Update app.py
Browse files
app.py
CHANGED
|
@@ -1,17 +1,22 @@
|
|
| 1 |
import os
|
| 2 |
import gradio as gr
|
| 3 |
from dotenv import load_dotenv
|
|
|
|
|
|
|
|
|
|
| 4 |
|
| 5 |
# --- RAG Libraries ---
|
| 6 |
-
# Removed: PyPDFLoader, TextLoader, Docx2txtLoader
|
| 7 |
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
| 8 |
-
from langchain_google_genai import GoogleGenerativeAIEmbeddings, ChatGoogleGenerativeAI
|
| 9 |
from langchain.chains import RetrievalQA
|
| 10 |
from langchain.prompts import PromptTemplate
|
| 11 |
-
from langchain.schema import Document
|
| 12 |
|
| 13 |
-
#
|
| 14 |
-
import
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
# Load environment variables (for API keys when running locally)
|
| 17 |
load_dotenv()
|
|
@@ -19,9 +24,8 @@ load_dotenv()
|
|
| 19 |
# --- RAG Setup ---
|
| 20 |
rag_initialized = False
|
| 21 |
try:
|
| 22 |
-
# --- Use Google Gemini Models ---
|
| 23 |
embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
|
| 24 |
-
llm = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.7)
|
| 25 |
rag_initialized = True
|
| 26 |
print("Google Gemini embeddings and LLM initialized successfully.")
|
| 27 |
except Exception as e:
|
|
@@ -31,11 +35,12 @@ except Exception as e:
|
|
| 31 |
print("RAG functionality will not work without a valid Google API key.")
|
| 32 |
|
| 33 |
|
| 34 |
-
def
|
| 35 |
"""
|
| 36 |
-
Loads and returns text from Excel or CSV files,
|
|
|
|
| 37 |
"""
|
| 38 |
-
print(f"Attempting to load
|
| 39 |
documents = []
|
| 40 |
|
| 41 |
if file_extension in ['.xlsx', '.xls']:
|
|
@@ -43,126 +48,412 @@ def get_document_content(file_path, file_extension, filename):
|
|
| 43 |
df = pd.read_excel(file_path)
|
| 44 |
print(f"Excel file '{filename}' loaded with {len(df)} rows.")
|
| 45 |
except Exception as e:
|
| 46 |
-
raise ValueError(f"Could not process Excel file '{filename}': {e}")
|
| 47 |
elif file_extension == '.csv':
|
| 48 |
try:
|
| 49 |
df = pd.read_csv(file_path)
|
| 50 |
print(f"CSV file '{filename}' loaded with {len(df)} rows.")
|
| 51 |
except Exception as e:
|
| 52 |
-
raise ValueError(f"Could not process CSV file '{filename}': {e}")
|
| 53 |
else:
|
| 54 |
-
|
| 55 |
-
|
|
|
|
|
|
|
| 56 |
|
| 57 |
-
#
|
| 58 |
-
# This loop applies to both Excel and CSV dataframes
|
| 59 |
for index, row in df.iterrows():
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
# For more readable context, you might pick specific columns or format:
|
| 63 |
-
# doc_content = f"Row {index+1} from '{filename}': " + ", ".join([f"{col}: {val}" for col, val in row.items() if pd.notna(val)])
|
| 64 |
-
doc_content = f"Row {index+1} from '{filename}': {row.to_json()}"
|
| 65 |
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
|
| 71 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
return documents
|
| 73 |
|
| 74 |
-
|
|
|
|
|
|
|
|
|
|
| 75 |
"""
|
| 76 |
-
|
|
|
|
| 77 |
"""
|
|
|
|
|
|
|
| 78 |
if not rag_initialized:
|
| 79 |
-
|
|
|
|
| 80 |
|
| 81 |
if file is None:
|
| 82 |
-
|
|
|
|
|
|
|
|
|
|
| 83 |
if not query.strip():
|
| 84 |
-
|
| 85 |
|
| 86 |
file_path = file.name
|
| 87 |
filename = os.path.basename(file_path)
|
| 88 |
file_extension = os.path.splitext(filename)[1].lower()
|
| 89 |
|
| 90 |
try:
|
| 91 |
-
|
| 92 |
-
documents = get_document_content(file_path, file_extension, filename)
|
| 93 |
|
| 94 |
-
# 2. Split Text (even Excel rows can be split further if they are long)
|
| 95 |
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
|
| 96 |
texts = text_splitter.split_documents(documents)
|
| 97 |
-
|
| 98 |
-
|
| 99 |
if not texts:
|
| 100 |
-
|
|
|
|
| 101 |
|
| 102 |
-
#
|
| 103 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 104 |
vectorstore = FAISS.from_documents(texts, embeddings)
|
| 105 |
-
print("Vector store created successfully.")
