this is the qa agent from agents.baseagent import BaseAgent class QAAgent(BaseAgent):…
- User
this is the qa agent
from agents.base_agent import BaseAgent
class QAAgent(BaseAgent):
prompt_sys = "Expert in extracting all Questions and Answers from transcripts for Macy's CEO"
prompt_analyze = """
You are an expert in analyzing transcripts of earnings calls or business meetings. Your task is to carefully review the provided transcript and extract EVERY question and its corresponding answer EXACTLY as they appear, including the speaker information.
- Extract ALL Q&A pairs in the transcript
- For each pair, include:
- The EXACT question text
- The EXACT answer text
- The speaker who asked the question
- The speaker who answered the question
- The timestamp or sequence number of the Q&A
- Format each Q&A pair as:
Q[#]: [exact question text]
Asked by: [speaker name]
A: [exact answer text]
Answered by: [speaker name]
- Do not skip any questions, even if they seem minor
- Do not paraphrase or summarize - use the exact words from the transcript
- Include follow-up questions and responses
- Preserve any numerical data, percentages, or specific terms exactly as spoken
Transcript:
{text}
"""
prompt_summary = """
You are preparing a comprehensive Q&A report from multiple transcripts for Macy's executive team.
Organize the Q&A pairs by document and speaker. For each document:
1. List all Q&A pairs in the order they appeared
2. For each pair, include:
- The exact question and answer
- Speaker who asked
- Speaker who answered
3. Add a summary section highlighting:
- Most active speakers (who asked most questions)
- Key topics covered
- Most substantial responses
Format the entire report as follows:
# Document: [Document Name]
## Speaker: [Questioner Name]
### Q1: [Exact question text]
A: [Exact answer text]
Answered by: [Speaker Name]
### Q2: [Exact question text]
A: [Exact answer text]
Answered by: [Speaker Name]
## Summary:
- Total questions: [number]
- Most active questioner: [name] with [number] questions
- Key topics: [list of topics]
- Most substantial response: [brief description]
Use the following extracted data:
{topics_block}
Note: Maintain professional tone and preserve all exact wording from the transcripts.
"""
prompt_detail = prompt_analyze
def analyze_document(self, text, custom_prompt=None):
prompt_analyze = custom_prompt if custom_prompt else self.prompt_analyze
return super().analyze_document(self.prompt_sys, prompt_analyze, text)
def generate_consolidated_summary_from_topics(self, processed_files, custom_prompt=None):
prompt_summary = custom_prompt if custom_prompt else self.prompt_summary
return super().generate_consolidated_summary_from_topics(self.prompt_sys, prompt_summary, processed_files)
agents/qa_agent.py
agents/qa_agent.py
agents/qa_agent.py
from agents.base_agent import BaseAgent
class QAAgent(BaseAgent): prompt_sys = "Expert in extracting all Questions and Answers from transcripts for Macy's CEO"
prompt_analyze = """You are an expert in analyzing transcripts of earnings calls or business meetings. Your task is to carefully review the provided transcript and extract EVERY question and its corresponding answer EXACTLY as they appear, including the speaker information.
-
Focus specifically on the QUESTION AND ANSWER SECTION of the document
-
Extract ALL Q&A pairs in this section without exception
-
For each pair, include:
- The EXACT question text
- The EXACT answer text
- The speaker who asked the question
- The speaker who answered the question
-
Format each Q&A pair as: Q[#]: [exact question text] Asked by: [speaker name] A: [exact answer text] Answered by: [speaker name]
-
Do not skip any questions - capture 100% of questions in the Q&A section
-
Do not paraphrase or summarize - use the exact words from the transcript
-
Include follow-up questions and responses
-
Preserve any numerical data, percentages, or specific terms exactly as spoken
-
Ensure complete coverage of all questions regardless of length or importance
Transcript: {text} """
prompt_summary = """You are preparing a comprehensive Q&A report from multiple transcripts for Macy's executive team.
For each document, list ALL Q&A pairs in the exact order they appeared in the QUESTION AND ANSWER SECTION.
Format the entire report as follows:
Document: [Document Name]
Q1: [Exact question text]
A: [Exact answer text]
Asked by: [Speaker Name] | Answered by: [Speaker Name]Q2: [Exact question text]
A: [Exact answer text]
Asked by: [Speaker Name] | Answered by: [Speaker Name][... continue for all questions ...]
Do NOT add any summary section, analysis, or commentary. Only list the exact Q&A pairs.
Use the following extracted data: {topics_block}
Note: Maintain professional tone and preserve all exact wording from the transcripts. """
prompt_detail = prompt_analyze def analyze_document(self, text, custom_prompt=None): prompt_analyze = custom_prompt if custom_prompt else self.prompt_analyze return super().analyze_document(self.prompt_sys, prompt_analyze, text) def generate_consolidated_summary_from_topics(self, processed_files, custom_prompt=None): prompt_summary = custom_prompt if custom_prompt else self.prompt_summary return super().generate_consolidated_summary_from_topics(self.prompt_sys, prompt_summary, processed_files)this is my main.py
import streamlit as st
from io import BytesIO
from datetime import datetime
# Assuming these are correctly defined and accessible
from utils.pdf_utils import extract_text
from clients.azure_client import AzureClient
from clients.gemini_client import GeminiClient
from agents.tariff_agent import TariffTradeAgent
from agents.sales_agent import SalesAgent
from agents.supply_chain_agent import SupplyChainAgent
from agents.overall_agent import OverallAgent
from agents.enhanced_chat_agent import EnhancedChatAgent
def analyze_documents(mode, agent, processed_files, sess, custom_prompt=None):
# Process individual files
for filename, file_bytes in sess['uploaded_files'].items():
if filename not in processed_files:
try:
file_obj = BytesIO(file_bytes)
file_obj.name = filename
text = extract_text(file_obj)
if text:
if mode == "overall":
topics = agent.analyze_document(text, custom_prompt)
else:
topics = agent.analyze_document(text, custom_prompt) # Pass custom_prompt to other agents too
processed_files[filename] = {
"text": text,
"topics": topics,
"context": text,
}
st.toast(f"✅ Processed {filename}")
else:
st.error(f"❌ Failed to extract text for {filename}")
except Exception as e:
st.error(f"Error processing {filename}: {str(e)}")
# Generate consolidated summary
if mode == "overall":
summary = agent.generate_consolidated_summary_from_topics(processed_files, custom_prompt)
else:
summary = agent.generate_consolidated_summary_from_topics(processed_files, custom_prompt) # Pass custom_prompt
if mode == "overall":
sess['consolidated_summary_overall'] = summary
elif mode == "tariff":
sess['consolidated_summary_tariff'] = summary
elif mode == "sales":
sess['consolidated_summary_sales'] = summary
elif mode == "supplychain":
sess['consolidated_summary_supplychain'] = summary
sess['last_analysis_mode'] = mode
sess['active_file'] = None
sess['active_topic'] = None
st.success(f"Analysis and summary generated for {mode.replace('supplychain', 'supply chain')}.")
