Spaces:
Sleeping
Sleeping
File size: 2,467 Bytes
e2b9039 3ecbeff e2b9039 b21411e 3ecbeff e2b9039 d792c52 b21411e e2b9039 3ecbeff b21411e 3ecbeff e2b9039 b21411e e2b9039 b21411e fff69e7 e2b9039 b21411e 3ecbeff b0a56a3 b21411e b0a56a3 b21411e b0a56a3 b21411e |
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 59 60 61 62 63 64 65 66 67 68 69 70 71 |
import os
import streamlit as st
from pinecone import Pinecone
from sentence_transformers import SentenceTransformer
# Title of the Streamlit App
st.title("Pinecone Query Search on 'pubmed-splade' Index")
# Initialize Pinecone globally
index = None
# Function to initialize Pinecone
def initialize_pinecone():
api_key = os.getenv('PINECONE_API_KEY') # Get Pinecone API key from environment variable
if api_key:
# Initialize Pinecone client using the new class instance method
pc = Pinecone(api_key=api_key)
return pc
else:
st.error("Pinecone API key not found! Please set the PINECONE_API_KEY environment variable.")
return None
# Function to connect to the 'pubmed-splade' index
def connect_to_index(pc):
index_name = 'pubmed-splade' # Hardcoded index name
# Connect to the 'pubmed-splade' index
if index_name in pc.list_indexes().names():
st.info(f"Successfully connected to index '{index_name}'")
index = pc.Index(index_name)
return index
else:
st.error(f"Index '{index_name}' not found!")
return None
# Function to encode query using sentence transformers model
def encode_query(model, query_text):
return model.encode(query_text).tolist()
# Initialize Pinecone
pc = initialize_pinecone()
# If Pinecone initialized successfully, proceed with index management
if pc:
# Connect directly to 'pubmed-splade' index
index = connect_to_index(pc)
# Model for query encoding
model = SentenceTransformer('msmarco-bert-base-dot-v5')
# Query input
query_text = st.text_input("Enter a Query to Search", "Can clinicians use the PHQ-9 to assess depression?")
# Button to encode query and search the Pinecone index
if st.button("Search Query"):
if query_text and index:
dense_vector = encode_query(model, query_text)
st.write(f"Encoded Query Vector: {dense_vector}")
# Search the index (sparse values can be added here as well)
results = index.query(
vector=dense_vector,
top_k=5,
include_metadata=True
)
st.write("Search Results:")
for match in results.matches:
st.write(f"ID: {match.id}, Score: {match.score}, Metadata: {match.metadata}")
else:
st.error("Please enter a query and ensure the index is initialized.")
|