|
| 106 |
|
| 107 |
-
# 4. Set up RetrievalQA Chain with Custom Prompt
|
| 108 |
template = """
|
| 109 |
-
You are an expert
|
| 110 |
-
|
| 111 |
-
|
| 112 |
-
|
| 113 |
-
|
| 114 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 115 |
Do not make up information.
|
| 116 |
|
| 117 |
-
Context:
|
| 118 |
{context}
|
| 119 |
|
| 120 |
Question: {question}
|
| 121 |
|
| 122 |
-
Your detailed
|
| 123 |
"""
|
| 124 |
QA_CHAIN_PROMPT = PromptTemplate.from_template(template)
|
| 125 |
|
| 126 |
qa_chain = RetrievalQA.from_chain_type(
|
| 127 |
llm=llm,
|
| 128 |
chain_type="stuff",
|
| 129 |
-
retriever=vectorstore.as_retriever(),
|
| 130 |
chain_type_kwargs={"prompt": QA_CHAIN_PROMPT}
|
| 131 |
)
|
| 132 |
|
| 133 |
-
# 5. Get Answer
|
| 134 |
-
print(f"Running RAG query for: '{query}'")
|
| 135 |
result = qa_chain.run(query)
|
| 136 |
-
print(f"Analysis complete. Result length: {len(result)} characters.")
|
| 137 |
|
| 138 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 139 |
|
| 140 |
except ValueError as e:
|
| 141 |
-
|
| 142 |
-
return
|
| 143 |
except Exception as e:
|
| 144 |
-
|
| 145 |
-
|
| 146 |
-
|
| 147 |
-
|
| 148 |
-
# ---
|
| 149 |
-
|
| 150 |
-
|
| 151 |
-
|
| 152 |
-
|
| 153 |
-
|
| 154 |
-
|
| 155 |
-
|
| 156 |
-
|
| 157 |
-
|
| 158 |
-
|
| 159 |
-
|
| 160 |
-
|
| 161 |
-
)
|
| 162 |
-
|
| 163 |
-
|
| 164 |
-
|
| 165 |
-
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 166 |
|
| 167 |
# This block is for running the Gradio app locally.
|
| 168 |
if __name__ == "__main__":
|
|
@@ -172,4 +463,4 @@ if __name__ == "__main__":
|
|
| 172 |
print("RAG functionality will not work locally without it. Please set it in a .env file or your environment.")
|
| 173 |
print("Example: GOOGLE_API_KEY='your-gemini-api-key-here'")
|
| 174 |
print("="*80 + "\n")
|
| 175 |
-
|
|
|
|
| 1 |
import os
|
| 2 |
import gradio as gr
|
| 3 |
from dotenv import load_dotenv
|
| 4 |
+
import pandas as pd
|
| 5 |
+
from datetime import datetime
|
| 6 |
+
import io # For in-memory file operations
|
| 7 |
|
| 8 |
# --- RAG Libraries ---
|
|
|
|
| 9 |
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
| 10 |
+
from langchain_google_genai import GoogleGenerativeAIEmbeddings, ChatGoogleGenerativeAI
|
| 11 |
from langchain.chains import RetrievalQA
|
| 12 |
from langchain.prompts import PromptTemplate
|
| 13 |
+
from langchain.schema import Document
|
| 14 |
|
| 15 |
+
# --- File Generation Libraries ---
|
| 16 |
+
from fpdf import FPDF # For PDF
|
| 17 |
+
from docx import Document as DocxDocument # For Word
|
| 18 |
+
from docx.shared import Inches # For document formatting in Word
|
| 19 |
+
from docx.enum.text import WD_ALIGN_PARAGRAPH # For text alignment in Word
|
| 20 |
|
| 21 |
# Load environment variables (for API keys when running locally)
|
| 22 |
load_dotenv()
|
|
|
|
| 24 |
# --- RAG Setup ---
|
| 25 |
rag_initialized = False
|
| 26 |
try:
|
|
|
|
| 27 |
embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
|
| 28 |
+
llm = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.7)
|
| 29 |
rag_initialized = True
|
| 30 |
print("Google Gemini embeddings and LLM initialized successfully.")
|
| 31 |
except Exception as e:
|
|
|
|
| 35 |
print("RAG functionality will not work without a valid Google API key.")
|
| 36 |
|
| 37 |
|
| 38 |
+
def get_document_content_from_tickets(file_path, file_extension, filename):
|
| 39 |
"""
|
| 40 |
+
Loads and returns text from Excel or CSV files, treating each row as a customer ticket.
|
| 41 |
+
Dynamically reads all columns and includes them in the document content.
