Update app.py

app.py

@@ -1,13 +1,6 @@
 # app.py
-# Advanced AI R&D Assistant for Hugging Face Spaces
-#
-# This app leverages LangGraph, DeepSeek-R1 via text-based function calling, and Agentic RAG.
-# API keys are securely loaded via environment variables.
-#
-# To deploy:
-# 1. Add your API key to Hugging Face Space secrets with the key DEEP_SEEK_API.
-# 2. Ensure your requirements.txt includes langchain-community.
-# 3. Run the app with Streamlit.
+# Multi-Agent Chatbot with LangGraph, DeepSeek-R1, Function Calls, and Agentic RAG
+# Using local (in-memory) Chroma to avoid tenant errors.
 
 import os
 import re
@@ -17,14 +10,17 @@ import requests
 from typing import Sequence
 from typing_extensions import TypedDict, Annotated
 
-# Updated imports for LangChain
+# 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
 
-# Imports for LangGraph remain the same
+# 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
@@ -46,22 +42,34 @@ development_texts = [
     "Product Y: In the Performance Optimization Stage Before Release"
 ]
 
+# --- Chroma Client Settings (in-memory) ---
+client_settings = Settings(
+    chroma_api_impl="local",
+    persist_directory=None  # Set to None for ephemeral in-memory DB
+)
+
 # --- 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")
+embeddings = OpenAIEmbeddings(
+    model="text-embedding-3-large",
+    openai_api_key=os.environ.get("OPENAI_API_KEY")  # Make sure your HF Space secret is set
+)
 
+# Create vector stores using local in-memory Chroma
 research_vectorstore = Chroma.from_documents(
     documents=research_docs,
     embedding=embeddings,
-    collection_name="research_collection"
+    collection_name="research_collection",
+    client_settings=client_settings
 )
 development_vectorstore = Chroma.from_documents(
     documents=development_docs,
     embedding=embeddings,
-    collection_name="development_collection"
+    collection_name="development_collection",
+    client_settings=client_settings
 )
 
 research_retriever = research_vectorstore.as_retriever()
@@ -77,11 +85,12 @@ development_tool = create_retriever_tool(
     "development_db_tool",
     "Search information from the development database."
 )
+
 tools = [research_tool, development_tool]
 
 # --- Agent and Workflow Functions ---
-# Note: We are using only AIMessage and HumanMessage for our message types.
 class AgentState(TypedDict):
+    # Using only AIMessage | HumanMessage
     messages: Annotated[Sequence[AIMessage | HumanMessage], add_messages]
 
 def agent(state: AgentState):
@@ -118,6 +127,8 @@ Otherwise, just answer directly.
     if response.status_code == 200:
         response_text = response.json()['choices'][0]['message']['content']
         logger.info(f"DeepSeek response: {response_text}")
+
+        # Format the response to call the right tool
         if "SEARCH_RESEARCH:" in response_text:
             query = response_text.split("SEARCH_RESEARCH:")[1].strip()
             results = research_retriever.invoke(query)
@@ -235,33 +246,87 @@ def process_question(user_question, app, config):
     return events
 
 # --- Streamlit UI ---
-import streamlit as st
-
 def main():
     st.set_page_config(
-        page_title="High Contrast Chatbot",
+        page_title="Multi-Agent Chatbot",
         layout="wide",
         initial_sidebar_state="expanded"
     )
 
-    # Force all text to be black (#000) and backgrounds to be white (#fff)
+    # Simple CSS for improved visibility
     st.markdown("""
     <style>
-    /* Apply to the entire app */
-    html, body, [class*="css"]  {
-        color: #000000 !important;          /* Black text */
-        background-color: #ffffff !important; /* White background */
-        text-shadow: none !important;       /* Remove any faint shadows */
+    .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>
     """, unsafe_allow_html=True)
 
-    st.title("High Contrast Chatbot")
-    st.markdown("Enter your question below. All text should now be clearly visible.")
+    # 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:
+                        # Step logs
+                        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.
 
-    user_query = st.text_area("Ask me something:")
-    if st.button("Submit"):
-        st.write("You asked:", user_query)
+        ### 💡 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?
+        """)
 
 if __name__ == "__main__":
     main()