init1

.gitignore

@@ -0,0 +1,34 @@
+__pycache__/
+
+
+.Python
+build/
+venv/
+ENV/
+env/
+.env
+.venv
+env.bak/
+venv.bak/
+.python-version
+
+# IPython
+profile_default/
+ipython_config.py
+
+# Logs
+*.log
+logs/
+log/
+
+
+.DS_Store
+.project
+.pydevproject
+
+*.db
+*.rdb
+
+.env
+
+.ruff_cache

agent.py

@@ -0,0 +1,103 @@
+import logging
+
+from langchain_core.messages import HumanMessage, SystemMessage
+from langchain_groq import ChatGroq
+from langchain_huggingface import (
+    ChatHuggingFace,
+    HuggingFaceEmbeddings,
+    HuggingFaceEndpoint,
+)
+from langgraph.graph import START, MessagesState, StateGraph
+from langgraph.prebuilt import ToolNode, tools_condition
+
+from tools import tools
+
+logger = logging.getLogger(__name__)
+
+
+# ----- Initializing vector store and retriever tool -------
+
+with open("system_prompt.txt", encoding="utf-8") as f:
+    system_prompt = f.read()
+print(system_prompt)
+
+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"""
+    if provider == "groq":
+        llm = ChatGroq(model="qwen/qwen3-32b", temperature=0)
+    elif provider == "huggingface":
+        llm = ChatHuggingFace(
+            llm=HuggingFaceEndpoint(
+                repo_id="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+                task="text-generation",
+                max_new_tokens=1024,
+                temperature=0,
+            ),
+            verbose=True,
+        )
+    else:
+        raise ValueError("Invalid provider. Choose 'groq' or 'huggingface'.")
+    llm_with_tools = llm.bind_tools(tools)
+
+    # 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)
+
+        if similar_question:
+            example_msg = HumanMessage(
+                content=f"Here I provide a similar question and answer for reference: \n\n{similar_question[0].page_content}",
+            )
+            return {"messages": [sys_msg] + state["messages"] + [example_msg]}
+        # no similar questions are found
+        return {"messages": [sys_msg] + state["messages"]}
+
+    builder = StateGraph(MessagesState)
+    builder.add_node("retriever", retriever)
+    builder.add_node("assistant", assistant)
+    builder.add_node("tools", ToolNode(tools))
+    builder.add_edge(START, "retriever")
+    builder.add_edge("retriever", "assistant")
+    builder.add_conditional_edges(
+        "assistant",
+        tools_condition,
+    )
+    builder.add_edge("tools", "assistant")
+
+    return builder.compile()
+
+
+if __name__ == "__main__":
+    question = "If Ada Lovelace was born in 1815 and Charles Babbage died in 1871, how old was she when he died?"
+    graph = build_graph(provider="groq")
+    messages = [HumanMessage(content=question)]
+    messages = graph.invoke({"messages": messages})
+    for m in messages["messages"]:
+        m.pretty_print()

app.py

@@ -1,15 +1,12 @@
 import os
+
 import gradio as gr
-import requests
-import inspect
 import pandas as pd
+import requests
 
-# (Keep Constants as is)
-# --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+# --- Agent Definition ---
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
@@ -91,7 +88,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         print("Agent did not produce any answers to submit.")
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
-    # 4. Prepare Submission 
+    # 4. Prepare Submission
     submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
     status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
     print(status_update)
@@ -140,7 +137,6 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         return status_message, results_df
 
 
-# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
     gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
@@ -163,7 +159,6 @@ with gr.Blocks() as demo:
     run_button = gr.Button("Run Evaluation & Submit All Answers")
 
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
     run_button.click(
@@ -193,4 +188,4 @@ if __name__ == "__main__":
     print("-"*(60 + len(" App Starting ")) + "\n")
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    demo.launch(debug=True, share=False)

pyproject.toml

@@ -0,0 +1,30 @@
+[project]
+name = "infersense"
+version = "0.1.0"
+authors = [{ name = "Semih Berkay Ozturk" }]
+dependencies = [
+    "gradio>=5.38.1",
+    "langchain-community>=0.3.27",
+    "langchain-groq>=0.3.6",
+    "langchain-huggingface>=0.3.1",
+    "langgraph>=0.5.4",
+    "polars>=1.31.0",
+    "pytesseract>=0.3.13",
+]
+
+[tool.ruff.lint]
+extend-select = [
+    "F",        # Pyflakes rules
+    "W",        # PyCodeStyle warnings
+    "E",        # PyCodeStyle errors
+    "I",        # Sort imports properly
+    "UP",       # Warn if certain things can changed due to newer Python versions
+    "C4",       # Catch incorrect use of comprehensions, dict, list, etc
+    "FA",       # Enforce from __future__ import annotations
+    "ISC",      # Good use of string concatenation
+    "ICN",      # Use common import conventions
+    "RET",      # Good return practices
+    "SIM",      # Common simplification rules
+    "TID",      # Some good import practices
+    "TC",       # Enforce importing certain types in a TYPE_CHECKING block
+]

requirements.txt

@@ -1,2 +0,0 @@
-gradio
-requests

system_prompt.txt

@@ -0,0 +1,9 @@
+You are an helpful assistant tasked with answering questions precisely and concisely by reasoning and, when needed, using available tools to find information.
+When given a question, think carefully, decide if a tool call is necessary, and use tools to gather information before answering.
+Once you have enough information, respond with only the final answer in this format:
+FINAL ANSWER: [YOUR FINAL ANSWER]
+Your FINAL ANSWER should be a number OR a few words OR a comma-separated list of numbers and/or words.
+If a number is requested, do not include commas, currency symbols, or units unless explicitly asked.
+If a string is requested, avoid articles and abbreviations, and write digits as plain text unless specified otherwise.
+For lists, apply these rules to each element accordingly.
+Only output the line starting with "FINAL ANSWER:" followed immediately by your answer, nothing else.