|
| 42 |
"""
|
| 43 |
+
print(f"Attempting to load customer ticket data: {filename} with extension {file_extension}")
|
| 44 |
documents = []
|
| 45 |
|
| 46 |
if file_extension in ['.xlsx', '.xls']:
|
|
|
|
| 48 |
df = pd.read_excel(file_path)
|
| 49 |
print(f"Excel file '{filename}' loaded with {len(df)} rows.")
|
| 50 |
except Exception as e:
|
| 51 |
+
raise ValueError(f"Could not process Excel file '{filename}': {e}. Ensure it's a valid Excel format for ticket data.")
|
| 52 |
elif file_extension == '.csv':
|
| 53 |
try:
|
| 54 |
df = pd.read_csv(file_path)
|
| 55 |
print(f"CSV file '{filename}' loaded with {len(df)} rows.")
|
| 56 |
except Exception as e:
|
| 57 |
+
raise ValueError(f"Could not process CSV file '{filename}': {e}. Ensure it's a valid CSV format for ticket data.")
|
| 58 |
else:
|
| 59 |
+
raise ValueError(f"Unsupported file type: {file_extension}. Only .xlsx, .xls, or .csv files are accepted for ticket data.")
|
| 60 |
+
|
| 61 |
+
if df.empty:
|
| 62 |
+
raise ValueError("The uploaded file contains no data or no rows could be parsed.")
|
| 63 |
|
| 64 |
+
# Dynamically include all non-empty column data in the document content
|
|
|
|
| 65 |
for index, row in df.iterrows():
|
| 66 |
+
ticket_content_parts = []
|
| 67 |
+
ticket_id = f"Row {index+1}" # Default ticket ID
|
|
|
|
|
|
|
|
|
|
| 68 |
|
| 69 |
+
for col_name, value in row.items():
|
| 70 |
+
if pd.notna(value) and str(value).strip() != '': # Check for NaN and empty strings
|
| 71 |
+
formatted_col_name = col_name.replace('_', ' ').title() # Make column names readable
|
| 72 |
+
ticket_content_parts.append(f"{formatted_col_name}: {value}")
|
| 73 |
+
|
| 74 |
+
# Try to capture a good ticket ID or issue description from common columns
|
| 75 |
+
if col_name.lower() in ['ticketid', 'ticket_id', 'id']:
|
| 76 |
+
ticket_id = value
|
| 77 |
+
elif col_name.lower() in ['issue', 'description', 'problem'] and len(str(value)) > 10: # Ensure it's a substantive description
|
| 78 |
+
pass # Issue will be in ticket_content_parts
|
| 79 |
+
|
| 80 |
+
if not ticket_content_parts:
|
| 81 |
+
raise ValueError(f"Row {index+1} from '{filename}' has no detectable content.")
|
| 82 |
+
|
| 83 |
+
ticket_content = "\n".join(ticket_content_parts)
|
| 84 |
+
|
| 85 |
+
# Store all row data in metadata for potential advanced RAG (though not used directly in prompt here)
|
| 86 |
+
metadata = {"source": filename, "ticket_row_number": index+1, "ticket_id": ticket_id}
|
| 87 |
+
metadata.update(row.to_dict()) # Add all columns to metadata
|
| 88 |
|
| 89 |
+
documents.append(Document(page_content=ticket_content, metadata=metadata))
|
| 90 |
+
|
| 91 |
+
if not documents:
|
| 92 |
+
raise ValueError("No usable ticket data extracted from the document.")
|
| 93 |
+
|
| 94 |
+
print(f"File '{filename}' processed into {len(documents)} Langchain Documents (one per ticket).")
|
| 95 |
return documents
|
| 96 |
|
| 97 |
+
# Global variable to store the last analysis result for download
|
| 98 |
+
last_analysis_result_text = ""
|
| 99 |
+
|
| 100 |
+
def perform_ticket_analysis(file, query):
|
| 101 |
"""
|
| 102 |
+
Main function to analyze customer tickets using RAG.
|
| 103 |
+
Updates a global variable with the result for download functions.
|
| 104 |
"""
|
| 105 |
+
global last_analysis_result_text # Declare global to modify it
|
| 106 |
+
|
| 107 |
if not rag_initialized:
|
| 108 |
+
last_analysis_result_text = "RAG system not initialized. Please ensure your **GOOGLE_API_KEY** is configured correctly in Hugging Face Space secrets."
|
| 109 |
+
return last_analysis_result_text
|
| 110 |
|
| 111 |
if file is None:
|
| 112 |
+
last_analysis_result_text = "Please upload a customer ticket file."
|
| 113 |
+
return last_analysis_result_text
|
| 114 |
+
|
| 115 |
+
# Default comprehensive analysis if query is empty
|
| 116 |
if not query.strip():
|
| 117 |
+
query = "Perform a comprehensive analysis of the tickets. Provide categorization, sub-categories, count of issues, detailed description of issues, infer the root cause, suggest potential resolution steps, identify future prediction, and propose proactive measures."
