Create app.py

app.py

@@ -0,0 +1,97 @@
+import streamlit as st
+import pandas as pd
+import os
+from dotenv import load_dotenv
+from langchain_community.document_loaders.csv_loader import CSVLoader
+from langchain_community.vectorstores import FAISS as LangChainFAISS
+from langchain.chains import create_retrieval_chain
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_openai import OpenAIEmbeddings, ChatOpenAI
+from llama_index import SimpleDirectoryReader, VectorStoreIndex
+from llama_index.embeddings.openai import OpenAIEmbedding
+from llama_index.vector_stores.faiss import FaissVectorStore
+from llama_index.llms.openai import OpenAI
+import faiss
+
+# Load environment variables
+os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
+
+# Set global OpenAI parameters
+EMBED_DIMENSION = 512
+llama_llm = OpenAI(model="gpt-3.5-turbo")
+llama_embedding_model = OpenAIEmbedding(model="text-embedding-3-small", dimensions=EMBED_DIMENSION)
+langchain_llm = ChatOpenAI(model="gpt-3.5-turbo")
+
+# Streamlit app
+st.title("Streamlit App with LangChain and LlamaIndex")
+
+# File uploader
+uploaded_file = st.file_uploader("Upload a CSV file", type=["csv"])
+if uploaded_file:
+    data = pd.read_csv(uploaded_file)
+    st.write("Preview of uploaded data:")
+    st.dataframe(data)
+
+    # Tabs
+    tab1, tab2 = st.tabs(["Chat w CSV using LangChain", "Chat w CSV using LlamaIndex"])
+
+    # LangChain Tab
+    with tab1:
+        st.subheader("LangChain Query")
+        loader = CSVLoader(file_path=uploaded_file)
+        docs = loader.load_and_split()
+
+        # LangChain FAISS VectorStore
+        langchain_index = faiss.IndexFlatL2(EMBED_DIMENSION)
+        langchain_vector_store = LangChainFAISS(
+            embedding_function=OpenAIEmbeddings(),
+            index=langchain_index,
+        )
+        langchain_vector_store.add_documents(docs)
+
+        # LangChain Retrieval Chain
+        retriever = langchain_vector_store.as_retriever()
+        system_prompt = (
+            "You are an assistant for question-answering tasks. "
+            "Use the following pieces of retrieved context to answer "
+            "the question. If you don't know the answer, say that you "
+            "don't know. Use three sentences maximum and keep the "
+            "answer concise.\n\n{context}"
+        )
+        prompt = ChatPromptTemplate.from_messages(
+            [("system", system_prompt), ("human", "{input}")]
+        )
+        question_answer_chain = create_stuff_documents_chain(langchain_llm, prompt)
+        langchain_rag_chain = create_retrieval_chain(retriever, question_answer_chain)
+
+        # Query input for LangChain
+        query = st.text_input("Ask a question about your data (LangChain):")
+        if query:
+            answer = langchain_rag_chain.invoke({"input": query})
+            st.write(f"Answer: {answer['answer']}")
+
+    # LlamaIndex Tab
+    with tab2:
+        st.subheader("LlamaIndex Query")
+        csv_reader = SimpleDirectoryReader(
+            input_files=[uploaded_file],
+            file_extractor={".csv": PagedCSVReader()},
+        )
+        docs = csv_reader.load_data()
+
+        # LlamaIndex FAISS VectorStore
+        llama_faiss_index = faiss.IndexFlatL2(EMBED_DIMENSION)
+        llama_vector_store = FaissVectorStore(faiss_index=llama_faiss_index)
+        pipeline = IngestionPipeline(vector_store=llama_vector_store, documents=docs)
+        nodes = pipeline.run()
+
+        # LlamaIndex Query Engine
+        llama_index = VectorStoreIndex(nodes)
+        query_engine = llama_index.as_query_engine(similarity_top_k=2)
+
+        # Query input for LlamaIndex
+        query = st.text_input("Ask a question about your data (LlamaIndex):")
+        if query:
+            response = query_engine.query(query)
+            st.write(f"Answer: {response.response}")