(f"* [SIM={score:3f}] {res.page_content} [{res.metadata}]")

* [SIM=0.553112] The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees. [{'source': 'news'}]

from couchbase import search

query = "Are there any concerning financial news?"
filter_on_source = search.MatchQuery("news", field="metadata.source")
results = vector_store.similarity_search_with_score(
    query, fields=["metadata.source"], filter=filter_on_source, k=5
)
for res, score in results:
    print(f"* {res.page_content} [{res.metadata}] {score}")

* The stock market is down 500 points today due to fears of a recession. [{'source': 'news'}] 0.3873019218444824
* Robbers broke into the city bank and stole $1 million in cash. [{'source': 'news'}] 0.20637212693691254
* The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees. [{'source': 'news'}] 0.10404900461435318

query = "What did I eat for breakfast today?"
results = vector_store.similarity_search(query, fields=["metadata.source"])
print(results[0])

page_content='I had chocolate chip pancakes and scrambled eggs for breakfast this morning.' metadata={'source': 'tweet'}

retriever = vector_store.as_retriever(
    search_type="similarity",
    search_kwargs={"k": 1, "score_threshold": 0.5},
)
filter_on_source = search.MatchQuery("news", field="metadata.source")
retriever.invoke("Stealing from the bank is a crime", filter=filter_on_source)

[Document(id='c7082b74-b385-4c4b-bbe5-0740909c01db', metadata={'source': 'news'}, page_content='Robbers broke into the city bank and stole $1 million in cash.')]

from langchain_community.document_loaders import TextLoader
from langchain_text_splitters import CharacterTextSplitter

loader = TextLoader("../../how_to/state_of_the_union.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

# Adding metadata to documents
for i, doc in enumerate(docs):
    doc.metadata["date"] = f"{range(2010, 2020)[i % 10]}-01-01"
    doc.metadata["rating"] = range(1, 6)[i % 5]
    doc.metadata["author"] = ["John Doe", "Jane Doe"][i % 2]

vector_store.add_documents(docs)

query = "What did the president say about Ketanji Brown Jackson"
results = vector_store.similarity_search(query)
print(results[0].metadata)

{'author': 'John Doe', 'date': '2016-01-01', 'rating': 2, 'source': '../../how_to/state_of_the_union.txt'}

query = "What did the president say about Ketanji Brown Jackson"
results = vector_store.similarity_search(
    query,
    search_options={"query": {"field": "metadata.author", "match": "John Doe"}},
    fields=["metadata.author"],
)
print(results[0])

page_content='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.' metadata={'author': 'John Doe'}

query = "What did the president say about Ketanji Brown Jackson"
results = vector_store.similarity_search(
    query,
    search_options={
        "query": {"field": "metadata.author", "match": "Jae", "fuzziness": 1}
    },
    fields=["metadata.author"],
)
print(results[0])

page_content='A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.

And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system.' metadata={'author': 'Jane Doe'}

query = "Any mention about independence?"
results = vector_store.similarity_search(
    query,
    search_options={
        "query": {
            "start": "2016-12-31",
            "end": "2017-01-02",
            "inclusive_start": True,
            "inclusive_end": False,
            "field": "metadata.date",
        }
    },
)
print(results[0])

page_content='And with 75% of adult Americans fully vaccinated and hospitalizations down by 77%, most Americans can remove their masks, return to work, stay in the classroom, and move forward safely.

We achieved this because we provided free vaccines, treatments, tests, and masks.

Of course, continuing this costs money.

I will soon send Congress a request.

The vast majority of Americans have used these tools and may want to again, so I expect Congress to pass it quickly.' metadata={'author': 'Jane Doe', 'date': '2017-01-01', 'rating': 3, 'source': '../../how_to/state_of_the_union.txt'}

query = "Any mention about independence?"
results = vector_store.similarity_search_with_score(
    query,
    search_options={
        "query": {
            "min": 3,
            "max": 5,
            "inclusive_min": True,
            "inclusive_max": True,
            "field": "metadata.rating",
        }
    },
)
print(results[0])

(Document(id='3a90405c0f5b4c09a6646259678f1f61', metadata={'author': 'John Doe', 'date': '2014-01-01', 'rating': 5, 'source': '../../how_to/state_of_the_union.txt'}, page_content='In this Capitol, generation after generation, Americans have debated great questions amid great strife, and have done great things. \n\nWe have fought for freedom, expanded liberty, defeated totalitarianism and terror. \n\nAnd built the strongest, freest, and most prosperous nation the world has ever known. \n\nNow is the hour. \n\nOur moment of responsibility. \n\nOur test of resolve and conscience, of history itself.'), 0.3573387440020518)

query = "Any mention about independence?"
results = vector_store.similarity_search_with_score(
    query,
    search_options={
        "query": {
            "conjuncts": [
                {"min": 3, "max": 4, "inclusive_max": True, "field": "metadata.rating"},
                {"start": "2016-12-31", "end": "2017-01-02", "field": "metadata.date"},
            ]
        }
    },
)
print(results[0])

(Document(id='7115a704877a46ad94d661dd9c81cbc3', metadata={'author': 'Jane Doe', 'date': '2017-01-01', 'rating': 3, 'source': '../../how_to/state_of_the_union.txt'}, page_content='And with 75% of adult Americans fully vaccinated and hospitalizations down by 77%, most Americans can remove their masks, return to work, stay in the classroom, and move forward safely. \n\nWe achieved this because we provided free vaccines, treatments, tests, and masks. \n\nOf course, continuing this costs money. \n\nI will soon send Congress a request. \n\nThe vast majority of Americans have used these tools and may want to again, so I expect Congress to pass it quickly.'), 0.6898253780130769)

filter_text = search.MatchQuery("independence", field="text")

query = "Any mention about independence?"
results = vector_store.similarity_search_with_score(
    query,
    search_options={
        "query": {
            "min": 3,
            "max": 5,
            "inclusive_min": True,
            "inclusive_max": True,
            "field": "metadata.rating",
        }
    },
    filter=filter_text,
)

print(results[0])

(Document(id='23bb51b4e4d54a94ab0a95e72be8428c', metadata={'author': 'John Doe', 'date': '2012-01-01', 'rating': 3, 'source': '../../how_to/state_of_the_union.txt'}, page_content='And we remain clear-eyed. The Ukrainians are fighting back with pure courage. But the next few days weeks, months, will be hard on them.  \n\nPutin has unleashed violence and chaos.  But while he may make gains on the battlefield – he will pay a continuing high price over the long run. \n\nAnd a proud Ukrainian people, who have known 30 years  of independence, have repeatedly shown that they will not tolerate anyone who tries to take their country backwards.'), 0.30549919644400614)