|
| 118 |
|
| 119 |
file_path = file.name
|
| 120 |
filename = os.path.basename(file_path)
|
| 121 |
file_extension = os.path.splitext(filename)[1].lower()
|
| 122 |
|
| 123 |
try:
|
| 124 |
+
documents = get_document_content_from_tickets(file_path, file_extension, filename)
|
|
|
|
| 125 |
|
|
|
|
| 126 |
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
|
| 127 |
texts = text_splitter.split_documents(documents)
|
| 128 |
+
|
|
|
|
| 129 |
if not texts:
|
| 130 |
+
last_analysis_result_text = "No usable text extracted from the ticket data after splitting."
|
| 131 |
+
return last_analysis_result_text
|
| 132 |
|
| 133 |
+
# Using FAISS for vector store (ensure it's imported or handled)
|
| 134 |
+
try:
|
| 135 |
+
from langchain_community.vectorstores import FAISS # Import FAISS if not already
|
| 136 |
+
except ImportError:
|
| 137 |
+
# Fallback for older langchain versions or if FAISS not in langchain_community
|
| 138 |
+
from langchain.vectorstores import FAISS # Fallback
|
| 139 |
+
|
| 140 |
vectorstore = FAISS.from_documents(texts, embeddings)
|
|
|
|
| 141 |
|
|
|
|
| 142 |
template = """
|
| 143 |
+
You are an expert customer support ticket analyst. Your goal is to provide a comprehensive analysis of customer tickets
|
| 144 |
+
based *only* on the provided context. The context contains individual customer tickets, each representing a row
|
| 145 |
+
from a data file. Each row contains various columns and their values.
|
| 146 |
+
|
| 147 |
+
Analyze the tickets to address the user's query. If the query asks for a general analysis,
|
| 148 |
+
provide the following structured insights. If a specific detail (like root cause) cannot be inferred from the available ticket data,
|
| 149 |
+
state 'Undetermined' or 'N/A'.
|
| 150 |
+
|
| 151 |
+
**Desired Output Format (Markdown Table):**
|
| 152 |
+
| Category | Sub-Category | Count | Issue Description (Summary) | Root Cause (Inferred) | Potential Resolution Steps | Future Prediction | Proactive Measures |
|
| 153 |
+
|---|---|---|---|---|---|---|---|
|
| 154 |
+
| ... | ... | ... | ... | ... | ... | ... | ... |
|
| 155 |
+
|
| 156 |
+
If the query is specific and doesn't require all columns, answer directly.
|
| 157 |
+
If the information is not present in the provided tickets, state that clearly.
|
| 158 |
Do not make up information.
|
| 159 |
|
| 160 |
+
Context (Customer Tickets):
|
| 161 |
{context}
|
| 162 |
|
| 163 |
Question: {question}
|
| 164 |
|
| 165 |
+
Your detailed ticket analysis:
|
| 166 |
"""
|
| 167 |
QA_CHAIN_PROMPT = PromptTemplate.from_template(template)
|
| 168 |
|
| 169 |
qa_chain = RetrievalQA.from_chain_type(
|
| 170 |
llm=llm,
|
| 171 |
chain_type="stuff",
|
| 172 |
+
retriever=vectorstore.as_retriever(k=10), # Retrieve more chunks for better context
|
| 173 |
chain_type_kwargs={"prompt": QA_CHAIN_PROMPT}
|
| 174 |
)
|
| 175 |
|
|
|
|
|
|
|
| 176 |
result = qa_chain.run(query)
|
|
|
|
| 177 |
|
| 178 |
+
disclaimer = "\n\n**Note:** 'Root Cause', 'Future Prediction', and 'Proactive Measures' are AI-inferred based on descriptions provided. For critical decisions, human expert review is essential."
|
| 179 |
+
final_result = result + disclaimer
|
| 180 |
+
|
| 181 |
+
last_analysis_result_text = final_result # Store the result
|
| 182 |
+
return final_result
|
| 183 |
|
| 184 |
except ValueError as e:
|
| 185 |
+
last_analysis_result_text = f"Ticket Analysis Error: {e}"
|
| 186 |
+
return last_analysis_result_text
|
| 187 |
except Exception as e:
|
| 188 |
+
last_analysis_result_text = f"An unexpected error occurred during analysis: {e}. Check logs for details."
