import streamlit as st
import pandas as pd
import anthropic
import base64
import plotly.express as px
from datetime import datetime
import json
from pathlib import Path
from utils import EmbeddingManager
def send_to_llm(user_query, data, df):
"""Send data chunks to the LLM and get a response."""
columns = df.columns.tolist()
dtypes = df.dtypes.to_dict()
summary_stats = df.describe().to_json()
client = anthropic.AnthropicBedrock()
prompt = f"""Given this Excel data:
Columns: {columns}
Data types: {dtypes}
Summary statistics: {summary_stats}
Create a complete, professional HTML report that includes:
1. Executive summary
2. Data insights and patterns
3. Statistical analysis
4. Visualizations using Plotly
Important Requirements:
- Include all necessary Plotly CDN scripts
- Choose appropriate visualizations based on the data patterns
- Include proper styling with CSS
- Make it visually appealing and professional
- Add explanations for each insight and visualization
- Include the current date in the report
For visualizations:
- Use Plotly.js for all charts
- Include the full Plotly JavaScript code
- Choose appropriate chart types based on the data
- Add proper titles, labels, and legends
Return only the complete HTML code that's ready to be saved as an HTML file."""
message = client.messages.create(
model="anthropic.claude-3-5-sonnet-20240620-v1:0",
max_tokens=4096, # Increased token limit for full HTML response
system=prompt,
messages=[{
"role": "user",
"content": f"Generate a complete HTML report analyzing this data: {str(data)} \nUser query: {user_query}"
}]
)
# Extract only the HTML content
response_text = message.content[0].text
if "" not in response_text:
# Fallback if response isn't proper HTML
return f"""
Analysis Report
{response_text}
"""
return response_text
def create_chunks_and_send(data: pd.DataFrame,filename):
output_dir=Path('./output')
embeddings_dir = output_dir / 'embeddings' / filename
if embeddings_dir.exists():
chunks_file = embeddings_dir / "chunks.json"
if chunks_file.is_file():
with open(chunks_file, "r", encoding="utf-8") as f:
chunks = json.load(f)
return chunks
#print("File content as list:", chunks)
else:
print("chunks.json does not exist in the directory.")
else:
embeddings_dir.mkdir(parents=True, exist_ok=True)
embedding_manager = EmbeddingManager(output_dir=Path('./output'))
text = data.to_json()
chunks, embedding_dir = embedding_manager.process_script(data=str(text),filename=filename)
return chunks
def main():
st.title("Excel Chatbot")
query = st.text_input("Enter the query")
# File upload
uploaded_file = st.file_uploader("Upload Excel File", type=['xlsx', 'xls'])
if uploaded_file and query:
try:
# Read Excel file
df = pd.read_excel(uploaded_file)
st.success("File uploaded successfully!")
# Show data preview
st.subheader("Data Preview")
st.dataframe(df)
with st.spinner("Generating response with Claude..."):
# Initialize Claude client
## use the out put embeddings saved
data = create_chunks_and_send(df,uploaded_file.name)
# Get complete HTML report from Claude
response = send_to_llm(user_query=query,data=data,df=df)
# Get the HTML content (ensure it's a string)
html_report = response
st.components.v1.html(html_report, height=800, scrolling=True)
st.success("Report generated successfully! Click the link above to download.")
except Exception as e:
st.error(f"An error occurred: {str(e)}")
#st.error("Please check your API key and file format, then try again.")
if __name__ == "__main__":
main()