Update app.py

app.py

@@ -1,332 +1,50 @@
-# app.py
-# Multi-Agent Chatbot with LangGraph, DeepSeek-R1, Function Calls, and Agentic RAG
-# Using local (in-memory) Chroma to avoid tenant errors.
-#
-# Ensure that the environment variables OPENAI_API_KEY and DEEP_SEEK_API are set in your HF Space Secrets.
-
-import os
-import re
-import logging
 import streamlit as st
-import requests
-from typing import Sequence
-from typing_extensions import TypedDict, Annotated
-
-# LangChain imports
-from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain.vectorstores import Chroma
-from langchain.schema import HumanMessage, AIMessage
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.tools.retriever import create_retriever_tool
-
-# Chroma in-memory settings
-from chromadb.config import Settings
-
-# LangGraph imports
-from langgraph.graph import END, StateGraph, START
-from langgraph.prebuilt import ToolNode
-from langgraph.graph.message import add_messages
-
-# Configure logging
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-# --- Dummy Data Setup ---
-research_texts = [
-    "Research Report: Results of a New AI Model Improving Image Recognition Accuracy to 98%",
-    "Academic Paper Summary: Why Transformers Became the Mainstream Architecture in Natural Language Processing",
-    "Latest Trends in Machine Learning Methods Using Quantum Computing"
-]
-
-development_texts = [
-    "Project A: UI Design Completed, API Integration in Progress",
-    "Project B: Testing New Feature X, Bug Fixes Needed",
-    "Product Y: In the Performance Optimization Stage Before Release"
-]
-
-# --- Chroma Client Settings (in-memory) ---
-client_settings = Settings(
-    chroma_api_impl="local",
-    persist_directory=None  # Use None for ephemeral in-memory DB; or specify a folder to persist data.
-)
-
-# --- Preprocessing & Embeddings ---
-splitter = RecursiveCharacterTextSplitter(chunk_size=100, chunk_overlap=10)
-research_docs = splitter.create_documents(research_texts)
-development_docs = splitter.create_documents(development_texts)
-
-embeddings = OpenAIEmbeddings(
-    model="text-embedding-3-large",
-    openai_api_key=os.environ.get("OPENAI_API_KEY")  # Set this in your HF Secrets.
-)
-
-# Create vector stores using local in-memory Chroma
-research_vectorstore = Chroma.from_documents(
-    documents=research_docs,
-    embedding=embeddings,
-    collection_name="research_collection",
-    client_settings=client_settings
-)
-development_vectorstore = Chroma.from_documents(
-    documents=development_docs,
-    embedding=embeddings,
-    collection_name="development_collection",
-    client_settings=client_settings
-)
-
-research_retriever = research_vectorstore.as_retriever()
-development_retriever = development_vectorstore.as_retriever()
-
-research_tool = create_retriever_tool(
-    research_retriever,
-    "research_db_tool",
-    "Search information from the research database."
-)
-development_tool = create_retriever_tool(
-    development_retriever,
-    "development_db_tool",
-    "Search information from the development database."
-)
-
-tools = [research_tool, development_tool]
-
-# --- Agent and Workflow Functions ---
-# Use only AIMessage and HumanMessage for message types.
-class AgentState(TypedDict):
-    messages: Annotated[Sequence[AIMessage | HumanMessage], add_messages]
-
-def agent(state: AgentState):
-    logger.info("Agent invoked")
-    messages = state["messages"]
-    user_message = messages[0][1] if isinstance(messages[0], tuple) else messages[0].content
 