|
| 189 |
+
print(f"Error: {e}")
|
| 190 |
+
return last_analysis_result_text
|
| 191 |
+
|
| 192 |
+
# --- Output Download Functions ---
|
| 193 |
+
|
| 194 |
+
def generate_pdf_report(markdown_text):
|
| 195 |
+
if not markdown_text or "RAG system not initialized" in markdown_text or "Error:" in markdown_text:
|
| 196 |
+
return None # Return None if no valid text to generate
|
| 197 |
+
|
| 198 |
+
pdf = FPDF()
|
| 199 |
+
pdf.add_page()
|
| 200 |
+
pdf.set_font("Arial", size=12)
|
| 201 |
+
|
| 202 |
+
# Add a title
|
| 203 |
+
pdf.set_font("Arial", 'B', 16)
|
| 204 |
+
pdf.cell(0, 10, "AI Customer Ticket Analysis Report", ln=True, align='C')
|
| 205 |
+
pdf.ln(5) # Line break
|
| 206 |
+
|
| 207 |
+
# Add timestamp
|
| 208 |
+
pdf.set_font("Arial", size=10)
|
| 209 |
+
pdf.cell(0, 10, f"Generated on: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}", ln=True, align='R')
|
| 210 |
+
pdf.ln(5)
|
| 211 |
+
|
| 212 |
+
pdf.set_font("Arial", size=12)
|
| 213 |
+
# Simple parsing for markdown: bold, italics, paragraphs
|
| 214 |
+
# This won't perfectly render markdown tables, but will output text.
|
| 215 |
+
# For full markdown rendering, you'd need a more advanced library or HTML conversion.
|
| 216 |
+
lines = markdown_text.split('\n')
|
| 217 |
+
for line in lines:
|
| 218 |
+
line = line.replace('**', '').replace('*', '') # Remove bold/italics for simple text
|
| 219 |
+
if line.strip().startswith('|') and '|---' not in line: # Basic table line detection
|
| 220 |
+
pdf.multi_cell(0, 7, line)
|
| 221 |
+
elif line.strip() == '':
|
| 222 |
+
pdf.ln(5) # Add a larger line break for empty lines
|
| 223 |
+
else:
|
| 224 |
+
pdf.multi_cell(0, 7, line) # Use multi_cell for wrapping text
|
| 225 |
+
|
| 226 |
+
# Save to an in-memory buffer
|
| 227 |
+
pdf_output = io.BytesIO()
|
| 228 |
+
pdf.output(pdf_output)
|
| 229 |
+
pdf_output.seek(0)
|
| 230 |
+
|
| 231 |
+
file_name = f"ticket_analysis_report_{datetime.now().strftime('%Y%m%d_%H%M%S')}.pdf"
|
| 232 |
+
# Gradio expects a path, so we'll save it temporarily and return the path
|
| 233 |
+
temp_dir = os.path.join(os.getcwd(), "temp_files")
|
| 234 |
+
os.makedirs(temp_dir, exist_ok=True)
|
| 235 |
+
temp_file_path = os.path.join(temp_dir, file_name)
|
| 236 |
+
with open(temp_file_path, "wb") as f:
|
| 237 |
+
f.write(pdf_output.read())
|
| 238 |
+
return temp_file_path
|
| 239 |
+
|
| 240 |
+
|
| 241 |
+
def generate_docx_report(markdown_text):
|
| 242 |
+
if not markdown_text or "RAG system not initialized" in markdown_text or "Error:" in markdown_text:
|
| 243 |
+
return None # Return None if no valid text to generate
|
| 244 |
+
|
| 245 |
+
doc = DocxDocument()
|
| 246 |
+
|
| 247 |
+
# Add a title
|
| 248 |
+
doc.add_heading("AI Customer Ticket Analysis Report", level=1)
|
| 249 |
+
doc.add_paragraph(f"Generated on: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}", style='Intense Quote')
|
| 250 |
+
doc.add_paragraph("") # Blank line
|
| 251 |
+
|
| 252 |
+
# Add content
|
| 253 |
+
lines = markdown_text.split('\n')
|
| 254 |
+
is_in_table = False
|
| 255 |
+
table = None
|
| 256 |
+
header_row = []
|
| 257 |
+
|
| 258 |
+
for line in lines:
|
| 259 |
+
stripped_line = line.strip()
|
| 260 |
+
|
| 261 |
+
if stripped_line.startswith('|') and '|---' not in stripped_line:
|
| 262 |
+
# It's a table row
|
| 263 |
+
cells_data = [cell.strip() for cell in stripped_line.strip('|').split('|')]
|
| 264 |
+
|
| 265 |
+
if not is_in_table: # First row of a table
|
| 266 |
+
is_in_table = True
|
| 267 |
+
table = doc.add_table(rows=1, cols=len(cells_data))
|
| 268 |
+
table.style = 'Table Grid' # Apply a table style
|
| 269 |
+
hdr_cells = table.rows[0].cells
|
| 270 |
+
for i, text in enumerate(cells_data):
|
| 271 |
+
hdr_cells[i].text = text
|
| 272 |
+