def main():
st.set_page_config(page_title="Macy's Document Analysis Pro", layout="wide")
st.title("📄 Macy's Document Analysis & Chat Tool")
# Mode selection
provider_select = st.radio("Select AI Provider", ["Azure GPT", "Google Gemini"])
# Session Initialization
if "session" not in st.session_state:
st.session_state.session = {
'uploaded_files': {},
'processed_files_overall': {},
'processed_files_tariff': {},
'processed_files_sales': {},
'processed_files_supplychain': {},
'active_file': None,
'active_topic': None,
'topic_details_cache': {},
'chat_history': [],
'consolidated_summary_overall': None,
'consolidated_summary_tariff': None,
'consolidated_summary_sales': None,
'consolidated_summary_supplychain': None,
'last_analysis_mode': None,
'custom_prompt_enabled': {}, # New: To track if custom prompt is enabled for each mode
'custom_prompt_text': {} # New: To store custom prompt text for each mode
}
if "client" not in st.session_state or st.session_state.get("provider") != provider_select:
if provider_select == "Azure GPT":
st.session_state.client = AzureClient()
is_azure = True
else:
st.session_state.client = GeminiClient()
is_azure = False
# Initialize agents
st.session_state.agent_overall = OverallAgent(st.session_state.client, is_azure)
st.session_state.agent_tariff = TariffTradeAgent(st.session_state.client, is_azure)
st.session_state.agent_sales = SalesAgent(st.session_state.client, is_azure)
st.session_state.agent_supplychain = SupplyChainAgent(st.session_state.client, is_azure)
st.session_state.chat_agent = EnhancedChatAgent(st.session_state.client, is_azure)
st.session_state.provider = provider_select
sess = st.session_state.session
# --- File Upload ---
st.subheader("1. Upload Documents")
uploaded_files = st.file_uploader(
"Upload PDF documents",
type=["pdf"],
accept_multiple_files=True,
key="file_uploader",
)
if uploaded_files:
new_files_added = False
for file in uploaded_files:
if file.name not in sess['uploaded_files']:
sess['uploaded_files'][file.name] = file.getvalue()
new_files_added = True
if new_files_added:
with st.spinner("🔍 Analyzing new documents with Overall Agent..."):
# Always run initial overall analysis for new files
analyze_documents(
mode="overall",
agent=st.session_state.agent_overall,
processed_files=sess['processed_files_overall'],
sess=sess
)
# --- Custom Prompts & Analysis ---
st.subheader("2. Custom Prompts & Analysis")
# Initialize custom prompts in session state
if 'custom_prompts' not in sess:
sess['custom_prompts'] = {
'overall': {
'summary': OverallAgent.prompt_summary,
'analyze': OverallAgent.prompt_analyze,
'detail': OverallAgent.prompt_detail
},
'tariff': {
'summary': TariffTradeAgent.prompt_summary,
'analyze': TariffTradeAgent.prompt_analyze,
'detail': TariffTradeAgent.prompt_detail
},
'sales': {
'summary': SalesAgent.prompt_summary,
'analyze': SalesAgent.prompt_analyze,
'detail': SalesAgent.prompt_detail
},
'supplychain': {
'summary': SupplyChainAgent.prompt_summary,
'analyze': SupplyChainAgent.prompt_analyze,
'detail': SupplyChainAgent.prompt_detail
}
}
# Create tabs for each agent's custom prompts
tab_overall, tab_tariff, tab_sales, tab_supply = st.tabs([
"📑 Overall", "🔍 Tariff", "📈 Sales", "🚚 Supply Chain"
])
# Store which mode we're generating for
generate_mode = None
with tab_overall:
st.subheader("Overall Prompts")
use_custom = st.checkbox("✏️ Use Custom Prompts", key="custom_overall")
if use_custom:
sess['custom_prompts']['overall']['summary'] = st.text_area(
"Summary Prompt:",
value=sess['custom_prompts']['overall']['summary'],
height=150,
key="overall_prompt_summary"
)
sess['custom_prompts']['overall']['analyze'] = st.text_area(
"Analysis Prompt:",
value=sess['custom_prompts']['overall']['analyze'],
height=150,
key="overall_prompt_analyze"
)
sess['custom_prompts']['overall']['detail'] = st.text_area(
"Detail Prompt:",
value=sess['custom_prompts']['overall']['detail'],
height=150,
key="overall_prompt_detail"
)
if st.button("🔄 Generate with Custom Prompts", key="generate_overall"):
generate_mode = "overall"
with tab_tariff:
st.subheader("Tariff Prompts")
use_custom = st.checkbox("✏️ Use Custom Prompts", key="custom_tariff")
if use_custom:
sess['custom_prompts']['tariff']['summary'] = st.text_area(
"Summary Prompt:",
value=sess['custom_prompts']['tariff']['summary'],
height=150,
key="tariff_prompt_summary"
)
sess['custom_prompts']['tariff']['analyze'] = st.text_area(
"Analysis Prompt:",
value=sess['custom_prompts']['tariff']['analyze'],
height=150,
key="tariff_prompt_analyze"
)
sess['custom_prompts']['tariff']['detail'] = st.text_area(
"Detail Prompt:",
value=sess['custom_prompts']['tariff']['detail'],
height=150,
key="tariff_prompt_detail"
)
if st.button("🔄 Generate with Custom Prompts", key="generate_tariff"):
generate_mode = "tariff"
with tab_sales:
st.subheader("Sales Prompts")
use_custom = st.checkbox("✏️ Use Custom Prompts", key="custom_sales")
if use_custom:
sess['custom_prompts']['sales']['summary'] = st.text_area(
"Summary Prompt:",
value=sess['custom_prompts']['sales']['summary'],
height=150,
key="sales_prompt_summary"
)
sess['custom_prompts']['sales']['analyze'] = st.text_area(
"Analysis Prompt:",
value=sess['custom_prompts']['sales']['analyze'],
height=150,
key="sales_prompt_analyze"
)
sess['custom_prompts']['sales']['detail'] = st.text_area(
"Detail Prompt:",
value=sess['custom_prompts']['sales']['detail'],
height=150,
key="sales_prompt_detail"
)
if st.button("🔄 Generate with Custom Prompts", key="generate_sales"):
generate_mode = "sales"
with tab_supply:
st.subheader("Supply Chain Prompts")
use_custom = st.checkbox("✏️ Use Custom Prompts", key="custom_supply")
if use_custom:
sess['custom_prompts']['supplychain']['summary'] = st.text_area(
"Summary Prompt:",
value=sess['custom_prompts']['supplychain']['summary'],
height=150,
key="supply_prompt_summary"
)
sess['custom_prompts']['supplychain']['analyze'] = st.text_area(
"Analysis Prompt:",
value=sess['custom_prompts']['supplychain']['analyze'],
height=150,
key="supply_prompt_analyze"
)
sess['custom_prompts']['supplychain']['detail'] = st.text_area(
"Detail Prompt:",
value=sess['custom_prompts']['supplychain']['detail'],
height=150,
key="supply_prompt_detail"
)
if st.button("🔄 Generate with Custom Prompts", key="generate_supplychain"):
generate_mode = "supplychain"
# --- Analysis Buttons ---
st.subheader("Quick Analysis")
col0, col1, col2, col3 = st.columns(4)
analyze_overall = col0.button("📑 Overall Summary")
analyze_tariff = col1.button("🔍 Analyze Tariffs")
analyze_sales = col2.button("📈 Analyze Sales")
analyze_supplychain = col3.button("🚚 Supply Chain")
# Handle generation requests
if generate_mode or analyze_overall or analyze_tariff or analyze_sales or analyze_supplychain:
if not sess['uploaded_files']:
st.error("Please upload documents first.")
st.stop()
mode = generate_mode or (
"overall" if analyze_overall else
"tariff" if analyze_tariff else
"sales" if analyze_sales else
"supplychain" if analyze_supplychain else None
)
agent = None
processed_files = None
if mode == "overall":
agent = st.session_state.agent_overall
processed_files = sess['processed_files_overall']
elif mode == "tariff":
agent = st.session_state.agent_tariff
processed_files = sess['processed_files_tariff']
elif mode == "sales":
agent = st.session_state.agent_sales
processed_files = sess['processed_files_sales']
elif mode == "supplychain":
agent = st.session_state.agent_supplychain
processed_files = sess['processed_files_supplychain']
# Update agent with custom prompts if used
if generate_mode:
agent.prompt_summary = sess['custom_prompts'][mode]['summary']
agent.prompt_analyze = sess['custom_prompts'][mode]['analyze']
agent.prompt_detail = sess['custom_prompts'][mode]['detail']
st.toast(f"Using custom prompts for {mode} analysis")
else:
# Reset to default prompts
if mode == "overall":
agent.prompt_summary = OverallAgent.prompt_summary
agent.prompt_analyze = OverallAgent.prompt_analyze
agent.prompt_detail = OverallAgent.prompt_detail
elif mode == "tariff":
agent.prompt_summary = TariffTradeAgent.prompt_summary
agent.prompt_analyze = TariffTradeAgent.prompt_analyze
agent.prompt_detail = TariffTradeAgent.prompt_detail
elif mode == "sales":
agent.prompt_summary = SalesAgent.prompt_summary
agent.prompt_analyze = SalesAgent.prompt_analyze
agent.prompt_detail = SalesAgent.prompt_detail
elif mode == "supplychain":
agent.prompt_summary = SupplyChainAgent.prompt_summary
agent.prompt_analyze = SupplyChainAgent.prompt_analyze
agent.prompt_detail = SupplyChainAgent.prompt_detail
with st.spinner(f"🔍 Analyzing {mode.replace('supplychain', 'supply chain')} documents..."):
analyze_documents(
mode,
agent,
processed_files,
sess
)
# ... rest of the code (main display, topic analysis, chat interface) ...
# After analysis, ensure the display mode is correctly set for the next render
sess['last_analysis_mode'] = mode
st.rerun() # Rerun to refresh UI after analysis and prompt updates
# --- Main Display ---
last_mode = sess['last_analysis_mode']
if last_mode is None:
st.info("Select an analysis type to begin.")
