Upload 5 files

app.py

@@ -0,0 +1,28 @@
+import streamlit as st
+from index import ask
+
+st.subheader(':red[AI Chatbot] :robot_face:')
+st.caption('This bot is here to assist you in discovering more about https://www.cardinality.ai/ :sunglasses:')
+
+# Initialize chat history
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+# Display chat messages from history on app rerun
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+# React to user input
+if prompt := st.chat_input("What is up?"):
+    # Display user message in chat message container
+    st.chat_message("human").markdown(prompt)
+    # Add user message to chat history
+    st.session_state.messages.append({"role": "user", "content": prompt})
+
+    response = ask(prompt)
+    # Display assistant response in chat message container
+    with st.chat_message("assistant"):
+        st.markdown(response)
+    # Add assistant response to chat history
+    st.session_state.messages.append({"role": "assistant", "content": response})

faiss_index/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b448cfb51dbccfdb2adac81c992ec471461e3cc302c583e4729465a6db3904b2
+size 31034

index.py

@@ -0,0 +1,29 @@
+from langchain.document_loaders import PyPDFLoader
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.vectorstores import ElasticVectorSearch, Pinecone, Weaviate, FAISS
+from langchain.chains import RetrievalQA
+from langchain.chat_models import ChatOpenAI
+import os
+os.environ["OPENAI_API_KEY"]
+
+# loader = PyPDFLoader("cardinality.pdf")
+# pages = loader.load_and_split()
+# print(len(pages), pages)
+
+embeddings = OpenAIEmbeddings()
+# Create DB
+# db = FAISS.from_documents(pages, embeddings)
+
+# Save the DB in your local
+# db.save_local("faiss_index")
+
+# # load the DB 
+new_db = FAISS.load_local("faiss_index", embeddings)
+
+# # Init LLM
+llm = ChatOpenAI()
+qa_chain = RetrievalQA.from_chain_type(llm, retriever=new_db.as_retriever())
+
+def ask(user_query):
+    res=qa_chain({"query": user_query})
+    return res["result"]

requirements.txt

@@ -0,0 +1,5 @@
+langchain
+pypdf
+openai
+faiss-cpu
+tiktoken