%pip install"pgvecto_rs[sdk]" langchain-community

from typingimport List

from langchain_community.document_loadersimport TextLoader
from langchain_community.embeddings.fakeimport FakeEmbeddings
from langchain_community.vectorstores.pgvecto_rsimport PGVecto_rs
from langchain_core.documentsimport Document
from langchain_text_splittersimport CharacterTextSplitter

loader= TextLoader("../../how_to/state_of_the_union.txt")
documents= loader.load()
text_splitter= CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs= text_splitter.split_documents(documents)

embeddings= FakeEmbeddings(size=3)

! docker run--name pgvecto-rs-demo-e POSTGRES_PASSWORD=mysecretpassword-p5432:5432-d tensorchord/pgvecto-rs:latest

## PGVecto.rs needs the connection string to the database.
## We will load it from the environment variables.
import os

PORT= os.getenv("DB_PORT",5432)
HOST= os.getenv("DB_HOST","localhost")
USER= os.getenv("DB_USER","postgres")
PASS= os.getenv("DB_PASS","mysecretpassword")
DB_NAME= os.getenv("DB_NAME","postgres")

# Run tests with shell:
URL="postgresql+psycopg://{username}:{password}@{host}:{port}/{db_name}".format(
    port=PORT,
    host=HOST,
    username=USER,
    password=PASS,
    db_name=DB_NAME,
)

db1= PGVecto_rs.from_documents(
    documents=docs,
    embedding=embeddings,
    db_url=URL,
# The table name is f"collection_{collection_name}", so that it should be unique.
    collection_name="state_of_the_union",
)

# Create new empty vectorstore with collection_name.
# Or connect to an existing vectorstore in database if exists.
# Arguments should be the same as when the vectorstore was created.
db1= PGVecto_rs.from_collection_name(
    embedding=embeddings,
    db_url=URL,
    collection_name="state_of_the_union",
)

query="What did the president say about Ketanji Brown Jackson"
docs: List[Document]= db1.similarity_search(query, k=4)
for docin docs:
print(doc.page_content)
print("======================")

from pgvecto_rs.sdk.filtersimport meta_contains

query="What did the president say about Ketanji Brown Jackson"
docs: List[Document]= db1.similarity_search(
    query, k=4,filter=meta_contains({"source":"../../how_to/state_of_the_union.txt"})
)

for docin docs:
print(doc.page_content)
print("======================")

query="What did the president say about Ketanji Brown Jackson"
docs: List[Document]= db1.similarity_search(
    query, k=4,filter={"source":"../../how_to/state_of_the_union.txt"}
)

for docin docs:
print(doc.page_content)
print("======================")