return
# Consolidated data setup
mode_config = {
'overall': {
'files': sess['processed_files_overall'],
'summary': sess['consolidated_summary_overall'],
'sidebar_header': "Overall Topics",
'main_header': "🌟 Executive Summary",
'agent': st.session_state.agent_overall
},
'tariff': {
'files': sess['processed_files_tariff'],
'summary': sess['consolidated_summary_tariff'],
'sidebar_header': "Tariff Topics",
'main_header': "🌟 Tariff Analysis",
'agent': st.session_state.agent_tariff
},
'sales': {
'files': sess['processed_files_sales'],
'summary': sess['consolidated_summary_sales'],
'sidebar_header': "Sales Topics",
'main_header': "🌟 Sales Analysis",
'agent': st.session_state.agent_sales
},
'supplychain': {
'files': sess['processed_files_supplychain'],
'summary': sess['consolidated_summary_supplychain'],
'sidebar_header': "Supply Chain Topics",
'main_header': "🌟 Supply Chain Analysis",
'agent': st.session_state.agent_supplychain
}
}
current_mode = mode_config[last_mode]
# --- Sidebar Topics ---
st.sidebar.header(current_mode['sidebar_header'])
if last_mode == "overall":
topics_by_file = {}
for filename, filedata in current_mode['files'].items():
for topic in filedata["topics"]:
topics_by_file.setdefault(topic['name'], []).append({
'file': filename,
'score': topic['score']
})
a = sorted(topics_by_file.items(),
key=lambda x: max(x[1], key=lambda y: y['score'])['score'],
reverse=True)
before_view_more , after_view_more = a[:3] , a[3:]
for topic_name, occurrences in before_view_more:
total_score = sum(occ['score'] for occ in occurrences)
file_count = len(occurrences)
btn_label = f"{topic_name} (📈 {total_score:.1f} | 📑 {file_count})"
if st.sidebar.button(
btn_label,
key=f"overall_topic_{topic_name}",
use_container_width=True,
):
sess['active_topic'] = topic_name
sess['active_file'] = None
if st.sidebar.button('View More',key = '1234' , use_container_width=True):
for topic_name, occurrences in after_view_more:
total_score = sum(occ['score'] for occ in occurrences)
file_count = len(occurrences)
btn_label = f"{topic_name} (📈 {total_score:.1f} | 📑 {file_count})"
if st.sidebar.button(
btn_label,
key=f"overall_topic_more_{topic_name}", # Changed key to avoid collision
use_container_width=True,
):
sess['active_topic'] = topic_name
sess['active_file'] = None
else: # For Tariff, Sales, Supply Chain modes
for filename, filedata in current_mode['files'].items():
expanded = (filename == sess['active_file'])
with st.sidebar.expander(f"📄 {filename}", expanded=expanded):
topics = sorted(filedata["topics"], key=lambda t: t["score"], reverse=True)
for topic in topics[:3]:
is_selected = (
sess['active_file'] == filename and sess['active_topic'] == topic['name']
)
style = "primary" if is_selected else "secondary"
if st.button(
f"• {topic['name']} (Score: {topic['score']})",
key=f"{last_mode}topic{filename}_{topic['name']}",
type=style,
use_container_width=True,
):
sess['active_file'] = filename
sess['active_topic'] = topic['name']
if len(topics) > 3 and st.sidebar.button(f'View More for {filename}',key = f'{filename}_view_more' ,use_container_width=True):
for topic in topics[3:]:
is_selected = (
sess['active_file'] == filename and sess['active_topic'] == topic['name']
)
style = "primary" if is_selected else "secondary"
if st.button(
f"• {topic['name']} (Score: {topic['score']})",
key=f"{last_mode}topic_more{filename}_{topic['name']}", # Changed key
type=style,
use_container_width=True,
):
sess['active_file'] = filename
sess['active_topic'] = topic['name']
# --- Topic Analysis ---
st.subheader("Detailed Analysis")
if last_mode == "overall" and sess['active_topic']:
mentions = []
for filename, filedata in current_mode['files'].items():
for topic in filedata["topics"]:
if topic['name'] == sess['active_topic']:
mentions.append({
'file': filename,
'summary': topic.get('summary', ''),
'score': topic['score'],
'context': filedata['context']
})
with st.expander("📊 Topic Prevalence"):
cols = st.columns(3)
cols[0].metric("Total Documents", len(mentions))
avg_relevance = (sum(m['score'] for m in mentions)/len(mentions)) if mentions else 0
cols[1].metric("Average Relevance", f"{avg_relevance:.1f}")
cols[2].metric("First Mentioned", mentions[0]['file'] if mentions else "N/A")
if mentions:
combined_context = "\n\n".join(f"=== {m['file']} ===\n{m['context']}" for m in mentions)
key_cache = (last_mode, sess['active_topic'])
if key_cache in sess['topic_details_cache']:
st.markdown(sess['topic_details_cache'][key_cache])
else:
placeholder = st.empty()
collected_text = ""
try:
for chunk in current_mode['agent'].generate_topic_detail(combined_context, sess['active_topic']):
collected_text = chunk
placeholder.markdown(collected_text + (" ▌" if "▌" in collected_text else ""))
sess['topic_details_cache'][key_cache] = collected_text
except Exception as e:
st.error(f"Analysis error: {str(e)}")
elif sess['active_file'] and sess['active_topic']:
key_cache = (last_mode, sess['active_file'], sess['active_topic'])
if key_cache in sess['topic_details_cache']:
st.markdown(sess['topic_details_cache'][key_cache])
else:
placeholder = st.empty()
collected_text = ""
try:
for chunk in current_mode['agent'].generate_topic_detail(
current_mode['files'][sess['active_file']]['context'],
sess['active_topic'],
):
collected_text = chunk
placeholder.markdown(collected_text + (" ▌" if "▌" in collected_text else ""))
sess['topic_details_cache'][key_cache] = collected_text
except Exception as e:
st.error(f"Analysis error: {str(e)}")
else:
st.info("Select a topic from the sidebar")
st.markdown("---")
# --- Consolidated Summary ---
st.header(current_mode['main_header'])
if current_mode['summary']:
st.markdown(current_mode['summary'])
else:
st.info("Summary not available yet")
st.divider()
# --- Chat Interface ---
st.subheader("💬 Document Chat")
# File selection
available_files = list(current_mode['files'].keys())
selected_files = st.multiselect(
"Select documents for context:",
available_files,
key=f"chat_selector_{last_mode}"
)
# Chat history
for msg in sess['chat_history']:
with st.chat_message(msg["role"]):
st.markdown(msg["content"])
# Question handling
question = st.chat_input("Ask about the documents...")
if question:
if not selected_files:
st.error("Please select documents first")
st.stop()
sess['chat_history'].append({
"role": "user",
"content": question,
"timestamp": datetime.utcnow().isoformat(),
})
try:
context = "\n\n".join([
f"=== {fname} ===\n{current_mode['files'][fname]['context']}"
for fname in selected_files
])
with st.chat_message("assistant"):
response_placeholder = st.empty()
full_response = ""
q_type = None
# Ensure custom_prompt_text_for_mode is available here if needed for chat_agent
# For now, it's used only for analysis in analyze_documents, adjust if chat_agent needs it.
for chunk, q_type in st.session_state.chat_agent.generate_answer(question, context):
full_response = chunk
response_placeholder.markdown(full_response + " ▌")
response_placeholder.markdown(full_response)
sess['chat_history'].append({
"role": "assistant",
"content": full_response,
"timestamp": datetime.utcnow().isoformat(),
"analysis_type": q_type
})
except Exception as e:
st.error(f"Chat error: {str(e)}")
sess['chat_history'].append({
"role": "assistant",
"content": f"Error: {str(e)}",
"timestamp": datetime.utcnow().isoformat(),
})
# Reset button
if st.button("🔄 Reset Session", type="secondary"):
# Preserve long-lived objects like client and agents to avoid overhead on re-init
preserved_keys = [
"client", "agent_overall", "agent_tariff",
"agent_sales", "agent_supplychain", "chat_agent", "provider"
]
preserved = {k: st.session_state[k] for k in preserved_keys if k in st.session_state}
# Clear entire session state
st.session_state.clear()
# Restore preserved keys back
st.session_state.update(preserved)
# Reset session-specific stored data completely
st.session_state.session = {
'uploaded_files': {},
'processed_files_overall': {},
'processed_files_tariff': {},
'processed_files_sales': {},
'processed_files_supplychain': {},
'active_file': None,
'active_topic': None,
'topic_details_cache': {},
'chat_history': [],
'consolidated_summary_overall': None,
'consolidated_summary_tariff': None,
'consolidated_summary_sales': None,
'consolidated_summary_supplychain': None,
'last_analysis_mode': None,
'custom_prompt_enabled': {},
'custom_prompt_text': {}
}
# Trigger a rerun for fresh UI without old content
st.rerun()
if name == "main":
main()
import streamlit as st
from io import BytesIO
from datetime import datetime
# Assuming these are correctly defined and accessible
from utils.pdf_utils import extract_text
from clients.azure_client import AzureClient
from clients.gemini_client import GeminiClient
from agents.tariff_agent import TariffTradeAgent
from agents.sales_agent import SalesAgent
from agents.supply_chain_agent import SupplyChainAgent
from agents.overall_agent import OverallAgent
from agents.enhanced_chat_agent import EnhancedChatAgent
from agents.qa_agent import QAAgent # New QA Agent
def analyze_documents(mode, agent, processed_files, sess, custom_prompt=None):
# Process individual files
for filename, file_bytes in sess['uploaded_files'].items():
if filename not in processed_files:
try:
file_obj = BytesIO(file_bytes)
file_obj.name = filename
text = extract_text(file_obj)
if text:
if mode == "overall":
topics = agent.analyze_document(text, custom_prompt)
else:
topics = agent.analyze_document(text, custom_prompt) # Pass custom_prompt to other agents too
processed_files[filename] = {
"text": text,
"topics": topics,
"context": text,
}
st.toast(f"✅ Processed {filename}")
else:
st.error(f"❌ Failed to extract text for {filename}")
except Exception as e:
st.error(f"Error processing {filename}: {str(e)}")
# Generate consolidated summary
if mode == "overall":
summary = agent.generate_consolidated_summary_from_topics(processed_files, custom_prompt)
else:
summary = agent.generate_consolidated_summary_from_topics(processed_files, custom_prompt) # Pass custom_prompt
if mode == "overall":
sess['consolidated_summary_overall'] = summary
elif mode == "tariff":
sess['consolidated_summary_tariff'] = summary
elif mode == "sales":
sess['consolidated_summary_sales'] = summary
elif mode == "supplychain":
sess['consolidated_summary_supplychain'] = summary
elif mode == "qa": # New QA summary
sess['consolidated_summary_qa'] = summary
sess['last_analysis_mode'] = mode
sess['active_file'] = None
sess['active_topic'] = None
st.success(f"Analysis and summary generated for {mode.replace('supplychain', 'supply chain').replace('qa', 'Q&A')}.")
