Update lab/app.py

lab/app.py

@@ -2,7 +2,7 @@ import streamlit as st
 import pandas as pd
 import os
 from dotenv import load_dotenv
-from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
+from llama_index.core import Settings, VectorStoreIndex, SimpleDirectoryReader
 from llama_index.readers.file import PagedCSVReader
 from llama_index.embeddings.openai import OpenAIEmbedding
 from llama_index.llms.openai import OpenAI
@@ -19,11 +19,10 @@ import faiss
 # Load environment variables
 os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
 
-# Global OpenAI and FAISS settings
+# Global settings for LlamaIndex
 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-0125")
+Settings.llm = OpenAI(model="gpt-3.5-turbo")
+Settings.embed_model = OpenAIEmbedding(model="text-embedding-3-small", dimensions=EMBED_DIMENSION)
 
 # Streamlit app
 st.title("Streamlit App with LangChain and LlamaIndex")
@@ -31,7 +30,13 @@ 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)
+    # Save the uploaded file temporarily
+    temp_file_path = f"temp_{uploaded_file.name}"
+    with open(temp_file_path, "wb") as temp_file:
+        temp_file.write(uploaded_file.getbuffer())
+
+    # Read and preview CSV data
+    data = pd.read_csv(temp_file_path)
     st.write("Preview of uploaded data:")
     st.dataframe(data)
 
@@ -41,12 +46,13 @@ if uploaded_file:
     # LangChain Tab
     with tab1:
         st.subheader("LangChain Query")
-        loader = CSVLoader(file_path=uploaded_file.name)
+        loader = CSVLoader(file_path=temp_file_path)
         docs = loader.load_and_split()
 
         # Preview the first document
-        st.write("Preview of a document chunk (LangChain):")
-        st.text(docs[0].page_content)
+        if docs:
+            st.write("Preview of a document chunk (LangChain):")
+            st.text(docs[0].page_content)
 
         # LangChain FAISS VectorStore
         langchain_index = faiss.IndexFlatL2(EMBED_DIMENSION)
@@ -68,7 +74,7 @@ if uploaded_file:
         prompt = ChatPromptTemplate.from_messages(
             [("system", system_prompt), ("human", "{input}")]
         )
-        question_answer_chain = create_stuff_documents_chain(langchain_llm, prompt)
+        question_answer_chain = create_stuff_documents_chain(ChatOpenAI(), prompt)
         langchain_rag_chain = create_retrieval_chain(retriever, question_answer_chain)
 
         # Query input for LangChain
@@ -80,17 +86,17 @@ if uploaded_file:
     # LlamaIndex Tab
     with tab2:
         st.subheader("LlamaIndex Query")
-        # Use PagedCSVReader for CSV loading
         csv_reader = PagedCSVReader()
         reader = SimpleDirectoryReader(
-            input_files=[uploaded_file.name],
+            input_files=[temp_file_path],
             file_extractor={".csv": csv_reader},
         )
         docs = reader.load_data()
 
         # Preview the first document
-        st.write("Preview of a document chunk (LlamaIndex):")
-        st.text(docs[0].text)
+        if docs:
+            st.write("Preview of a document chunk (LlamaIndex):")
+            st.text(docs[0].text)
 
         # Initialize FAISS Vector Store
         llama_faiss_index = faiss.IndexFlatL2(EMBED_DIMENSION)
@@ -108,4 +114,7 @@ if uploaded_file:
         query = st.text_input("Ask a question about your data (LlamaIndex):")
         if query:
             response = query_engine.query(query)
-            st.write(f"Answer: {response.response}")
+            st.write(f"Answer: {response.response}")
+
+    # Cleanup temporary file
+    os.remove(temp_file_path)