duckdb

agent.py

@@ -1,5 +1,4 @@
 import logging
-
 from langchain_core.messages import HumanMessage, SystemMessage
 from langchain_groq import ChatGroq
 from langchain_huggingface import (
@@ -9,12 +8,15 @@ from langchain_huggingface import (
 )
 from langgraph.graph import START, MessagesState, StateGraph
 from langgraph.prebuilt import ToolNode, tools_condition
+from langchain_community.vectorstores import DuckDB
+from langchain.tools.retriever import create_retriever_tool
+from langchain_core.documents import Document
+import uuid
 
 from tools import tools
 
 logger = logging.getLogger(__name__)
 
-
 # ----- Initializing vector store and retriever tool -------
 
 with open("system_prompt.txt", encoding="utf-8") as f:
@@ -25,24 +27,7 @@ sys_msg = SystemMessage(content=system_prompt)
 
 embeddings = HuggingFaceEmbeddings(
     model_name="sentence-transformers/all-mpnet-base-v2"
-)  #  dim=768
-
-'''
-supabase: Client = create_client(
-    os.environ.get("SUPABASE_URL"), os.environ.get("SUPABASE_SERVICE_ROLE_KEY")
-)
-vector_store = SupabaseVectorStore(
-    client=supabase,
-    embedding=embeddings,
-    table_name="documents2",
-    query_name="match_documents_2",
-)
-create_retriever_tool = create_retriever_tool(
-    retriever=vector_store.as_retriever(),
-    name="Question Search",
-    description="A tool to retrieve similar questions from a vector store.",
 )
-'''
 
 def build_graph(provider: str = "groq"):
     """Build the graph"""
@@ -62,22 +47,44 @@ def build_graph(provider: str = "groq"):
         raise ValueError("Invalid provider. Choose 'groq' or 'huggingface'.")
     llm_with_tools = llm.bind_tools(tools)
 
+    def convert_messages_to_documents(messages: list[HumanMessage]) -> list[Document]:
+        return [
+            Document(
+                page_content=msg.content,
+                metadata={"role": "user", "index": idx, "id": str(uuid.uuid4())}
+            )
+            for idx, msg in enumerate(messages)
+        ]
+    
+
     # Node
     def assistant(state: MessagesState):
         """Assistant node"""
         return {"messages": [llm_with_tools.invoke(state["messages"])]}
 
+    
     def retriever(state: MessagesState):
-        """Retriever node"""
-        similar_question = vector_store.similarity_search(state["messages"][0].content)
+        """Retriever node using DuckDB"""
+        docs = convert_messages_to_documents(state["messages"])
+        vector_store = DuckDB.from_documents(docs, embedding=embeddings)
+
+        create_retriever_tool = create_retriever_tool(
+            retriever=vector_store.as_retriever(),
+            name="Question Search",
+            description="A tool to retrieve similar questions from a vector store.",
+        )
 
-        if similar_question:
+        query = state["messages"][0].content
+        similar = vector_store.similarity_search(query)
+
+        if similar:
             example_msg = HumanMessage(
-                content=f"Here I provide a similar question and answer for reference: \n\n{similar_question[0].page_content}",
+                content=f"Here I provide a similar question and answer for reference: \n\n{similar[0].page_content}"
             )
             return {"messages": [sys_msg] + state["messages"] + [example_msg]}
-        # no similar questions are found
-        return {"messages": [sys_msg] + state["messages"]}
+        else:
+            return {"messages": [sys_msg] + state["messages"]}
+
 
     builder = StateGraph(MessagesState)
     builder.add_node("retriever", retriever)

app.py

@@ -3,22 +3,27 @@ import os
 import gradio as gr
 import pandas as pd
 import requests
+from agent import build_graph
+from langchain_core.messages import HumanMessage
 
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Agent Definition ---
-class BasicAgent:
+class InfersenseAgent:
+    """A langgraph based agent."""
     def __init__(self):
-        print("BasicAgent initialized.")
+        print("InfersenseAgent initialized.")
+        self.graph = build_graph()
+
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
+        messages = [HumanMessage(content=question)]
+        messages = self.graph.invoke({"messages": messages})
+        answer = messages['messages'][-1].content
+        return answer[14:]
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    Fetches all questions, runs the Infersense agent on them, submits all answers,
     and displays the results.
     """
     # --- Determine HF Space Runtime URL and Repo URL ---
@@ -35,9 +40,9 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # 1. Instantiate Agent
     try:
-        agent = BasicAgent()
+        agent = InfersenseAgent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
@@ -66,7 +71,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         print(f"An unexpected error occurred fetching questions: {e}")
         return f"An unexpected error occurred fetching questions: {e}", None
 
-    # 3. Run your Agent
+    # 3. Run
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")