def main():
st.set_page_config(page_title="Macy's Document Analysis Pro", layout="wide")
st.title("📄 Macy's Document Analysis & Chat Tool")
# Mode selection
provider_select = st.radio("Select AI Provider", ["Azure GPT", "Google Gemini"])
# Session Initialization
if "session" not in st.session_state:
st.session_state.session = {
'uploaded_files': {},
'processed_files_overall': {},
'processed_files_tariff': {},
'processed_files_sales': {},
'processed_files_supplychain': {},
'processed_files_qa': {}, # New QA processed files
'active_file': None,
'active_topic': None,
'topic_details_cache': {},
'chat_history': [],
'consolidated_summary_overall': None,
'consolidated_summary_tariff': None,
'consolidated_summary_sales': None,
'consolidated_summary_supplychain': None,
'consolidated_summary_qa': None, # New QA summary
'last_analysis_mode': None,
'custom_prompt_enabled': {},
'custom_prompt_text': {}
}
if "client" not in st.session_state or st.session_state.get("provider") != provider_select:
if provider_select == "Azure GPT":
st.session_state.client = AzureClient()
is_azure = True
else:
st.session_state.client = GeminiClient()
is_azure = False
# Initialize agents
st.session_state.agent_overall = OverallAgent(st.session_state.client, is_azure)
st.session_state.agent_tariff = TariffTradeAgent(st.session_state.client, is_azure)
st.session_state.agent_sales = SalesAgent(st.session_state.client, is_azure)
st.session_state.agent_supplychain = SupplyChainAgent(st.session_state.client, is_azure)
st.session_state.agent_qa = QAAgent(st.session_state.client, is_azure) # New QA agent
st.session_state.chat_agent = EnhancedChatAgent(st.session_state.client, is_azure)
st.session_state.provider = provider_select
sess = st.session_state.session
# --- File Upload ---
st.subheader("1. Upload Documents")
uploaded_files = st.file_uploader(
"Upload PDF documents",
type=["pdf"],
accept_multiple_files=True,
key="file_uploader",
)
if uploaded_files:
new_files_added = False
for file in uploaded_files:
if file.name not in sess['uploaded_files']:
sess['uploaded_files'][file.name] = file.getvalue()
new_files_added = True
if new_files_added:
with st.spinner("🔍 Analyzing new documents with Overall Agent..."):
# Always run initial overall analysis for new files
analyze_documents(
mode="overall",
agent=st.session_state.agent_overall,
processed_files=sess['processed_files_overall'],
sess=sess
)
# --- Custom Prompts & Analysis ---
st.subheader("2. Custom Prompts & Analysis")
# Initialize custom prompts in session state
if 'custom_prompts' not in sess:
sess['custom_prompts'] = {
'overall': {
'summary': OverallAgent.prompt_summary,
'analyze': OverallAgent.prompt_analyze,
'detail': OverallAgent.prompt_detail
},
'tariff': {
'summary': TariffTradeAgent.prompt_summary,
'analyze': TariffTradeAgent.prompt_analyze,
'detail': TariffTradeAgent.prompt_detail
},
'sales': {
'summary': SalesAgent.prompt_summary,
'analyze': SalesAgent.prompt_analyze,
'detail': SalesAgent.prompt_detail
},
'supplychain': {
'summary': SupplyChainAgent.prompt_summary,
'analyze': SupplyChainAgent.prompt_analyze,
'detail': SupplyChainAgent.prompt_detail
},
'qa': { # New QA prompts
'summary': QAAgent.prompt_summary,
'analyze': QAAgent.prompt_analyze,
'detail': QAAgent.prompt_detail
}
}
# Create tabs for each agent's custom prompts
tab_overall, tab_tariff, tab_sales, tab_supply, tab_qa = st.tabs([
"📑 Overall", "🔍 Tariff", "📈 Sales", "🚚 Supply Chain", "❓ Q&A" # New QA tab
])
# Store which mode we're generating for
generate_mode = None
with tab_overall:
st.subheader("Overall Prompts")
use_custom = st.checkbox("✏️ Use Custom Prompts", key="custom_overall")
if use_custom:
sess['custom_prompts']['overall']['summary'] = st.text_area(
"Summary Prompt:",
value=sess['custom_prompts']['overall']['summary'],
height=150,
key="overall_prompt_summary"
)
sess['custom_prompts']['overall']['analyze'] = st.text_area(
"Analysis Prompt:",
value=sess['custom_prompts']['overall']['analyze'],
height=150,
key="overall_prompt_analyze"
)
sess['custom_prompts']['overall']['detail'] = st.text_area(
"Detail Prompt:",
value=sess['custom_prompts']['overall']['detail'],
height=150,
key="overall_prompt_detail"
)
if st.button("🔄 Generate with Custom Prompts", key="generate_overall"):
generate_mode = "overall"
with tab_tariff:
st.subheader("Tariff Prompts")
use_custom = st.checkbox("✏️ Use Custom Prompts", key="custom_tariff")
if use_custom:
sess['custom_prompts']['tariff']['summary'] = st.text_area(
"Summary Prompt:",
value=sess['custom_prompts']['tariff']['summary'],
height=150,
key="tariff_prompt_summary"
)
sess['custom_prompts']['tariff']['analyze'] = st.text_area(
"Analysis Prompt:",
value=sess['custom_prompts']['tariff']['analyze'],
height=150,
key="tariff_prompt_analyze"
)
sess['custom_prompts']['tariff']['detail'] = st.text_area(
"Detail Prompt:",
value=sess['custom_prompts']['tariff']['detail'],
height=150,
key="tariff_prompt_detail"
)
if st.button("🔄 Generate with Custom Prompts", key="generate_tariff"):
generate_mode = "tariff"
with tab_sales:
st.subheader("Sales Prompts")
use_custom = st.checkbox("✏️ Use Custom Prompts", key="custom_sales")
if use_custom:
sess['custom_prompts']['sales']['summary'] = st.text_area(
"Summary Prompt:",
value=sess['custom_prompts']['sales']['summary'],
height=150,
key="sales_prompt_summary"
)
sess['custom_prompts']['sales']['analyze'] = st.text_area(
"Analysis Prompt:",
value=sess['custom_prompts']['sales']['analyze'],
height=150,
key="sales_prompt_analyze"
)
sess['custom_prompts']['sales']['detail'] = st.text_area(
"Detail Prompt:",
value=sess['custom_prompts']['sales']['detail'],
height=150,
key="sales_prompt_detail"
)
if st.button("🔄 Generate with Custom Prompts", key="generate_sales"):
generate_mode = "sales"
with tab_supply:
st.subheader("Supply Chain Prompts")
use_custom = st.checkbox("✏️ Use Custom Prompts", key="custom_supply")
if use_custom:
sess['custom_prompts']['supplychain']['summary'] = st.text_area(
"Summary Prompt:",
value=sess['custom_prompts']['supplychain']['summary'],
height=150,
key="supply_prompt_summary"
)
sess['custom_prompts']['supplychain']['analyze'] = st.text_area(
"Analysis Prompt:",
value=sess['custom_prompts']['supplychain']['analyze'],
height=150,
key="supply_prompt_analyze"
)
sess['custom_prompts']['supplychain']['detail'] = st.text_area(
"Detail Prompt:",
value=sess['custom_prompts']['supplychain']['detail'],
height=150,
key="supply_prompt_detail"
)
if st.button("🔄 Generate with Custom Prompts", key="generate_supplychain"):
generate_mode = "supplychain"
with tab_qa: # New QA tab
st.subheader("Q&A Prompts")
use_custom = st.checkbox("✏️ Use Custom Prompts", key="custom_qa")
if use_custom:
sess['custom_prompts']['qa']['summary'] = st.text_area(
"Summary Prompt:",
value=sess['custom_prompts']['qa']['summary'],
height=150,
key="qa_prompt_summary"
)
sess['custom_prompts']['qa']['analyze'] = st.text_area(
"Analysis Prompt:",
value=sess['custom_prompts']['qa']['analyze'],
height=150,
key="qa_prompt_analyze"
)
sess['custom_prompts']['qa']['detail'] = st.text_area(
"Detail Prompt:",
value=sess['custom_prompts']['qa']['detail'],
height=150,
key="qa_prompt_detail"
)
if st.button("🔄 Generate with Custom Prompts", key="generate_qa"):
generate_mode = "qa"
# --- Analysis Buttons ---
st.subheader("Quick Analysis")
col0, col1, col2, col3, col4 = st.columns(5) # Added extra column for QA
analyze_overall = col0.button("📑 Overall Summary")
analyze_tariff = col1.button("🔍 Analyze Tariffs")
analyze_sales = col2.button("📈 Analyze Sales")
analyze_supplychain = col3.button("🚚 Supply Chain")
analyze_qa = col4.button("❓ Q&A") # New QA button
# Handle generation requests
if generate_mode or analyze_overall or analyze_tariff or analyze_sales or analyze_supplychain or analyze_qa:
if not sess['uploaded_files']:
st.error("Please upload documents first.")
