revert back to Faiss

app.py

@@ -1,4 +1,5 @@
 # Langchain imports
+from langchain_community.vectorstores.faiss import FAISS
 from langchain_groq import ChatGroq 
 from langchain_community.document_loaders import WebBaseLoader
 from langchain_community.embeddings import HuggingFaceEmbeddings
@@ -6,7 +7,6 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.chains.combine_documents import create_stuff_documents_chain
 from langchain_core.prompts import ChatPromptTemplate
 from langchain.chains import create_retrieval_chain
-from langchain_pinecone import PineconeVectorStore
 
 # Embedding and model import
 # Other
@@ -62,10 +62,6 @@ st.session_state.embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2
 
 st.session_state.text_splitter = RecursiveCharacterTextSplitter(chunk_size =1000, chunk_overlap= 200)
 
-index_name = "myindex"
-st.session_state.vector = PineconeVectorStore(index_name=index_name, embedding=st.session_state.embeddings)
-
-
 if option:
     if option == "Website":
         website_link = st.text_input("Enter the website link:")
@@ -74,7 +70,7 @@ if option:
                 st.session_state.loader = WebBaseLoader(website_link)
                 st.session_state.docs = st.session_state.loader.load()
                 st.session_state.final_documents = st.session_state.text_splitter.split_documents(st.session_state.docs)
-                st.session_state.vector = PineconeVectorStore.from_documents(st.session_state.final_documents, index_name=index_name, embedding = st.session_state.embeddings)
+                st.session_state.vector = FAISS.from_documents(st.session_state.final_documents,st.session_state.embeddings)            
             st.success("Done!")
         llm_model()
             
@@ -84,7 +80,7 @@ if option:
             with st.spinner("Loading pdf..."):
                 st.session_state.docs = get_pdf_processed(pdf_files)
                 st.session_state.final_documents = st.session_state.text_splitter.split_text(st.session_state.docs)
-                st.session_state.vector = PineconeVectorStore.from_texts(st.session_state.final_documents, index_name=index_name, embedding = st.session_state.embeddings) 
+                st.session_state.vector = FAISS.from_texts(st.session_state.final_documents,st.session_state.embeddings)            
             st.success("Done!")
             st.empty()
             llm_model()