Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,8 +1,11 @@
-# Hugging Face-compatible environment fixes
+# ✅ Clean and Final Streamlit RAG App (Hugging Face + Local Ready)
+
+# --- Environment Setup (Safe for Hugging Face) ---
 import os
 os.environ["STREAMLIT_HOME"] = "/tmp"
 os.environ["XDG_CONFIG_HOME"] = "/tmp"
 os.environ["XDG_DATA_HOME"] = "/tmp"
+os.environ["HOME"] = "/tmp"
 
 import asyncio
 try:
@@ -10,45 +13,35 @@ try:
 except RuntimeError:
     asyncio.set_event_loop(asyncio.new_event_loop())
 
-
-from dotenv import load_dotenv, find_dotenv
-import os
+# --- Imports ---
 import streamlit as st
 import pandas as pd
 import json
 import io
-
+from dotenv import load_dotenv, find_dotenv
 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.chains import RetrievalQA
-import streamlit.runtime.metrics_util
-streamlit.runtime.metrics_util._get_machine_id_v4 = lambda: "HUGGINGFACE_PATCH"
-
 import PyPDF2
 from docx import Document
 
-# Load local .env if it exists
+# --- Load API Key Securely ---
 _ = load_dotenv(find_dotenv())
-
-# Try Hugging Face secret first, then fallback to environment
 API_KEY = st.secrets.get("OPENAI_API_KEY", os.getenv("OPENAI_API_KEY"))
 
 if not API_KEY:
-    st.error("❌ OPENAI_API_KEY not found. Please set it in Hugging Face → Settings → Secrets.")
+    st.error("\u274c `OPENAI_API_KEY` is missing.\n\nGo to Hugging Face Settings → Secrets and add it, or use a `.env` file locally.")
     st.stop()
 
-# Get OpenAI API key from Hugging Face secrets
-
-
 embeddings_model = OpenAIEmbeddings(openai_api_key=API_KEY)
 
-# Streamlit settings
+# --- Streamlit Page Setup ---
 st.set_page_config(page_title="RAG File Chat", layout="centered")
-st.title("🧠 Chat with Your Uploaded File")
+st.title("\ud83e\udee0 Chat with Your Uploaded File")
 
-# Session state init
+# --- Session State ---
 if "uploaded_file" not in st.session_state:
     st.session_state.uploaded_file = None
 if "file_uploaded" not in st.session_state:
@@ -60,7 +53,7 @@ if "agent" not in st.session_state:
 if "file_type" not in st.session_state:
     st.session_state.file_type = None
 
-
+# --- File Parsing Functions ---
 def extract_text_from_file(file_content, file_type):
     if file_type == "pdf":
         reader = PyPDF2.PdfReader(io.BytesIO(file_content))
@@ -70,62 +63,55 @@ def extract_text_from_file(file_content, file_type):
         return "\n".join([p.text for p in doc.paragraphs if p.text.strip()])
     return ""
 
-
 def create_agent_and_index(file_content, file_type):
     if file_type == "csv":
         df = pd.read_csv(io.StringIO(file_content.decode("utf-8")))
-        st.success("📄 CSV file loaded.")
         llm = OpenAI(openai_api_key=API_KEY)
         st.session_state.agent = create_pandas_dataframe_agent(llm, df, verbose=False)
-        st.success("🤖 Agent created for tabular data.")
+        st.success("\ud83e\udd16 Agent created for CSV.")
     elif file_type == "xlsx":
         df = pd.read_excel(file_content)
-        st.success("📄 Excel file loaded.")
         llm = OpenAI(openai_api_key=API_KEY)
         st.session_state.agent = create_pandas_dataframe_agent(llm, df, verbose=False)
-        st.success("🤖 Agent created for tabular data.")
+        st.success("\ud83e\udd16 Agent created for Excel.")
     elif file_type == "json":
         df = pd.DataFrame(json.loads(file_content.decode("utf-8")))
-        st.success("📄 JSON file loaded.")
         llm = OpenAI(openai_api_key=API_KEY)
         st.session_state.agent = create_pandas_dataframe_agent(llm, df, verbose=False)
-        st.success("🤖 Agent created for tabular data.")
+        st.success("\ud83e\udd16 Agent created for JSON.")
     elif file_type in ["pdf", "docx"]:
         text = extract_text_from_file(file_content, file_type)
-        st.success(f"📃 Extracted text from {file_type.upper()}.")
-        splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
-        chunks = splitter.split_text(text)
+        chunks = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0).split_text(text)
         st.session_state.vectorstore = FAISS.from_texts(chunks, embeddings_model)
-        st.success("🧠 Embedded text and stored in FAISS.")
+        st.success("\ud83d\udcca Text embedded into FAISS vectorstore.")
     else:
-        st.error("❌ Unsupported file type.")
+        st.error("\u274c Unsupported file type.")
         return
     st.session_state.file_uploaded = True
     st.session_state.file_type = file_type
 
-
-# 📁 Upload UI
-uploaded = st.file_uploader("📁 Browse and select a file", type=["csv", "xlsx", "json", "pdf", "docx"])
+# --- File Upload UI ---
+uploaded = st.file_uploader("\ud83d\udcc1 Browse and select a file", type=["csv", "xlsx", "json", "pdf", "docx"])
 if uploaded:
     st.session_state.uploaded_file = uploaded
-    st.info(f"✅ File selected: `{uploaded.name}` ({uploaded.size / 1024:.1f} KB)")
+    st.info(f"\u2705 File selected: `{uploaded.name}` ({uploaded.size / 1024:.1f} KB)")
 
-if st.session_state.uploaded_file and st.button("📤 Upload File"):
-    file_content = st.session_state.uploaded_file.read()
-    file_type = st.session_state.uploaded_file.name.split(".")[-1]
-    with st.spinner("🔄 Uploading and processing..."):
-        create_agent_and_index(file_content, file_type)
+if st.session_state.uploaded_file and st.button("\ud83d\udce4 Upload File"):
+    content = st.session_state.uploaded_file.read()
+    ftype = st.session_state.uploaded_file.name.split(".")[-1].lower()
+    with st.spinner("\ud83d\udd04 Processing file..."):
+        create_agent_and_index(content, ftype)
 
-# 💬 Query UI
+# --- 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")
+    output_format = st.selectbox("\ud83d\udcca Select Output Format", ["Plain Text", "Markdown", "Tabular View"])
+    query = st.text_area("\ud83d\udd0d Ask a question about your uploaded file")
 
     if st.button("Submit Query"):
         if not query.strip():
-            st.warning("⚠️ Please enter a valid question.")
+            st.warning("\u26a0\ufe0f Please enter a valid question.")
         else:
-            with st.spinner("💡 Thinking..."):
+            with st.spinner("\ud83d\udca1 Thinking..."):
                 if st.session_state.file_type in ["pdf", "docx"]:
                     qa_chain = RetrievalQA.from_chain_type(
                         llm=OpenAI(openai_api_key=API_KEY),
@@ -137,8 +123,7 @@ if st.session_state.file_uploaded:
                 else:
                     response = st.session_state.agent.run(query)
 
-            st.subheader("📌 Answer")
-
+            st.subheader("\ud83d\udccc Answer")
             if output_format == "Plain Text":
                 st.text(response)
             elif output_format == "Markdown":
@@ -151,5 +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 table. Showing raw text.")
+                    st.warning("\u26a0\ufe0f Could not render table. Showing raw text.")
                     st.text(response)