st.stop()
mode = generate_mode or (
"overall" if analyze_overall else
"tariff" if analyze_tariff else
"sales" if analyze_sales else
"supplychain" if analyze_supplychain else
"qa" if analyze_qa else None # New QA mode
)
agent = None
processed_files = None
if mode == "overall":
agent = st.session_state.agent_overall
processed_files = sess['processed_files_overall']
elif mode == "tariff":
agent = st.session_state.agent_tariff
processed_files = sess['processed_files_tariff']
elif mode == "sales":
agent = st.session_state.agent_sales
processed_files = sess['processed_files_sales']
elif mode == "supplychain":
agent = st.session_state.agent_supplychain
processed_files = sess['processed_files_supplychain']
elif mode == "qa": # New QA handling
agent = st.session_state.agent_qa
processed_files = sess['processed_files_qa']
# Update agent with custom prompts if used
if generate_mode:
agent.prompt_summary = sess['custom_prompts'][mode]['summary']
agent.prompt_analyze = sess['custom_prompts'][mode]['analyze']
agent.prompt_detail = sess['custom_prompts'][mode]['detail']
st.toast(f"Using custom prompts for {mode} analysis")
else:
# Reset to default prompts
if mode == "overall":
agent.prompt_summary = OverallAgent.prompt_summary
agent.prompt_analyze = OverallAgent.prompt_analyze
agent.prompt_detail = OverallAgent.prompt_detail
elif mode == "tariff":
agent.prompt_summary = TariffTradeAgent.prompt_summary
agent.prompt_analyze = TariffTradeAgent.prompt_analyze
agent.prompt_detail = TariffTradeAgent.prompt_detail
elif mode == "sales":
agent.prompt_summary = SalesAgent.prompt_summary
agent.prompt_analyze = SalesAgent.prompt_analyze
agent.prompt_detail = SalesAgent.prompt_detail
elif mode == "supplychain":
agent.prompt_summary = SupplyChainAgent.prompt_summary
agent.prompt_analyze = SupplyChainAgent.prompt_analyze
agent.prompt_detail = SupplyChainAgent.prompt_detail
elif mode == "qa": # New QA reset
agent.prompt_summary = QAAgent.prompt_summary
agent.prompt_analyze = QAAgent.prompt_analyze
agent.prompt_detail = QAAgent.prompt_detail
with st.spinner(f"🔍 Analyzing {mode.replace('supplychain', 'supply chain').replace('qa', 'Q&A')} documents..."):
analyze_documents(
mode,
agent,
processed_files,
sess
)
# --- Main Display ---
last_mode = sess['last_analysis_mode']
if last_mode is None:
st.info("Select an analysis type to begin.")
return
# Consolidated data setup
mode_config = {
'overall': {
'files': sess['processed_files_overall'],
'summary': sess['consolidated_summary_overall'],
'sidebar_header': "Overall Topics",
'main_header': "🌟 Executive Summary",
'agent': st.session_state.agent_overall
},
'tariff': {
'files': sess['processed_files_tariff'],
'summary': sess['consolidated_summary_tariff'],
'sidebar_header': "Tariff Topics",
'main_header': "🌟 Tariff Analysis",
'agent': st.session_state.agent_tariff
},
'sales': {
'files': sess['processed_files_sales'],
'summary': sess['consolidated_summary_sales'],
'sidebar_header': "Sales Topics",
'main_header': "🌟 Sales Analysis",
'agent': st.session_state.agent_sales
},
'supplychain': {
'files': sess['processed_files_supplychain'],
'summary': sess['consolidated_summary_supplychain'],
'sidebar_header': "Supply Chain Topics",
'main_header': "🌟 Supply Chain Analysis",
'agent': st.session_state.agent_supplychain
},
'qa': { # New QA config
'files': sess['processed_files_qa'],
'summary': sess['consolidated_summary_qa'],
'sidebar_header': "Q&A by Document",
'main_header': "❓ Questions & Answers",
'agent': st.session_state.agent_qa
}
}
current_mode = mode_config[last_mode]
# --- Sidebar Topics ---
st.sidebar.header(current_mode['sidebar_header'])
if last_mode == "overall":
topics_by_file = {}
for filename, filedata in current_mode['files'].items():
for topic in filedata["topics"]:
topics_by_file.setdefault(topic['name'], []).append({
'file': filename,
'score': topic['score']
})
a = sorted(topics_by_file.items(),
key=lambda x: max(x[1], key=lambda y: y['score'])['score'],
reverse=True)
before_view_more , after_view_more = a[:3] , a[3:]
for topic_name, occurrences in before_view_more:
total_score = sum(occ['score'] for occ in occurrences)
file_count = len(occurrences)
btn_label = f"{topic_name} (📈 {total_score:.1f} | 📑 {file_count})"
if st.sidebar.button(
btn_label,
key=f"overall_topic_{topic_name}",
use_container_width=True,
):
sess['active_topic'] = topic_name
sess['active_file'] = None
if st.sidebar.button('View More',key = '1234' , use_container_width=True):
for topic_name, occurrences in after_view_more:
total_score = sum(occ['score'] for occ in occurrences)
file_count = len(occurrences)
btn_label = f"{topic_name} (📈 {total_score:.1f} | 📑 {file_count})"
if st.sidebar.button(
btn_label,
key=f"overall_topic_more_{topic_name}", # Changed key to avoid collision
use_container_width=True,
):
sess['active_topic'] = topic_name
sess['active_file'] = None
elif last_mode == "qa": # New QA sidebar
st.sidebar.subheader("Documents with Q&A")
for filename in current_mode['files']:
if st.sidebar.button(
filename,
key=f"qa_doc_{filename}",
use_container_width=True
):
sess['active_file'] = filename
sess['active_topic'] = None
else: # For Tariff, Sales, Supply Chain modes
for filename, filedata in current_mode['files'].items():
expanded = (filename == sess['active_file'])
with st.sidebar.expander(f"📄 {filename}", expanded=expanded):
topics = sorted(filedata["topics"], key=lambda t: t["score"], reverse=True)
for topic in topics[:3]:
is_selected = (
sess['active_file'] == filename and sess['active_topic'] == topic['name']
)
style = "primary" if is_selected else "secondary"
if st.button(
f"• {topic['name']} (Score: {topic['score']})",
key=f"{last_mode}topic{filename}_{topic['name']}",
type=style,
use_container_width=True,
):
sess['active_file'] = filename
sess['active_topic'] = topic['name']
if len(topics) > 3 and st.sidebar.button(f'View More for {filename}',key = f'{filename}_view_more' ,use_container_width=True):
for topic in topics[3:]:
is_selected = (
sess['active_file'] == filename and sess['active_topic'] == topic['name']
)
style = "primary" if is_selected else "secondary"
if st.button(
f"• {topic['name']} (Score: {topic['score']})",
key=f"{last_mode}topic_more{filename}_{topic['name']}", # Changed key
type=style,
use_container_width=True,
):
sess['active_file'] = filename
sess['active_topic'] = topic['name']
# --- Topic Analysis ---
st.subheader("Detailed Analysis")
if last_mode == "overall" and sess['active_topic']:
mentions = []
for filename, filedata in current_mode['files'].items():
for topic in filedata["topics"]:
if topic['name'] == sess['active_topic']:
mentions.append({
'file': filename,
'summary': topic.get('summary', ''),
'score': topic['score'],
'context': filedata['context']
})
with st.expander("📊 Topic Prevalence"):
cols = st.columns(3)
cols[0].metric("Total Documents", len(mentions))
avg_relevance = (sum(m['score'] for m in mentions)/len(mentions)) if mentions else 0
cols[1].metric("Average Relevance", f"{avg_relevance:.1f}")
cols[2].metric("First Mentioned", mentions[0]['file'] if mentions else "N/A")
if mentions:
combined_context = "\n\n".join(f"=== {m['file']} ===\n{m['context']}" for m in mentions)
key_cache = (last_mode, sess['active_topic'])
if key_cache in sess['topic_details_cache']:
st.markdown(sess['topic_details_cache'][key_cache])
else:
placeholder = st.empty()
collected_text = ""
try:
for chunk in current_mode['agent'].generate_topic_detail(combined_context, sess['active_topic']):
collected_text = chunk
placeholder.markdown(collected_text + (" ▌" if "▌" in collected_text else ""))
sess['topic_details_cache'][key_cache] = collected_text
except Exception as e:
st.error(f"Analysis error: {str(e)}")
elif last_mode == "qa" and sess['active_file']: # New QA display
st.subheader(f"Q&A for {sess['active_file']}")
filedata = current_mode['files'].get(sess['active_file'])
if filedata:
# Display Q&A pairs
for qa in filedata["topics"]:
with st.expander(f"Q: {qa['question']}"):
st.markdown(f"A: {qa['answer']}")
st.caption(f"Relevance: {qa['score']} | Speaker: {qa['speaker']} | Category: {qa['category']}")
else:
st.warning("Document not found in Q&A analysis")
elif sess['active_file'] and sess['active_topic']:
key_cache = (last_mode, sess['active_file'], sess['active_topic'])
if key_cache in sess['topic_details_cache']:
st.markdown(sess['topic_details_cache'][key_cache])
else:
placeholder = st.empty()
collected_text = ""
try:
for chunk in current_mode['agent'].generate_topic_detail(
current_mode['files'][sess['active_file']]['context'],
sess['active_topic'],
):
collected_text = chunk
placeholder.markdown(collected_text + (" ▌" if "▌" in collected_text else ""))
sess['topic_details_cache'][key_cache] = collected_text
except Exception as e:
st.error(f"Analysis error: {str(e)}")
else:
st.info("Select a topic from the sidebar")
st.markdown("---")
# --- Consolidated Summary ---
st.header(current_mode['main_header'])
if current_mode['summary']:
st.markdown(current_mode['summary'])
else:
st.info("Summary not available yet")
st.divider()
# --- Chat Interface ---
st.subheader("💬 Document Chat")
# File selection
available_files = list(current_mode['files'].keys())
selected_files = st.multiselect(
"Select documents for context:",
available_files,
key=f"chat_selector_{last_mode}"
)
# Chat history
for msg in sess['chat_history']:
with st.chat_message(msg["role"]):
st.markdown(msg["content"])
# Question handling
question = st.chat_input("Ask about the documents...")
