Spaces:
Sleeping
Sleeping
File size: 1,370 Bytes
97ea681 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 | # import basics
import os
from dotenv import load_dotenv
# import pinecone
from pinecone import Pinecone, ServerlessSpec
# import langchain
from langchain_pinecone import PineconeVectorStore
from langchain_google_genai import GoogleGenerativeAIEmbeddings
from langchain_core.documents import Document
load_dotenv()
# initialize pinecone database
pc = Pinecone(api_key=os.environ.get("PINECONE_API_KEY"))
# set the pinecone index
index_name = "sample-index"
index = pc.Index(index_name)
# initialize embeddings model + vector store
embeddings = GoogleGenerativeAIEmbeddings(model="models/gemini-embedding-001")
vector_store = PineconeVectorStore(index=index, embedding=embeddings)
# retrieval
'''
###### add docs to db ##############################
results = vector_store.similarity_search_with_score(
"what did you have for breakfast?",
#k=2,
filter={"source": "tweet"},
)
print("RESULTS:")
for res in results:
print(f"* {res[0].page_content} [{res[0].metadata}] -- {res[1]}")
'''
retriever = vector_store.as_retriever(
search_type="similarity_score_threshold",
search_kwargs={"k": 5, "score_threshold": 0.6},
)
results = retriever.invoke("what did you have for breakfast?")
print("RESULTS:")
for res in results:
print(f"* {res.page_content} [{res.metadata}]")
#'''
|