-    prompt = f"""Given this user question: "{user_message}"
-If it's about research or academic topics, respond EXACTLY in this format:
-SEARCH_RESEARCH: <search terms>
-
-If it's about development status, respond EXACTLY in this format:
-SEARCH_DEV: <search terms>
-
-Otherwise, just answer directly.
-"""
-    headers = {
-        "Accept": "application/json",
-        "Authorization": f"Bearer {os.environ.get('DEEP_SEEK_API')}",
-        "Content-Type": "application/json"
-    }
-    data = {
-        "model": "deepseek-chat",
-        "messages": [{"role": "user", "content": prompt}],
-        "temperature": 0.7,
-        "max_tokens": 1024
-    }
-    response = requests.post(
-        "https://api.deepseek.com/v1/chat/completions",
-        headers=headers,
-        json=data,
-        verify=False
-    )
-    if response.status_code == 200:
-        response_text = response.json()['choices'][0]['message']['content']
-        logger.info(f"DeepSeek response: {response_text}")
-        if "SEARCH_RESEARCH:" in response_text:
-            query = response_text.split("SEARCH_RESEARCH:")[1].strip()
-            results = research_retriever.invoke(query)
-            return {"messages": [AIMessage(content=f'Action: research_db_tool\n{{"query": "{query}"}}\n\nResults: {str(results)}')]}
-        elif "SEARCH_DEV:" in response_text:
-            query = response_text.split("SEARCH_DEV:")[1].strip()
-            results = development_retriever.invoke(query)
-            return {"messages": [AIMessage(content=f'Action: development_db_tool\n{{"query": "{query}"}}\n\nResults: {str(results)}')]}
-        else:
-            return {"messages": [AIMessage(content=response_text)]}
-    else:
-        error_msg = f"DeepSeek API call failed: {response.text}"
-        logger.error(error_msg)
-        raise Exception(error_msg)
-
-def simple_grade_documents(state: AgentState):
-    last_message = state["messages"][-1]
-    logger.info(f"Grading message: {last_message.content}")
-    if "Results: [Document" in last_message.content:
-        return "generate"
-    else:
-        return "rewrite"
-
-def generate(state: AgentState):
-    logger.info("Generating final answer")
-    messages = state["messages"]
-    question = messages[0].content if not isinstance(messages[0], tuple) else messages[0][1]
-    last_message = messages[-1]
-    docs = ""
-    if "Results: [" in last_message.content:
-        docs = last_message.content[last_message.content.find("Results: ["):]
-    headers = {
-        "Accept": "application/json",
-        "Authorization": f"Bearer {os.environ.get('DEEP_SEEK_API')}",
-        "Content-Type": "application/json"
-    }
-    prompt = f"""Based on these research documents, summarize the latest advancements in AI:
-Question: {question}
-Documents: {docs}
-Focus on extracting and synthesizing the key findings from the research papers.
-"""
-    data = {
-        "model": "deepseek-chat",
-        "messages": [{"role": "user", "content": prompt}],
-        "temperature": 0.7,
-        "max_tokens": 1024
-    }
-    response = requests.post(
-        "https://api.deepseek.com/v1/chat/completions",
-        headers=headers,
-        json=data,
-        verify=False
-    )
-    if response.status_code == 200:
-        response_text = response.json()['choices'][0]['message']['content']
-        return {"messages": [AIMessage(content=response_text)]}
-    else:
-        error_msg = f"DeepSeek API generate call failed: {response.text}"
-        logger.error(error_msg)
-        raise Exception(error_msg)
-
-def rewrite(state: AgentState):
-    logger.info("Rewriting question")
-    original_question = state["messages"][0].content if state["messages"] else "N/A"
-    headers = {
-        "Accept": "application/json",
-        "Authorization": f"Bearer {os.environ.get('DEEP_SEEK_API')}",
-        "Content-Type": "application/json"
-    }
-    data = {
-        "model": "deepseek-chat",
-        "messages": [{"role": "user", "content": f"Rewrite this question to be more specific and clearer: {original_question}"}],
-        "temperature": 0.7,
-        "max_tokens": 1024
-    }
-    response = requests.post(
-        "https://api.deepseek.com/v1/chat/completions",
-        headers=headers,
-        json=data,
-        verify=False
-    )
-    if response.status_code == 200:
-        response_text = response.json()['choices'][0]['message']['content']
-        return {"messages": [AIMessage(content=response_text)]}
-    else:
-        error_msg = f"DeepSeek API rewrite call failed: {response.text}"
-        logger.error(error_msg)
-        raise Exception(error_msg)
-
-tools_pattern = re.compile(r"Action: .*")
-def custom_tools_condition(state: AgentState):
-    last_message = state["messages"][-1]
-    if tools_pattern.match(last_message.content):
-        return "tools"
-    return END
-
-# Build the workflow with LangGraph's StateGraph
-workflow = StateGraph(AgentState)
-workflow.add_node("agent", agent)
-retrieve_node = ToolNode(tools)
-workflow.add_node("retrieve", retrieve_node)
-workflow.add_node("rewrite", rewrite)
-workflow.add_node("generate", generate)
-workflow.add_edge(START, "agent")
-workflow.add_conditional_edges("agent", custom_tools_condition, {"tools": "retrieve", END: END})
-workflow.add_conditional_edges("retrieve", simple_grade_documents)
-workflow.add_edge("generate", END)
-workflow.add_edge("rewrite", "agent")
-app_workflow = workflow.compile()
-
-def process_question(user_question, app, config):
-    events = []
-    for event in app.stream({"messages": [("user", user_question)]}, config):
-        events.append(event)
-    return events
-
-# --- Streamlit UI ---
 def main():
     st.set_page_config(
-        page_title="Multi-Agent Chatbot",
+        page_title="Enhanced Contrast Chatbot",
         layout="wide",
         initial_sidebar_state="expanded"
     )
 
