File size: 1,599 Bytes
0a93ad3 569e532 0a93ad3 a740eb7 0a93ad3 a740eb7 0a93ad3 e123c9b |
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 |
# Retriever function
from pinecone import Pinecone
from langchain_openai import AzureOpenAIEmbeddings
import uuid
import pandas as pd
import streamlit as st
import os
# Initialize Pinecone client
pc = Pinecone(api_key=st.secrets["PC_API_KEY"])
index = pc.Index("openai-serverless")
# Azure OpenAI configuration
os.environ["AZURE_OPENAI_API_KEY"] = st.secrets["api_key"]
os.environ["AZURE_OPENAI_ENDPOINT"] = "https://davidfearn-gpt4.openai.azure.com/"
os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"] = "text-embedding-ada-002"
os.environ["AZURE_OPENAI_API_VERSION"] = "2024-08-01-preview"
# Model configuration
embeddings_model = AzureOpenAIEmbeddings(
azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
openai_api_version=os.environ["AZURE_OPENAI_API_VERSION"],
)
def retriever(query, k):
namespace="gskRegIntel"
"""
Embeds a query string and searches the vector database for similar entries.
:param query: The string to embed and search for.
:param namespace: Pinecone namespace to search within.
:param top_k: Number of top results to retrieve.
:return: List of search results with metadata and scores.
"""
try:
# Generate embedding for the query
query_embedding = embeddings_model.embed_query(query)
# Perform search in Pinecone
results = index.query(vector=query_embedding, top_k=k, namespace=namespace, include_metadata=True)
return results.matches
except Exception as e:
print(f"Error during search: {e}")
return [] |