getting client details

app.py

@@ -1,15 +1,8 @@
 import streamlit as st
 import pandas as pd
-from torch import cuda
-from langchain_community.embeddings import HuggingFaceEmbeddings, HuggingFaceInferenceAPIEmbeddings
-from langchain_community.vectorstores import Qdrant
-from qdrant_client import QdrantClient
-from langchain.retrievers import ContextualCompressionRetriever
-from langchain.retrievers.document_compressors import CrossEncoderReranker
-from langchain_community.cross_encoders import HuggingFaceCrossEncoder
 from appStore.prep_data import process_giz_worldwide
-from appStore.prep_utils import create_documents
-from appStore.embed import hybrid_embed_chunks, get_local_qdrant
+from appStore.prep_utils import create_documents, get_client
+from appStore.embed import hybrid_embed_chunks
 
 # get the device to be used eithe gpu or cpu
 device = 'cuda' if cuda.is_available() else 'cpu'
@@ -19,12 +12,6 @@ st.set_page_config(page_title="SEARCH IATI",layout='wide')
 st.title("SEARCH IATI Database")
 var=st.text_input("enter keyword")
 
-import pkg_resources
-installed_packages = pkg_resources.working_set 
-list_ = ""
-for package in installed_packages:
-    list_ = list_ + f"{package.key}=={package.version}\n"
-st.download_button('Download Requirements', list_, file_name='ins_requirements.txt')  
 ####################  Create the embeddings collection and save ######################
 # the steps below need to be performed only once and then commented out any unnecssary compute over-run
 ##### First we process and create the chunks for relvant data source
@@ -32,10 +19,12 @@ st.download_button('Download Requirements', list_, file_name='ins_requirements.t
 ##### Convert to langchain documents
 #temp_doc = create_documents(chunks,'chunks')
 ##### Embed and store docs, check if collection exist then you need to update the collection
-#hybrid_embed_chunks(docs= temp_doc, collection_name = "giz_worldwide")
+#collection_name = "giz_worldwide"
+#hybrid_embed_chunks(docs= temp_doc, collection_name = collection_name)
 
 ################### Hybrid Search ######################################################
-
+client = get_client()
+print(client.get_collections())
 
 
 button=st.button("search")