Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,41 +1,39 @@
-# Fix permission error on Hugging Face
+# Hugging Face-compatible environment fixes
 import os
 os.environ["STREAMLIT_HOME"] = "/tmp"
 os.environ["XDG_CONFIG_HOME"] = "/tmp"
 os.environ["XDG_DATA_HOME"] = "/tmp"
 
+# Fix async loop crash in HF Spaces
+import asyncio
+try:
+    asyncio.get_running_loop()
+except RuntimeError:
+    asyncio.set_event_loop(asyncio.new_event_loop())
+
 import streamlit as st
 import pandas as pd
 import json
 import io
 
-
-from langchain.llms import OpenAI
+from langchain_openai import OpenAIEmbeddings, OpenAI
+from langchain_community.vectorstores import FAISS
 from langchain_experimental.agents.agent_toolkits import create_pandas_dataframe_agent
 from langchain.text_splitter import CharacterTextSplitter
-from langchain.embeddings import OpenAIEmbeddings
-from langchain.vectorstores import FAISS
 from langchain.chains import RetrievalQA
-from langchain_community.vectorstores import FAISS
-from langchain_openai import OpenAIEmbeddings
 
 import PyPDF2
 from docx import Document
 
-# Load OpenAI API Key
-
-from dotenv import load_dotenv, find_dotenv
-
-_ = load_dotenv(find_dotenv())
-
-# Get API key from Streamlit secrets
-API_KEY = os.getenv("OPENAI_API_KEY")
+# Load API key securely
+API_KEY = st.secrets["OPENAI_API_KEY"]
+embeddings_model = OpenAIEmbeddings(openai_api_key=API_KEY)
 
-# Streamlit app settings
+# Streamlit settings
 st.set_page_config(page_title="RAG File Chat", layout="centered")
 st.title("🧠 Chat with Your Uploaded File")
 
-# Initialize session state
+# Session state init
 if "uploaded_file" not in st.session_state:
     st.session_state.uploaded_file = None
 if "file_uploaded" not in st.session_state:
@@ -80,9 +78,9 @@ def create_agent_and_index(file_content, file_type):
     elif file_type in ["pdf", "docx"]:
         text = extract_text_from_file(file_content, file_type)
         st.success(f"📃 Extracted text from {file_type.upper()}.")
-        text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
-        texts = text_splitter.split_text(text)
-        st.session_state.vectorstore = FAISS.from_texts(texts, embeddings_model)
+        splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+        chunks = splitter.split_text(text)
+        st.session_state.vectorstore = FAISS.from_texts(chunks, embeddings_model)
         st.success("🧠 Embedded text and stored in FAISS.")
     else:
         st.error("❌ Unsupported file type.")
@@ -91,7 +89,7 @@ def create_agent_and_index(file_content, file_type):
     st.session_state.file_type = file_type
 
 
-# 📁 Upload Section
+# 📁 Upload UI
 uploaded = st.file_uploader("📁 Browse and select a file", type=["csv", "xlsx", "json", "pdf", "docx"])
 if uploaded:
     st.session_state.uploaded_file = uploaded
@@ -103,7 +101,7 @@ if st.session_state.uploaded_file and st.button("📤 Upload File"):
     with st.spinner("🔄 Uploading and processing..."):
         create_agent_and_index(file_content, file_type)
 
-# 💬 Query Section
+# 💬 Query UI
 if st.session_state.file_uploaded:
     output_format = st.selectbox("📋 Select Output Format", ["Plain Text", "Markdown", "Tabular View"])
     query = st.text_area("💬 Ask a question about your uploaded file")
@@ -138,5 +136,5 @@ if st.session_state.file_uploaded:
                     df = pd.DataFrame(rows[1:], columns=rows[0])
                     st.dataframe(df)
                 except Exception:
-                    st.warning("⚠️ Could not render a table. Showing raw output instead.")
+                    st.warning("⚠️ Could not render table. Showing raw text.")
                     st.text(response)