header_row.append(text) # Store header for reference
|
| 273 |
+
else: # Subsequent row in table
|
| 274 |
+
if len(cells_data) == len(header_row): # Ensure consistent columns
|
| 275 |
+
row_cells = table.add_row().cells
|
| 276 |
+
for i, text in enumerate(cells_data):
|
| 277 |
+
row_cells[i].text = text
|
| 278 |
+
else: # Fallback if table structure is inconsistent, add as paragraph
|
| 279 |
+
doc.add_paragraph(line)
|
| 280 |
+
elif '|---' in stripped_line: # Table separator line
|
| 281 |
+
continue # Skip this line
|
| 282 |
+
else:
|
| 283 |
+
if is_in_table: # End of table
|
| 284 |
+
is_in_table = False
|
| 285 |
+
table = None
|
| 286 |
+
header_row = []
|
| 287 |
+
doc.add_paragraph("") # Add a space after table
|
| 288 |
+
|
| 289 |
+
# Regular paragraph
|
| 290 |
+
if stripped_line.startswith('**') and stripped_line.endswith('**'):
|
| 291 |
+
p = doc.add_paragraph()
|
| 292 |
+
p.add_run(stripped_line.strip('**')).bold = True
|
| 293 |
+
elif stripped_line.startswith('*') or stripped_line.startswith('-'):
|
| 294 |
+
# Basic list item
|
| 295 |
+
doc.add_paragraph(stripped_line, style='List Bullet')
|
| 296 |
+
else:
|
| 297 |
+
doc.add_paragraph(stripped_line)
|
| 298 |
+
|
| 299 |
+
# Save to an in-memory buffer
|
| 300 |
+
docx_output = io.BytesIO()
|
| 301 |
+
doc.save(docx_output)
|
| 302 |
+
docx_output.seek(0)
|
| 303 |
+
|
| 304 |
+
file_name = f"ticket_analysis_summary_{datetime.now().strftime('%Y%m%d_%H%M%S')}.docx"
|
| 305 |
+
temp_dir = os.path.join(os.getcwd(), "temp_files")
|
| 306 |
+
os.makedirs(temp_dir, exist_ok=True)
|
| 307 |
+
temp_file_path = os.path.join(temp_dir, file_name)
|
| 308 |
+
with open(temp_file_path, "wb") as f:
|
| 309 |
+
f.write(docx_output.read())
|
| 310 |
+
return temp_file_path
|
| 311 |
+
|
| 312 |
+
|
| 313 |
+
# --- Gradio Interface Setup (using gr.Blocks for complex layout) ---
|
| 314 |
+
|
| 315 |
+
# --- Sample Data (same as previous response, ensure these files are uploaded to your space) ---
|
| 316 |
+
# 'sample_customer_tickets_minimal.csv'
|
| 317 |
+
# 'sample_customer_tickets_full.csv'
|
| 318 |
+
example_data = [
|
| 319 |
+
["sample_customer_tickets_minimal.csv", "Provide a comprehensive analysis of the tickets, focusing on common issues."],
|
| 320 |
+
["sample_customer_tickets_full.csv", "Summarize high-priority open issues, their root causes, and suggest proactive measures."],
|
| 321 |
+
["sample_customer_tickets_full.csv", "Categorize all tickets by their primary issue type and count them."],
|
| 322 |
+
]
|
| 323 |
+
|
| 324 |
+
with gr.Blocks(theme=gr.themes.Soft(), css="""
|
| 325 |
+
.gradio-container { max-width: 900px; margin: auto; padding: 20px; box-shadow: 0 4px 8px rgba(0,0,0,0.1); border-radius: 10px; }
|
| 326 |
+
h1, h2, h3, h4, h5, h6 { color: #3F51B5; }
|
| 327 |
+
p { line-height: 1.6; }
|
| 328 |
+
.gr-button { background-color: #4CAF50; color: white; border-radius: 5px; }
|
| 329 |
+
.gr-textarea, .gr-file { border-radius: 5px; border: 1px solid #ddd; }
|
| 330 |
+
.gradio-container .gr-button:hover { background-color: #45a049; }
|
| 331 |
+
#download-buttons { display: flex; justify-content: center; gap: 10px; margin-top: 15px; }
|
| 332 |
+
.download-button { flex-grow: 1; max-width: 200px; }
|
| 333 |
+
""") as demo:
|
| 334 |
+
gr.HTML("""
|
| 335 |
+
<h1 align="center">π΅οΈββοΈ Advanced AI Customer Ticket Analyst π΅οΈββοΈ</h1>
|
| 336 |
+
<p align="center">Unlock deep insights from your customer support data with Gemini RAG!</p>
|
| 337 |
+
""")
|
| 338 |
+
|
| 339 |
+
gr.Markdown(
|
| 340 |
+
"""
|
| 341 |
+
### Welcome to the Advanced AI Customer Ticket Analyst! π
|
| 342 |
+
This powerful tool leverages **Retrieval-Augmented Generation (RAG)** with **Google Gemini** to provide detailed, structured insights from your customer support tickets.
