pip install vectorview


Get your key by logging in to the vectorview dashboard

from vectorview import Vectorview
vv = Vectorview(key)
vv.event(query, docs_with_score)


from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import TokenTextSplitter
from langchain.vectorstores import FAISS
from vectorview import Vectorview

# Setup
vv = Vectorview(key)

# Do semantic search
with open("./text.txt", "r") as f:
    text =
text_splitter = TokenTextSplitter(chunk_size=40, chunk_overlap=0)
texts = text_splitter.split_text(text)

embeddings = OpenAIEmbeddings()
db = FAISS.from_texts(texts, embeddings)

query = "What did the president say about Ketanji Brown Jackson"
docs_with_score = db.similarity_search_with_score(query, 3)

# Log vv event
vv.event(query, docs_with_score)

Advanced Use

Query metadata

Assign custom metadata to an event() by passing a dict as the third argument.

vv.event(query, docs_with_score, {"foo": "bar"})

Document metadata

Documents in vectorview are langchain Documents which has a metadata field. Any metadata added will show up in your vectorview dashboard.

docs_with_score[0][0].metadata = {"foo": "bar"}
vv.event(query, docs_with_score)

Custom document id

Vectorview assigns an id to each document used in an event(). To assign a custom id, add an id field in the Document’s metadata.

docs_with_score[0][0].metadata = {"id": new_id}
vv.event(query, docs_with_score)