if question:
if not selected_files:
st.error("Please select documents first")
st.stop()
sess['chat_history'].append({
"role": "user",
"content": question,
"timestamp": datetime.utcnow().isoformat(),
})
try:
context = "\n\n".join([
f"=== {fname} ===\n{current_mode['files'][fname]['context']}"
for fname in selected_files
])
with st.chat_message("assistant"):
response_placeholder = st.empty()
full_response = ""
q_type = None
# Ensure custom_prompt_text_for_mode is available here if needed for chat_agent
# For now, it's used only for analysis in analyze_documents, adjust if chat_agent needs it.
for chunk, q_type in st.session_state.chat_agent.generate_answer(question, context):
full_response = chunk
response_placeholder.markdown(full_response + " ▌")
response_placeholder.markdown(full_response)
sess['chat_history'].append({
"role": "assistant",
"content": full_response,
"timestamp": datetime.utcnow().isoformat(),
'analysis_type': q_type
})
except Exception as e:
st.error(f"Chat error: {str(e)}")
sess['chat_history'].append({
"role": "assistant",
"content": f"Error: {str(e)}",
"timestamp": datetime.utcnow().isoformat(),
})
# Reset button
if st.button("🔄 Reset Session", type="secondary"):
# Preserve long-lived objects like client and agents to avoid overhead on re-init
preserved_keys = [
"client", "agent_overall", "agent_tariff",
"agent_sales", "agent_supplychain", "agent_qa", "chat_agent", "provider"
]
preserved = {k: st.session_state[k] for k in preserved_keys if k in st.session_state}
# Clear entire session state
st.session_state.clear()
# Restore preserved keys back
st.session_state.update(preserved)
# Reset session-specific stored data completely
st.session_state.session = {
'uploaded_files': {},
'processed_files_overall': {},
'processed_files_tariff': {},
'processed_files_sales': {},
'processed_files_supplychain': {},
'processed_files_qa': {}, # New QA processed files
'active_file': None,
'active_topic': None,
'topic_details_cache': {},
'chat_history': [],
'consolidated_summary_overall': None,
'consolidated_summary_tariff': None,
'consolidated_summary_sales': None,
'consolidated_summary_supplychain': None,
'consolidated_summary_qa': None, # New QA summary
'last_analysis_mode': None,
'custom_prompt_enabled': {},
'custom_prompt_text': {}
}
# Trigger a rerun for fresh UI without old content
st.rerun()
if name == "main":
main()
main.py
import streamlit as st from io import BytesIO from datetime import datetime
Assuming these are correctly defined and accessible
from utils.pdf_utils import extract_text from clients.azure_client import AzureClient from clients.gemini_client import GeminiClient
from agents.tariff_agent import TariffTradeAgent from agents.sales_agent import SalesAgent from agents.supply_chain_agent import SupplyChainAgent from agents.overall_agent import OverallAgent from agents.enhanced_chat_agent import EnhancedChatAgent from agents.qa_agent import QAAgent
def analyze_documents(mode, agent, processed_files, sess, custom_prompt=None):
# Process individual files for filename, file_bytes in sess['uploaded_files'].items(): if filename not in processed_files: try: file_obj = BytesIO(file_bytes) file_obj.name = filename text = extract_text(file_obj) if text: topics = agent.analyze_document(text, custom_prompt) processed_files[filename] = { "text": text, "topics": topics, "context": text, } st.toast(f"✅ Processed {filename}") else: st.error(f"❌ Failed to extract text for {filename}") except Exception as e: st.error(f"Error processing {filename}: {str(e)}") # Generate consolidated summary summary = agent.generate_consolidated_summary_from_topics(processed_files, custom_prompt) # Store summary based on mode summary_keys = { "overall": 'consolidated_summary_overall', "tariff": 'consolidated_summary_tariff', "sales": 'consolidated_summary_sales', "supplychain": 'consolidated_summary_supplychain', "qa": 'consolidated_summary_qa' } sess[summary_keys[mode]] = summary sess['last_analysis_mode'] = mode sess['active_file'] = None sess['active_topic'] = None st.success(f"Analysis and summary generated for {mode.replace('supplychain', 'supply chain').replace('qa', 'Q&A')}.")def main(): st.set_page_config(page_title="Macy's Document Analysis Pro", layout="wide") st.title("📄 Macy's Document Analysis & Chat Tool")
# Mode selection provider_select = st.radio("Select AI Provider", ["Azure GPT", "Google Gemini"]) # Session Initialization if "session" not in st.session_state: st.session_state.session = { 'uploaded_files': {}, 'processed_files_overall': {}, 'processed_files_tariff': {}, 'processed_files_sales': {}, 'processed_files_supplychain': {}, 'processed_files_qa': {}, 'active_file': None, 'active_topic': None, 'topic_details_cache': {}, 'chat_history': [], 'consolidated_summary_overall': None, 'consolidated_summary_tariff': None, 'consolidated_summary_sales': None, 'consolidated_summary_supplychain': None, 'consolidated_summary_qa': None, 'last_analysis_mode': None, 'custom_prompt_enabled': {}, 'custom_prompt_text': {} } if "client" not in st.session_state or st.session_state.get("provider") != provider_select: if provider_select == "Azure GPT": st.session_state.client = AzureClient() is_azure = True else: st.session_state.client = GeminiClient() is_azure = False # Initialize agents st.session_state.agent_overall = OverallAgent(st.session_state.client, is_azure) st.session_state.agent_tariff = TariffTradeAgent(st.session_state.client, is_azure) st.session_state.agent_sales = SalesAgent(st.session_state.client, is_azure) st.session_state.agent_supplychain = SupplyChainAgent(st.session_state.client, is_azure) st.session_state.agent_qa = QAAgent(st.session_state.client, is_azure) st.session_state.chat_agent = EnhancedChatAgent(st.session_state.client, is_azure) st.session_state.provider = provider_select sess = st.session_state.session # --- File Upload --- st.subheader("1. Upload Documents") uploaded_files = st.file_uploader( "Upload PDF documents", type=["pdf"], accept_multiple_files=True, key="file_uploader", ) if uploaded_files: new_files_added = False for file in uploaded_files: if file.name not in sess['uploaded_files']: sess['uploaded_files'][file.name] = file.getvalue() new_files_added = True if new_files_added: with st.spinner("🔍 Analyzing new documents with Overall Agent..."): analyze_documents( mode="overall", agent=st.session_state.agent_overall, processed_files=sess['processed_files_overall'], sess=sess ) # --- Custom Prompts & Analysis --- st.subheader("2. Custom Prompts & Analysis") # Initialize custom prompts in session state if 'custom_prompts' not in sess: sess['custom_prompts'] = { 'overall': { 'summary': OverallAgent.prompt_summary, 'analyze': OverallAgent.prompt_analyze, 'detail': OverallAgent.prompt_detail }, 'tariff': { 'summary': TariffTradeAgent.prompt_summary, 'analyze': TariffTradeAgent.prompt_analyze, 'detail': TariffTradeAgent.prompt_detail }, 'sales': { 'summary': SalesAgent.prompt_summary, 'analyze': SalesAgent.prompt_analyze, 'detail': SalesAgent.prompt_detail }, 'supplychain': { 'summary': SupplyChainAgent.prompt_summary, 'analyze': SupplyChainAgent.prompt_analyze, 'detail': SupplyChainAgent.prompt_detail }, 'qa': { 'summary': QAAgent.prompt_summary, 'analyze': QAAgent.prompt_analyze, 'detail': QAAgent.prompt_detail } } # Create tabs for each agent's custom prompts tab_overall, tab_tariff, tab_sales, tab_supply, tab_qa = st.tabs([ "📑 Overall", "🔍 Tariff", "📈 Sales", "🚚 Supply Chain", "❓ Q&A" ]) # Store which mode we're generating for generate_mode = None with tab_overall: st.subheader("Overall Prompts") use_custom = st.checkbox("✏️ Use Custom Prompts", key="custom_overall") if use_custom: sess['custom_prompts']['overall']['summary'] = st.text_area( "Summary Prompt:", value=sess['custom_prompts']['overall']['summary'], height=150, key="overall_prompt_summary" ) sess['custom_prompts']['overall']['analyze'] = st.text_area( "Analysis Prompt:", value=sess['custom_prompts']['overall']['analyze'], height=150, key="overall_prompt_analyze" ) sess['custom_prompts']['overall']['detail'] = st.text_area( "Detail Prompt:", value=sess['custom_prompts']['overall']['detail'], height=150, key="overall_prompt_detail" ) if st.button("🔄 Generate with Custom Prompts", key="generate_overall"): generate_mode = "overall" with tab_tariff: st.subheader("Tariff Prompts") use_custom = st.checkbox("✏️ Use Custom Prompts", key="custom_tariff") if use_custom: sess['custom_prompts']['tariff']['summary'] = st.text_area( "Summary Prompt:", value=sess['custom_prompts']['tariff']['summary'], height=150, key="tariff_prompt_summary" ) sess['custom_prompts']['tariff']['analyze'] = st.text_area( "Analysis Prompt:", value=sess['custom_prompts']['tariff']['analyze'], height=150, key="tariff_prompt_analyze" ) sess['custom_prompts']['tariff']['detail'] = st.text_area( "Detail Prompt:", value=sess['custom_prompts']['tariff']['detail'], height=150, key="tariff_prompt_detail" ) if st.button("🔄 Generate with Custom Prompts", key="generate_tariff"): generate_mode = "tariff" with tab_sales: st.subheader("Sales Prompts") use_custom = st.checkbox("✏️ Use Custom Prompts", key="custom_sales") if use_custom: sess['custom_prompts']['sales']['summary'] = st.text_area( "Summary Prompt:", value=sess['custom_prompts']['sales']['summary'], height=150, key="sales_prompt_summary" ) sess['custom_prompts']['sales']['analyze'] = st.text_area( "Analysis Prompt:", value=sess['custom_prompts']['sales']['analyze'], height=150, key="sales_prompt_analyze" ) sess['custom_prompts']['sales']['detail'] = st.text_area( "Detail