Create app.py

app.py

@@ -0,0 +1,301 @@
+# app.py
+# Advanced Hugging Face Space – Multi-Agent Chatbot
+#
+# Developed with a forward-looking vision, inspired by Bill Gates’ drive for technological innovation.
+# This app leverages LangGraph, DeepSeek-R1 (via text-based function calling), and Agentic RAG to deliver
+# a multi-agent chatbot capable of autonomous reasoning and action.
+#
+# To deploy:
+# 1. Add your API keys to the Hugging Face Space secrets (e.g., DEEPSEEK_API_KEY).
+# 2. Install dependencies via a requirements.txt file.
+# 3. Enjoy a robust and scalable AI assistant for research and development.
+
+import os
+import re
+import logging
+import streamlit as st
+import requests
+from typing import Sequence
+from typing_extensions import TypedDict, Annotated
+
+from langchain_openai import OpenAIEmbeddings
+from langchain_community.vectorstores import Chroma
+from langchain_core.messages import HumanMessage, AIMessage, ToolMessage
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.tools.retriever import create_retriever_tool
+from langgraph.graph import END, StateGraph, START
+from langgraph.prebuilt import ToolNode
+from langgraph.graph.message import add_messages
+
+# Configure logging for better observability
+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"
+]
+
+# --- 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"
+)
+
+research_vectorstore = Chroma.from_documents(
+    documents=research_docs,
+    embedding=embeddings,
+    collection_name="research_collection"
+)
+development_vectorstore = Chroma.from_documents(
+    documents=development_docs,
+    embedding=embeddings,
+    collection_name="development_collection"
+)
+
+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 ---
+class AgentState(TypedDict):
+    messages: Annotated[Sequence[AIMessage | HumanMessage | ToolMessage], 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('DEEPSEEK_API_KEY')}",
+        "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('DEEPSEEK_API_KEY')}",
+        "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('DEEPSEEK_API_KEY')}",
+        "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 using 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="Advanced AI R&D Assistant", layout="wide", initial_sidebar_state="expanded")
+    st.markdown(
+        """
+        <style>
+        .stApp { background-color: #f8f9fa; }
+        .stButton > button { width: 100%; margin-top: 20px; }
+        .data-box { padding: 20px; border-radius: 10px; margin: 10px 0; }
+        .research-box { background-color: #e3f2fd; border-left: 5px solid #1976d2; }
+        .dev-box { background-color: #e8f5e9; border-left: 5px solid #43a047; }
+        </style>
+        """, unsafe_allow_html=True
+    )
+
+    # Sidebar: Display available 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("🤖 Advanced AI R&D Assistant")
+    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:
+                        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.
+            
+            ### 💡 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()