Spaces:
Sleeping
Sleeping
File size: 4,138 Bytes
8f5e545 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 |
import streamlit as st
import os
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from io import StringIO
from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
os.environ["HF_TOKEN"]=os.getenv('HF_Token')
os.environ["HUGGINGFACEHUB_API_KEY"]=os.getenv('HF_Token')
st.set_page_config(page_title="InsightGenie – AI-Powered CSV Explorer", layout="wide")
st.title("🧙 InsightGenie")
st.markdown("**Explore your CSV like magic – Ask, analyze, and visualize with AI.**")
if "qa_conversations" not in st.session_state:
st.session_state.qa_conversations = []
uploaded_csv = st.file_uploader("📂 Upload your CSV file to begin", type=["csv"])
if uploaded_csv:
try:
data = pd.read_csv(uploaded_csv)
st.success("✅ Data loaded successfully!")
st.header("🔎 Dataset Overview")
st.markdown(f"- **Rows and Columns:** {data.shape[0]} rows × {data.shape[1]} columns")
st.markdown("**📌 Column Names:**")
st.write(data.columns.tolist())
col1, col2 = st.columns(2)
with col1:
st.markdown("**🧩 Missing Values**")
st.dataframe(data.isnull().sum(), height=200)
with col2:
st.markdown("**🔢 Data Types**")
st.dataframe(data.dtypes, height=200)
except Exception as e:
st.error(f"❌ Failed to read the file: {e}")
st.stop()
st.header("💬 Ask InsightGenie")
user_question = st.text_input("Type your question about the dataset here:")
genie_endpoint = HuggingFaceEndpoint(
repo_id="deepseek-ai/DeepSeek-R1",
provider="nebius",
temperature=0.5,
max_new_tokens=150,
task="conversational"
)
genie_chatbot = ChatHuggingFace(
llm=genie_endpoint,
repo_id=genie_endpoint.repo_id,
provider=genie_endpoint.provider,
temperature=0.5,
max_new_tokens=150,
task="conversational"
)
if user_question:
sample_data = data.head(50).to_csv(index=False)
prompt = f"""
You are a skilled data assistant named InsightGenie. A user has uploaded a dataset and asked a question.
Answer clearly. If the question involves charts or graphs, provide appropriate Python code using matplotlib or seaborn.
Here’s a preview of the dataset:
{sample_data}
User question:
{user_question}
"""
with st.spinner("🔍 Generating response..."):
try:
model_response = genie_chatbot.invoke([{"role": "user", "content": prompt}])
bot_reply = model_response.content if hasattr(model_response, "content") else model_response
st.session_state.qa_conversations.append((user_question, bot_reply))
st.markdown("### 🧠 Genie Says")
st.write(bot_reply)
# Auto-plot for simple queries
if "plot" in user_question.lower():
with st.expander("📊 Auto-generated Plot"):
try:
numeric_cols = data.select_dtypes(include='number').columns.tolist()
if len(numeric_cols) >= 2:
fig, ax = plt.subplots()
sns.lineplot(data=data, x=numeric_cols[0], y=numeric_cols[1], ax=ax)
ax.set_title(f"{numeric_cols[1]} vs {numeric_cols[0]}")
st.pyplot(fig)
else:
st.info("⚠️ Not enough numeric columns to generate a plot.")
except Exception as e:
st.error(f"❌ Plotting error: {e}")
except Exception as e:
st.error(f"❌ Error generating AI response: {e}")
if st.session_state.qa_conversations:
st.header("📚 Chat History")
for user_q, ai_a in reversed(st.session_state.qa_conversations):
st.markdown(f"**🧑💻 You:** {user_q}")
st.markdown(f"**🤖 InsightGenie:** {ai_a}")
st.markdown("---")
|