Prompt:", value=sess['custom_prompts']['sales']['detail'], height=150, key="sales_prompt_detail" ) if st.button("🔄 Generate with Custom Prompts", key="generate_sales"): generate_mode = "sales" with tab_supply: st.subheader("Supply Chain Prompts") use_custom = st.checkbox("✏️ Use Custom Prompts", key="custom_supply") if use_custom: sess['custom_prompts']['supplychain']['summary'] = st.text_area( "Summary Prompt:", value=sess['custom_prompts']['supplychain']['summary'], height=150, key="supply_prompt_summary" ) sess['custom_prompts']['supplychain']['analyze'] = st.text_area( "Analysis Prompt:", value=sess['custom_prompts']['supplychain']['analyze'], height=150, key="supply_prompt_analyze" ) sess['custom_prompts']['supplychain']['detail'] = st.text_area( "Detail Prompt:", value=sess['custom_prompts']['supplychain']['detail'], height=150, key="supply_prompt_detail" ) if st.button("🔄 Generate with Custom Prompts", key="generate_supplychain"): generate_mode = "supplychain" with tab_qa: st.subheader("Q&A Prompts") use_custom = st.checkbox("✏️ Use Custom Prompts", key="custom_qa") if use_custom: sess['custom_prompts']['qa']['summary'] = st.text_area( "Summary Prompt:", value=sess['custom_prompts']['qa']['summary'], height=150, key="qa_prompt_summary" ) sess['custom_prompts']['qa']['analyze'] = st.text_area( "Analysis Prompt:", value=sess['custom_prompts']['qa']['analyze'], height=150, key="qa_prompt_analyze" ) sess['custom_prompts']['qa']['detail'] = st.text_area( "Detail Prompt:", value=sess['custom_prompts']['qa']['detail'], height=150, key="qa_prompt_detail" ) if st.button("🔄 Generate with Custom Prompts", key="generate_qa"): generate_mode = "qa" # --- Analysis Buttons --- st.subheader("Quick Analysis") col0, col1, col2, col3, col4 = st.columns(5) analyze_overall = col0.button("📑 Overall Summary") analyze_tariff = col1.button("🔍 Analyze Tariffs") analyze_sales = col2.button("📈 Analyze Sales") analyze_supplychain = col3.button("🚚 Supply Chain") analyze_qa = col4.button("❓ Q&A") # Handle generation requests if generate_mode or analyze_overall or analyze_tariff or analyze_sales or analyze_supplychain or analyze_qa: if not sess['uploaded_files']: st.error("Please upload documents first.") st.stop() mode = generate_mode or ( "overall" if analyze_overall else "tariff" if analyze_tariff else "sales" if analyze_sales else "supplychain" if analyze_supplychain else "qa" if analyze_qa else None ) agent = None processed_files = None if mode == "overall": agent = st.session_state.agent_overall processed_files = sess['processed_files_overall'] elif mode == "tariff": agent = st.session_state.agent_tariff processed_files = sess['processed_files_tariff'] elif mode == "sales": agent = st.session_state.agent_sales processed_files = sess['processed_files_sales'] elif mode == "supplychain": agent = st.session_state.agent_supplychain processed_files = sess['processed_files_supplychain'] elif mode == "qa": agent = st.session_state.agent_qa processed_files = sess['processed_files_qa'] # Update agent with custom prompts if used if generate_mode: agent.prompt_summary = sess['custom_prompts'][mode]['summary'] agent.prompt_analyze = sess['custom_prompts'][mode]['analyze'] agent.prompt_detail = sess['custom_prompts'][mode]['detail'] st.toast(f"Using custom prompts for {mode} analysis") else: # Reset to default prompts if mode == "overall": agent.prompt_summary = OverallAgent.prompt_summary agent.prompt_analyze = OverallAgent.prompt_analyze agent.prompt_detail = OverallAgent.prompt_detail elif mode == "tariff": agent.prompt_summary = TariffTradeAgent.prompt_summary agent.prompt_analyze = TariffTradeAgent.prompt_analyze agent.prompt_detail = TariffTradeAgent.prompt_detail elif mode == "sales": agent.prompt_summary = SalesAgent.prompt_summary agent.prompt_analyze = SalesAgent.prompt_analyze agent.prompt_detail = SalesAgent.prompt_detail elif mode == "supplychain": agent.prompt_summary = SupplyChainAgent.prompt_summary agent.prompt_analyze = SupplyChainAgent.prompt_analyze agent.prompt_detail = SupplyChainAgent.prompt_detail elif mode == "qa": agent.prompt_summary = QAAgent.prompt_summary agent.prompt_analyze = QAAgent.prompt_analyze agent.prompt_detail = QAAgent.prompt_detail with st.spinner(f"🔍 Analyzing {mode.replace('supplychain', 'supply chain').replace('qa', 'Q&A')} documents..."): analyze_documents( mode, agent, processed_files, sess ) # --- Main Display --- last_mode = sess['last_analysis_mode'] if last_mode is None: st.info("Select an analysis type to begin.") return # Consolidated data setup mode_config = { 'overall': { 'files': sess['processed_files_overall'], 'summary': sess['consolidated_summary_overall'], 'sidebar_header': "Overall Topics", 'main_header': "🌟 Executive Summary", 'agent': st.session_state.agent_overall }, 'tariff': { 'files': sess['processed_files_tariff'], 'summary': sess['consolidated_summary_tariff'], 'sidebar_header': "Tariff Topics", 'main_header': "🌟 Tariff Analysis", 'agent': st.session_state.agent_tariff }, 'sales': { 'files': sess['processed_files_sales'], 'summary': sess['consolidated_summary_sales'], 'sidebar_header': "Sales Topics", 'main_header': "🌟 Sales Analysis", 'agent': st.session_state.agent_sales }, 'supplychain': { 'files': sess['processed_files_supplychain'], 'summary': sess['consolidated_summary_supplychain'], 'sidebar_header': "Supply Chain Topics", 'main_header': "🌟 Supply Chain Analysis", 'agent': st.session_state.agent_supplychain }, 'qa': { 'files': sess['processed_files_qa'], 'summary': sess['consolidated_summary_qa'], 'sidebar_header': "Q&A by Document", 'main_header': "❓ Questions & Answers", 'agent': st.session_state.agent_qa } } current_mode = mode_config[last_mode] # --- Sidebar Topics --- st.sidebar.header(current_mode['sidebar_header']) if last_mode == "overall": topics_by_file = {} for filename, filedata in current_mode['files'].items(): for topic in filedata["topics"]: topics_by_file.setdefault(topic['name'], []).append({ 'file': filename, 'score': topic['score'] }) a = sorted(topics_by_file.items(), key=lambda x: max(x[1], key=lambda y: y['score'])['score'], reverse=True) before_view_more , after_view_more = a[:3] , a[3:] for topic_name, occurrences in before_view_more: total_score = sum(occ['score'] for occ in occurrences) file_count = len(occurrences) btn_label = f"{topic_name} (📈 {total_score:.1f} | 📑 {file_count})" if st.sidebar.button( btn_label, key=f"overall_topic_{topic_name}", use_container_width=True, ): sess['active_topic'] = topic_name sess['active_file'] = None if st.sidebar.button('View More',key = '1234' , use_container_width=True): for topic_name, occurrences in after_view_more: total_score = sum(occ['score'] for occ in occurrences) file_count = len(occurrences) btn_label = f"{topic_name} (📈 {total_score:.1f} | 📑 {file_count})" if st.sidebar.button( btn_label, key=f"overall_topic_more_{topic_name}", use_container_width=True, ): sess['active_topic'] = topic_name sess['active_file'] = None elif last_mode == "qa": st.sidebar.subheader("Documents with Q&A") for filename in current_mode['files']: if st.sidebar.button( filename, key=f"qa_doc_{filename}", use_container_width=True ): sess['active_file'] = filename sess['active_topic'] = None else: for filename, filedata in current_mode['files'].items(): expanded = (filename == sess['active_file']) with st.sidebar.expander(f"📄 {filename}", expanded=expanded): topics = sorted(filedata["topics"], key=lambda t: t["score"], reverse=True) for topic in topics[:3]: is_selected = ( sess['active_file'] == filename and sess['active_topic'] == topic['name'] ) style = "primary" if is_selected else "secondary" if st.button( f"• {topic['name']} (Score: {topic['score']})", key=f"{last_mode}_topic_{filename}_{topic['name']}", type=style, use_container_width=True, ): sess['active_file'] = filename sess['active_topic'] = topic['name'] if len(topics) > 3 and st.sidebar.button(f'View More for {filename}',key = f'{filename}_view_more' ,use_container_width=True): for topic in topics[3:]: is_selected = ( sess['active_file'] == filename and sess['active_topic'] == topic['name'] ) style = "primary" if is_selected else "secondary" if st.button( f"• {topic['name']} (Score: {topic['score']})", key=f"{last_mode}_topic_more_{filename}_{topic['name']}", type=style, use_container_width=True, ): sess['active_file'] = filename sess['active_topic'] = topic['name'] # --- Topic Analysis --- st.subheader("Detailed Analysis") if last_mode == "overall" and sess['active_topic']: mentions = [] for filename, filedata in current_mode['files'].items(): for topic in filedata["topics"]: if topic['name'] == sess['active_topic']: mentions.append({ 'file': filename, 'summary': topic.get('summary', ''), 'score': topic['score'], 'context': filedata['context'] }) with st.expander("📊 Topic Prevalence"): cols = st.columns(3) cols[0].metric("Total Documents", len(mentions)) avg_relevance = (sum(m['score'] for m in mentions)/len(mentions)) if mentions else 0 cols[1].metric("Average Relevance", f"{avg_relevance:.1f}") cols[2].metric("First Mentioned", mentions[0]['file'] if mentions else "N/A") if mentions: combined_context = "\n\n".join(f"=== {m['file']} ===\n{m['context']}" for m in mentions) key_cache = (last_mode, sess['active_topic']) if key_cache in sess['topic_details_cache']: st.markdown(sess['topic_details_cache'][key_cache]) else: placeholder = st.empty() collected_text = "" try: for chunk in current_mode['agent'].generate_topic_detail(combined_context, sess['active_topic']): collected_text = chunk placeholder.markdown(collected_text + (" ▌" if "▌" in collected_text else "")) sess['topic_details_cache'][key_cache] = collected_text except Exception as e: st.error(f"Analysis error: {str(e)}") elif last_mode == "qa" and sess['active_file']: st.subheader(f"Q&A for {sess['active_file']}") filedata = current_mode['files'].get(sess['active_file']) if filedata and "topics" in filedata: # Display Q&A pairs for qa in filedata["topics"]: with st.expander(f"**Q:** {qa['question']}"): st.markdown(f"**A:** {qa['answer']}") st.caption(f"Asked by: {qa['asked_by']} | Answered by: {qa['answered_by']}") else: st.warning("Document not found in Q&A analysis") elif sess['active_file'] and sess['active_topic']: key_cache = (last_mode, sess['active_file'], sess['active_topic']) if key_cache in sess['topic_details_cache']: st.markdown(sess['topic_details_cache'][key_cache]) else: placeholder = st.empty() collected_text = "" try: for chunk in current_mode['agent'].generate_topic_detail( current_mode['files'][sess['active_file']]['context'], sess['active_topic'], ): collected_text = chunk placeholder.markdown(collected_text + (" ▌" if "▌" in collected_text else "")) sess['topic_details_cache'][key_cache] = collected_text except Exception as e: st.error(f"Analysis error: {str(e)}") else: st.info("Select a topic from the sidebar") st.markdown("---") # --- Consolidated Summary --- st.header(current_mode['main_header']) if current_mode['summary']: st.markdown(current_mode['summary']) else: st.info("Summary not available yet") st.divider() # --- Chat Interface --- st.subheader("💬 Document Chat") # File selection available_files = list(current_mode['files'].keys()) selected_files = st.multiselect( "Select documents for context:", available_files, key=f"chat_selector_{last_mode}" ) # Chat history for msg in sess['chat_history']: with st.chat_message(msg["role"]): st.markdown(msg["content"]) # Question handling question = st.chat_input("Ask about the documents...") if question: if not selected_files: st.error("Please select documents first") st.stop() sess['chat_history'].append({ "role": "user", "content": question, "timestamp": datetime.utcnow().isoformat(), }) try: context = "\n\n".join([ f"=== {fname} ===\n{current_mode['files'][fname]['context']}" for fname in selected_files ]) with st.chat_message("assistant"): response_placeholder = st.empty() full_response = "" q_type = None for chunk, q_type in st.session_state.chat_agent.generate_answer(question, context): full_response = chunk response_placeholder.markdown(full_response + " ▌") response_placeholder.markdown(full_response) sess['chat_history'].append({ "role": "assistant", "content": full_response, "timestamp": datetime.utcnow().isoformat(), 'analysis_type': q_type }) except Exception as e: st.error(f"Chat error: {str(e)}") sess['chat_history'].append({ "role": "assistant", "content": f"Error: {str(e)}", "timestamp": datetime.utcnow().isoformat(), }) # Reset button if st.button("🔄 Reset Session", type="secondary"): # Preserve long-lived objects preserved_keys = [ "client", "agent_overall", "agent_tariff", "agent_sales", "agent_supplychain", "agent_qa", "chat_agent", "provider" ] preserved = {k: st.session_state[k] for k in preserved_keys if k in st.session_state} # Clear entire session state st.session_state.clear() # Restore preserved keys st.session_state.update(preserved) # Reset session data st.session_state.session = { 'uploaded_files': {}, 'processed_files_overall': {}, 'processed_files_tariff': {}, 'processed_files_sales': {}, 'processed_files_supplychain': {}, 'processed_files_qa': {}, 'active_file': None, 'active_topic': None, 'topic_details_cache': {}, 'chat_history': [], 'consolidated_summary_overall': None, 'consolidated_summary_tariff': None, 'consolidated_summary_sales': None, 'consolidated_summary_supplychain': None, 'consolidated_summary_qa': None, 'last_analysis_mode': None, 'custom_prompt_enabled': {}, 'custom_prompt_text': {} } # Trigger rerun st.rerun()if name == "main": main()
i do not need generate_consolidated_summary_from_topics what is required is only analyze_document get all the question present in QUESTION AND ANSWER SECTION from each file need to get all the questions present as clubed as topics
-
- Assistant
If your goal is to extract all questions from the QUESTION AND ANSWER section of each document — specifically from each file separately — and present those questions as topics (without needing to generate a consolidated summary or additional processing), then here's what you want:
- Modify your QA agent and the main workflow to only run analyze_document on each file independently.
- Have the analyze_document function output a list of Q&A pairs per document (including question text, asked by, answer text, and answered by).
- Instead of "topics," store these extracted questions as topics or clusters associated with each document.
- Remove or skip any calls to
generate_consolidated_summary_from_topics. - Change the sidebar display to list per-document extracted questions (without summaries) so the user can see all questions extracted from each file.
- In the UI main area, upon selecting a file, display the full list of extracted Q&A pairs from that file.
How to implement this in your existing setup?
1. Keep QAAgent as is, with
analyze_documentreturning Q&A pairs list per file.Your QAAgent presumably returns Q&A data structured roughly like:
[ { "question": "What is the revenue guidance for next quarter?", "asked_by": "Analyst John", "answer": "We expect around $5 billion.", "answered_by": "CEO Jane", "sequence": 1 }, ... ]If not structured as above, ensure output of
analyze_documentreturns a Python list or dictionary of extracted Q&A objects.
2. Update the
analyze_documentsfunctionCurrently, you have:
def analyze_documents(mode, agent, processed_files, sess, custom_prompt=None): # ... topics = agent.analyze_document(text, custom_prompt) # returns processed data per file processed_files[filename] = { "text": text, "topics": topics, "context": text, } # ... # You call generate_consolidated_summary_from_topics here which you want to removeModification:
- Remove the call to
generate_consolidated_summary_from_topics. - Store the results of
analyze_documentunderprocessed_files[filename]['topics'](which will now be a list of Q&A pairs). - Do not generate or store any summary.
def analyze_documents(mode, agent, processed_files, sess, custom_prompt=None): for filename, file_bytes in sess['uploaded_files'].items(): if filename not in processed_files: try: file_obj = BytesIO(file_bytes) file_obj.name = filename text = extract_text(file_obj) if text: # Extract Q&A pairs per document (topics = list of dicts) topics = agent.analyze_document(text, custom_prompt) processed_files[filename] = { "text": text, "topics": topics, # This is the list of Q&A pairs "context": text, } st.toast(f"✅ Processed {filename}") else: st.error(f"❌ Failed to extract text for {filename}") except Exception as e: st.error(f"Error processing {filename}: {str(e)}") # No summary generation for 'qa' mode or any other if not desired sess['last_analysis_mode'] = mode sess['active_file'] = None sess['active_topic'] = None st.success(f"Analysis completed for {mode.replace('qa', 'Q&A')}.")
3. Update main UI to display the extracted questions as "topics" per document
In your sidebar for mode "qa", you already have:
elif last_mode == "qa": st.sidebar.subheader("Documents with Q&A") for filename in current_mode['files']: if st.sidebar.button( filename, key=f"qa_doc_{filename}", use_container_width=True ): sess['active_file'] = filename sess['active_topic'] = NoneThis is fine.
In the main detailed analysis area:
elif last_mode == "qa" and sess['active_file']: st.subheader(f"Q&A for {sess['active_file']}") filedata = current_mode['files'].get(sess['active_file']) if filedata and "topics" in filedata: # Display Q&A pairs for qa in filedata["topics"]: with st.expander(f"**Q:** {qa['question']}"): st.markdown(f"**A:** {qa['answer']}") st.caption(f"Asked by: {qa['asked_by']} | Answered by: {qa['answered_by']}") else: st.warning("Document not found in Q&A analysis")This is aligned perfectly with what you want — listing extracted questions per document with the full Q&A.
If you want, you can rename
qa['asked_by']andqa['answered_by']keys to match what your QA Agent returns.
4. Skip any consolidated summary usage/display for
qamode- Don't call
generate_consolidated_summary_from_topics. - Don't display any consolidated summary.
- Your current main.py already does this if you just don't call these functions for 'qa' mode (or if your
analyze_documents()skips the summary generation).
Summary of key points:
- Use
QAAgent.analyze_documentfor per-file extraction. - Store the extracted Q&A pairs per document in
processed_files_qa. - Do NOT call or use
generate_consolidated_summary_from_topicsfor the Q&A. - Sidebar lists document names for
qamode. - Main display lists all Q&A pairs extracted from the selected document.
- NO consolidated summary needed or shown for Q&A.
Optional: If needed, adjust QAAgent to provide consistent output format
If your QAAgent returns a raw string or a formatted text output, wrap or parse that output back into structured data — e.g., a list of dicts with
question,asked_by,answer,answered_by.Example:
def analyze_document(self, text, custom_prompt=None): raw_output = super().analyze_document(self.prompt_sys, self.prompt_analyze, text) # parse raw_output into structured list qas = parse_qas_from_raw_text(raw_output) return qas(Implement
parse_qas_from_raw_textaccording to the output format.)
If you want help writing that parsing code or further UI improvements for your Q&A mode, just ask!