|
| 343 |
+
Upload your Excel or CSV file and ask a specific question, or leave the query blank for a **comprehensive analysis** including categorization, root causes, predictions, and proactive measures.
|
| 344 |
+
|
| 345 |
+
---
|
| 346 |
+
|
| 347 |
+
#### **<span style="color: #FF9800;">π‘ Important Note on AI Inferences:</span>**
|
| 348 |
+
The 'Root Cause', 'Future Prediction', and 'Proactive Measures' are **AI-inferred** based on the descriptions provided in your tickets. These are educated guesses by the AI and should be used for **guidance only**. For critical business decisions, human expert validation is highly recommended.
|
| 349 |
+
|
| 350 |
+
---
|
| 351 |
+
|
| 352 |
+
#### **<span style="color: #4CAF50;">π’ Input File Prerequisites & Guidance:</span>**
|
| 353 |
+
* **Supported Formats:** Only `.xlsx` (Excel), `.xls` (Legacy Excel), and `.csv` (Comma Separated Values) files are accepted.
|
| 354 |
+
* **Data Structure:** Your file must contain **tabular data with clear headers in the first row**. Each row is processed as an individual customer ticket.
|
| 355 |
+
* **Dynamic Column Reading:** The tool will attempt to read **ALL** columns present in your file. Ensure column headers are clear and meaningful.
|
| 356 |
+
* **Minimum Columns:** A **minimum of two columns are highly recommended**: one for a unique `Ticket ID` (or `ID`) and one for the `Issue` (or `Description`).
|
| 357 |
+
* **Recommended Columns:** For richer analysis, include columns like `Status`, `Priority`, `CustomerName`, `Timestamp`, etc. The more relevant details provided, the better the AI's inferences.
|
| 358 |
+
* **Size Recommendation:** For optimal performance on the free tier, we recommend files with up to **~1000 rows**. Larger files might experience slower processing or hit API rate limits.
|
| 359 |
+
* **Privacy:** **DO NOT upload sensitive or confidential customer information.** This is a publicly hosted demo.
|
| 360 |
+
|
| 361 |
+
---
|
| 362 |
+
|
| 363 |
+
#### **<span style="color: #2196F3;">π΅ Expected Analysis Output:</span>**
|
| 364 |
+
The AI will provide a **clear, actionable, and data-driven answer** based *only* on the information present in your uploaded ticket file.
|
| 365 |
+
If you ask for a comprehensive analysis (or leave the query blank), the output will strive to be in a **Markdown Table format** with the following columns:
|
| 366 |
+
* **Category:** Broad classification (e.g., Network, Software, Billing).
|
| 367 |
+
* **Sub-Category:** More specific classification (e.g., Connectivity, Installation, Invoice Inquiry).
|
| 368 |
+
* **Count:** Number of tickets falling into this category/sub-category (if applicable to query).
|
| 369 |
+
* **Issue Description (Summary):** A concise summary of the issue(s).
|
| 370 |
+
* **Root Cause (Inferred):** The most likely underlying reason for the issue.
|
| 371 |
+
* **Potential Resolution Steps:** Actionable steps to resolve the issue.
|
| 372 |
+
* **Future Prediction:** What might happen if issues persist or aren't addressed.
|
| 373 |
+
* **Proactive Measures:** Steps to prevent similar issues in the future.