tools.py

@@ -0,0 +1,196 @@
+import polars as pl
+import pytesseract
+from langchain_community.document_loaders import ArxivLoader, WikipediaLoader
+from langchain_community.tools.tavily_search import TavilySearchResults
+from langchain_core.tools import tool
+from PIL import Image
+
+# --------- Basic Math tools ---------
+
+@tool
+def add(a: float, b: float) -> float:
+    """
+    Add two numbers.
+    Args:
+        a (float): the first number
+        b (float): the second number
+    """
+    return a + b
+
+@tool
+def subtract(a: float, b: float) -> int:
+    """
+    Subtract two numbers.
+    Args:
+        a (float): the first number
+        b (float): the second number
+    """
+    return a - b
+
+@tool
+def multiply(a: float, b: float) -> float:
+    """
+    Multiplies two numbers.
+    Args:
+        a (float): the first number
+        b (float): the second number
+    """
+    return a * b
+
+@tool
+def divide(a: float, b: float) -> float:
+    """
+    Divides two numbers.
+    Args:
+        a (float): the first float number
+        b (float): the second float number
+    """
+    if b == 0:
+        raise ValueError("Cannot divided by zero.")
+    return a / b
+
+
+@tool
+def modulus(a: int, b: int) -> int:
+    """
+    Get the modulus of two numbers.
+    Args:
+        a (int): the first number
+        b (int): the second number
+    """
+    return a % b
+
+
+@tool
+def power(a: float, b: float) -> float:
+    """
+    Get the power of two numbers.
+    Args:
+        a (float): the first number
+        b (float): the second number
+    """
+    return a**b
+
+# ------- Search Tools -------
+
+@tool
+def arxiv_search(query: str) -> str:
+    """Search Arxiv for a query and return maximum 3 result.
+    Args:
+        query: The search query."""
+    search_docs = ArxivLoader(query=query, load_max_docs=3).load()
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
+            for doc in search_docs
+        ]
+    )
+    return {"arxiv_results": formatted_search_docs}
+
+@tool
+def web_search(query: str) -> str:
+    """Search the Web via Tavily for a query and return 3 results in maximum.
+    Args:
+        query: The search query."""
+    search_docs = TavilySearchResults(max_results=3).invoke(query)
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata.get("url", "")}" title="{doc.get("title", "")}"/>\n{doc.get("content", "")}\n</Document>'
+            for doc in search_docs
+        ]
+    )
+    return {"web_results": formatted_search_docs}
+
+@tool
+def wikipedia_search(query: str) -> str:
+    """Search Wikipedia for a query and return maximum 3 results.
+    Args:
+        query: The search query."""
+    search_docs = WikipediaLoader(query=query, load_max_docs=3).load()
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
+            for doc in search_docs
+        ])
+    return {"wiki_results": formatted_search_docs}
+
+# ------ Document Processing Tools ------
+
+@tool
+def extract_text_from_image(image_path: str) -> str:
+    """
+    Extract text from an image by using pytesseract via OCR.
+    Args:
+        image_path (str): the path to the image file.
+    """
+    try:
+        image = Image.open(image_path)
+        text = pytesseract.image_to_string(image)
+
+        return f"Extracted the text from image:\n\n{text}"
+    except Exception as e:
+        return f"Error extracting text from image: {str(e)}"
+
+
+@tool
+def analyze_csv_file(file_path: str, query: str) -> str:
+    """
+    Analyze a CSV file by using Polars and answer a question about it.
+    Args:
+        file_path (str): the path to the CSV file.
+        query (str): Question about the data
+    """
+    try:
+        df = pl.read_csv(file_path)
+
+        result = f"CSV file loaded with {len(df)} rows and {len(df.columns)} columns.\n"
+        result += f"Columns: {', '.join(df.columns)}\n\n"
+
+        result += "Summary statistics:\n"
+        result += str(df.describe())
+
+        return result
+
+    except Exception as e:
+        return f"Error occured analyzing CSV file: {str(e)}"
+
+
+@tool
+def analyze_excel_file(file_path: str, query: str) -> str:
+    """
+    Analyze an Excel file using Polars and answer a question about it.
+    Args:
+        file_path (str): the path to the Excel file.
+        query (str): Question about the data
+    """
+    try:
+        df = pl.read_excel(file_path)
+
+        result = (
+            f"Excel file loaded with {len(df)} rows and {len(df.columns)} columns.\n"
+        )
+        result += f"Columns: {', '.join(df.columns)}\n\n"
+
+        result += "Summary statistics:\n"
+        result += str(df.describe())
+
+        return result
+
+    except Exception as e:
+        return f"Error occured analyzing Excel file: {str(e)}"
+
+
+tools = [
+    multiply,
+    add,
+    subtract,
+    divide,
+    modulus,
+    power,
+    web_search,
+    wikipedia_search,
+    arxiv_search,
+    extract_text_from_image,
+    analyze_csv_file,
+    analyze_excel_file,
+]