-    # Simple CSS for improved visibility
+    # Custom CSS to improve text visibility
     st.markdown("""
-    <style>
-    .stApp {
-        background-color: #ffffff;
-    }
-    .stButton > button {
-        width: 100%;
-        margin-top: 20px;
-    }
-    .data-box {
-        padding: 20px;
-        border-radius: 10px;
-        margin: 10px 0;
-        background-color: #f0f0f0;
-    }
-    .research-box {
-        border-left: 5px solid #1976d2;
-        color: #111 !important;
-    }
-    .dev-box {
-        border-left: 5px solid #43a047;
-        color: #111 !important;
-    }
-    </style>
+        <style>
+        /* Force a white background for the main app area */
+        .stApp {
+            background-color: #ffffff !important;
+        }
+        
+        /* Make text darker for better contrast */
+        html, body, [class^="css"]  {
+            color: #111111 !important;
+        }
+
+        /* Adjust label text (like "Enter your question") */
+        .stTextArea label {
+            color: #111111 !important;
+        }
+
+        /* Make sure sidebar text is also dark */
+        .css-1v3fvcr {
+            color: #111111 !important;
+        }
+
+        /* Example: You can also adjust the background color of 
+           your "data-box" classes if needed */
+        .data-box {
+            background-color: #f0f0f0 !important;
+            color: #111111 !important;
+        }
+        </style>
     """, unsafe_allow_html=True)
 
-    # Sidebar with data
-    with st.sidebar:
-        st.header("📚 Available Data")
-        st.subheader("Research Database")
-        for text in research_texts:
-            st.markdown(f'<div class="data-box research-box">{text}</div>', unsafe_allow_html=True)
-        st.subheader("Development Database")
-        for text in development_texts:
-            st.markdown(f'<div class="data-box dev-box">{text}</div>', unsafe_allow_html=True)
-
-    st.title("🤖 Multi-Agent Chatbot")
-    st.markdown("---")
-
-    query = st.text_area("Enter your question:", height=100, placeholder="e.g., What is the latest advancement in AI research?")
-
-    col1, col2 = st.columns([1, 2])
-    with col1:
-        if st.button("🔍 Get Answer", use_container_width=True):
-            if query:
-                with st.spinner("Processing your question..."):
-                    events = process_question(query, app_workflow, {"configurable": {"thread_id": "1"}})
-                    for event in events:
-                        # Display processing steps
-                        if 'agent' in event:
-                            with st.expander("🔄 Processing Step", expanded=True):
-                                content = event['agent']['messages'][0].content
-                                if "Results:" in content:
-                                    st.markdown("### 📑 Retrieved Documents:")
-                                    docs = content[content.find("Results:"):]
-                                    st.info(docs)
-                        elif 'generate' in event:
-                            st.markdown("### ✨ Final Answer:")
-                            st.success(event['generate']['messages'][0].content)
-            else:
-                st.warning("⚠️ Please enter a question first!")
-    with col2:
-        st.markdown("""
-        ### 🎯 How to Use
-        1. Type your question in the text box.
-        2. Click "Get Answer" to process.
-        3. View retrieved documents and the final answer.
+    st.title("Enhanced Contrast Chatbot")
+    st.markdown("Try typing your question below to see if the text is clearer now:")
 
-        ### 💡 Example Questions
-        - What are the latest advancements in AI research?
-        - What is the status of Project A?
-        - What are the current trends in machine learning?
-        """)
+    user_query = st.text_area("Enter your question here:")
+    if st.button("Submit"):
+        st.write("Your query:", user_query)
 
 if __name__ == "__main__":
     main()