|
| 374 |
+
|
| 375 |
+
**<span style="color: #FF9800;">π‘ Sample Output Structure (from a comprehensive analysis):</span>**
|
| 376 |
+
```markdown
|
| 377 |
+
| Category | Sub-Category | Count | Issue Description (Summary) | Root Cause (Inferred) | Potential Resolution Steps | Future Prediction | Proactive Measures |
|
| 378 |
+
|-------------|--------------|-------|---------------------------------------------------|---------------------------------|--------------------------------------|-------------------------------------------|--------------------------------------|
|
| 379 |
+
| Network | Connectivity | 1 | Intermittent internet drops, not working. | Faulty router/ISP fluctuations | Router reboot, check ISP status | Increased customer frustration | Regular network diagnostics |
|
| 380 |
+
| Software | Installation | 1 | Software failed to install on startup. | Corrupt installer/conflicting app | Reinstall, check system logs | System instability, productivity loss | Pre-install checks, compatibility tests |
|
| 381 |
+
| Account | Billing | 1 | Customer inquiring about billing statement. | Unclear invoice/customer confusion | Explain statement, provide breakdown | Continued customer churn | Clearer billing statements, FAQs |
|
| 382 |
+
| Credentials | Email Access | 1 | Email access denied after password reset. | Sync issues/account lockouts | Manual account reset, guide user | Loss of critical communication | Automated account sync, better alerts |
|
| 383 |
+
| Hardware | Peripherals | 1 | Printer not responding to print commands. | Driver issue/connection problem | Reinstall driver, check connections | Reduced productivity, equipment downtime | Driver auto-updates, robust setup guide |
|
| 384 |
+
```
|
| 385 |
+
"""
|
| 386 |
+
)
|
| 387 |
+
|
| 388 |
+
with gr.Row():
|
| 389 |
+
file_input = gr.File(
|
| 390 |
+
label="Upload Customer Ticket Data (Excel or CSV)",
|
| 391 |
+
file_types=[".xlsx", ".xls", ".csv"],
|
| 392 |
+
type="filepath", # Use 'filepath' for temp file access
|
| 393 |
+
file_count="single",
|
| 394 |
+
interactive=True
|
| 395 |
+
)
|
| 396 |
+
query_input = gr.Textbox(
|
| 397 |
+
label="Your Analysis Request (Optional, leave blank for full analysis)",
|
| 398 |
+
placeholder="e.g., 'Summarize all high-priority issues' OR leave blank for a full analysis.",
|
| 399 |
+
lines=2,
|
| 400 |
+
interactive=True
|
| 401 |
+
)
|
| 402 |
+
|
| 403 |
+
submit_btn = gr.Button("Analyze Tickets", variant="primary")
|
| 404 |
+
|
| 405 |
+
output_text = gr.Textbox(
|
| 406 |
+
label="AI Ticket Analysis Result",
|
| 407 |
+
show_copy_button=True,
|
| 408 |
+
lines=15, # Increased lines for more comprehensive output
|
| 409 |
+
interactive=False,
|
| 410 |
+
)
|
| 411 |
+
|
| 412 |
+
with gr.Group(elem_id="download-buttons"): # Group buttons for styling
|
| 413 |
+
pdf_btn = gr.Button("Download as PDF Report", elem_classes="download-button")
|
| 414 |
+
docx_btn = gr.Button("Download as Word Document", elem_classes="download-button")
|
| 415 |
+
|
| 416 |
+
pdf_output_file = gr.File(label="Download PDF", visible=False)
|
| 417 |
+
docx_output_file = gr.File(label="Download Word Doc", visible=False)
|
| 418 |
+
|
| 419 |
+
# Event Handlers
|
| 420 |
+
submit_btn.click(
|
| 421 |
+
fn=perform_ticket_analysis,
|
| 422 |
+
inputs=[file_input, query_input],
|
| 423 |
+
outputs=output_text
|
| 424 |
+
)
|
| 425 |
+
|
| 426 |
+
pdf_btn.click(
|
| 427 |
+
fn=generate_pdf_report,
|
| 428 |
+
inputs=output_text, # Pass the content of the output_text box
|
| 429 |
+
outputs=pdf_output_file,
|
| 430 |
+
# After generating, show the download link
|
| 431 |
+
api_name="download_pdf" # Expose for potential external use
|
| 432 |
+
).then(
|
| 433 |
+
fn=lambda: gr.File(visible=True), # Make the file download component visible
|
| 434 |
+
inputs=[],
|
| 435 |
+
outputs=pdf_output_file
|
| 436 |
+
)
|
| 437 |
+
|
| 438 |
+
docx_btn.click(
|
| 439 |
+
fn=generate_docx_report,
|
| 440 |
+
inputs=output_text, # Pass the content of the output_text box
|
| 441 |
+
outputs=docx_output_file,
|
| 442 |
+
api_name="download_docx" # Expose for potential external use
|
| 443 |
+
).then(
|
| 444 |
+
fn=lambda: gr.File(visible=True), # Make the file download component visible
|
| 445 |
+
inputs=[],
|
| 446 |
+
outputs=docx_output_file
|
| 447 |
+
)
|
| 448 |
+
|
| 449 |
+
gr.Examples(
|
| 450 |
+
examples=example_data,
|
| 451 |
+
inputs=[file_input, query_input],
|
| 452 |
+
outputs=output_text, # Ensure examples populate the output text box too
|
| 453 |
+
fn=perform_ticket_analysis, # Call the analysis function when example is clicked
|
| 454 |
+
cache_examples=True, # Cache results for faster example loading
|
| 455 |
+
)
|
| 456 |
+
|
| 457 |
|
| 458 |
# This block is for running the Gradio app locally.
|
| 459 |
if __name__ == "__main__":
|
|
|
|
| 463 |
print("RAG functionality will not work locally without it. Please set it in a .env file or your environment.")
|
| 464 |
print("Example: GOOGLE_API_KEY='your-gemini-api-key-here'")
|
| 465 |
print("="*80 + "\n")
|
| 466 |
+
demo.launch()
|