File size: 9,535 Bytes
f55e54c 5db9e14 f55e54c b091835 f55e54c 9ffd2db f55e54c 9ffd2db f55e54c 9ffd2db f55e54c 9ffd2db f55e54c 7269a35 f55e54c |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 |
import os
import gradio as gr
import tempfile
from pathlib import Path
import base64
from PIL import Image
import io
import time
import sys
current_dir = os.path.dirname(os.path.abspath(__file__))
sys.path.append(current_dir)
# Import our components
from models.llm_setup import setup_llm
from indexes.csv_index_builder import EnhancedCSVReader
from indexes.index_manager import CSVIndexManager
from indexes.query_engine import CSVQueryEngine
# Try a different import approach for tools
tools_dir = os.path.join(current_dir, "tools")
sys.path.append(tools_dir)
from tools.data_tools import PandasDataTools
from tools.visualization import VisualizationTools
from tools.export import ExportTools
# Setup temporary directory for uploaded files
UPLOAD_DIR = Path(tempfile.mkdtemp())
EXPORT_DIR = Path(tempfile.mkdtemp())
class CSVChatApp:
"""Main application class for CSV chatbot."""
def __init__(self):
"""Initialize the application components."""
# Initialize the language model
self.llm = setup_llm()
# Initialize the index manager
self.index_manager = CSVIndexManager()
# Initialize tools
self.data_tools = PandasDataTools(str(UPLOAD_DIR))
self.viz_tools = VisualizationTools(str(UPLOAD_DIR))
self.export_tools = ExportTools(str(EXPORT_DIR))
# Initialize query engine with tools
self.query_engine = self._setup_query_engine()
# Track conversation history
self.chat_history = []
self.uploaded_files = []
def _setup_query_engine(self):
"""Set up the query engine with tools."""
# Get all tools
tools = (
self.data_tools.get_tools() +
self.viz_tools.get_tools() +
self.export_tools.get_tools()
)
# Create query engine with tools
query_engine = CSVQueryEngine(self.index_manager, self.llm)
return query_engine
def handle_file_upload(self, files):
"""Process uploaded CSV files."""
file_info = []
for file in files:
if file is None:
continue
# Get file path
file_path = Path(file.name)
# Only process CSV files
if not file_path.suffix.lower() == '.csv':
continue
# Copy to upload directory
dest_path = UPLOAD_DIR / file_path.name
with open(dest_path, 'wb') as f:
f.write(file_path.read_bytes())
# Create index for this file
try:
self.index_manager.create_index(str(dest_path))
file_info.append(f"✅ Indexed: {file_path.name}")
self.uploaded_files.append(str(dest_path))
except Exception as e:
file_info.append(f"❌ Failed to index {file_path.name}: {str(e)}")
# Return information about processed files
if file_info:
return "\n".join(file_info)
else:
return "No CSV files were uploaded."
# def process_query(self, query, history):
# """Process a user query and generate a response."""
# if not self.uploaded_files:
# return "Please upload CSV files before asking questions."
# # Add user message to history
# self.chat_history.append({"role": "user", "content": query})
# # Process the query
# try:
# response = self.query_engine.query(query)
# answer = response["answer"]
# # Check if response contains an image
# if isinstance(answer, dict) and "image" in answer:
# # Handle image in response
# img_data = answer["image"]
# img = Image.open(io.BytesIO(base64.b64decode(img_data)))
# img_path = EXPORT_DIR / f"viz_{int(time.time())}.png"
# img.save(img_path)
# # Update answer to include image path
# text_response = answer.get("text", "Generated visualization")
# answer = (text_response, str(img_path))
# # Add assistant message to history
# self.chat_history.append({"role": "assistant", "content": answer})
# return answer
# except Exception as e:
# error_msg = f"Error processing query: {str(e)}"
# self.chat_history.append({"role": "assistant", "content": error_msg})
# return error_msg
# In app.py, modify the process_query method:
def process_query(self, query, history):
"""Process a user query and generate a response."""
if not self.uploaded_files:
# Return in the correct format for the chatbot
return history + [[query, "Please upload CSV files before asking questions."]]
# Add user message to history
self.chat_history.append({"role": "user", "content": query})
# Process the query
try:
response = self.query_engine.query(query)
answer = response["answer"]
# Check if response contains an image
if isinstance(answer, dict) and "image" in answer:
# Handle image in response
img_data = answer["image"]
img = Image.open(io.BytesIO(base64.b64decode(img_data)))
img_path = EXPORT_DIR / f"viz_{int(time.time())}.png"
img.save(img_path)
# Update answer to include image path
text_response = answer.get("text", "Generated visualization")
answer = (text_response, str(img_path))
# Add assistant message to history
self.chat_history.append({"role": "assistant", "content": answer})
# Return in the correct format for the chatbot
return history + [[query, answer]]
except Exception as e:
error_msg = f"Error processing query: {str(e)}"
self.chat_history.append({"role": "assistant", "content": error_msg})
# Return in the correct format for the chatbot
return history + [[query, error_msg]]
def export_conversation(self):
"""Export the conversation as a report."""
if not self.chat_history:
return "No conversation to export."
# Extract content for report
title = "CSV Chat Conversation Report"
content = ""
images = []
for msg in self.chat_history:
role = msg["role"]
content_text = msg["content"]
# Handle content that might contain images
if isinstance(content_text, tuple) and len(content_text) == 2:
text, img_path = content_text
content += f"\n\n{'User' if role == 'user' else 'Assistant'}: {text}"
# Add image to report
try:
with open(img_path, "rb") as img_file:
img_data = base64.b64encode(img_file.read()).decode('utf-8')
images.append(img_data)
except Exception:
pass
else:
content += f"\n\n{'User' if role == 'user' else 'Assistant'}: {content_text}"
# Generate report
result = self.export_tools.generate_report(title, content, images)
if result["success"]:
return f"Report exported to: {result['report_path']}"
else:
return "Failed to export report."
# Create the Gradio interface
def create_interface():
"""Create the Gradio web interface."""
app = CSVChatApp()
with gr.Blocks(title="CSV Chat Assistant") as interface:
gr.Markdown("# CSV Chat Assistant")
gr.Markdown("Upload CSV files and ask questions in natural language.")
with gr.Row():
with gr.Column(scale=1):
file_upload = gr.File(
label="Upload CSV Files",
file_count="multiple",
type="filepath"
)
upload_button = gr.Button("Process Files")
file_status = gr.Textbox(label="File Status")
export_button = gr.Button("Export Conversation")
export_status = gr.Textbox(label="Export Status")
with gr.Column(scale=2):
chatbot = gr.Chatbot(label="Conversation")
msg = gr.Textbox(label="Your Question")
submit_button = gr.Button("Submit")
# Set up event handlers
upload_button.click(
fn=app.handle_file_upload,
inputs=[file_upload],
outputs=[file_status]
)
submit_button.click(
fn=app.process_query,
inputs=[msg, chatbot],
outputs=[chatbot]
)
export_button.click(
fn=app.export_conversation,
inputs=[],
outputs=[export_status]
)
return interface
# Launch the app
if __name__ == "__main__":
interface = create_interface()
interface.launch()
|