First version of Final-assigment from AI agents course

.gitignore

@@ -0,0 +1,115 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Virtual environments
+venv/
+ENV/
+env/
+.env
+.venv
+env.bak/
+venv.bak/
+.python-version
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+pytest-*.xml
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# Logs
+*.log
+logs/
+log/
+
+# IDE specific files
+.idea/
+.vscode/
+*.swp
+*.swo
+*~
+.DS_Store
+.project
+.pydevproject
+.settings/
+.vs/
+*.sublime-project
+*.sublime-workspace
+
+# Database
+*.db
+*.rdb
+*.sqlite
+*.sqlite3
+
+# Environment variables
+.env
+.env.local
+.env.development.local
+.env.test.local
+.env.production.local
+
+# macOS specific
+.DS_Store
+.AppleDouble
+.LSOverride
+Icon
+._*
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# AI/model files
+*.h5
+*.pb
+*.onnx
+*.tflite
+*.pt
+*.pth
+*.weights
+
+# Temporary files
+tmp/
+temp/
+.tmp
+*.tmp

agent.py

@@ -0,0 +1,99 @@
+import os
+from dotenv import load_dotenv
+from langgraph.graph import START, StateGraph, MessagesState
+from langgraph.prebuilt import tools_condition, ToolNode
+from langchain_core.messages import SystemMessage, HumanMessage
+from langchain.tools.retriever import create_retriever_tool
+from langchain_community.vectorstores import Qdrant
+from qdrant_client import QdrantClient
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_groq import ChatGroq
+from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
+from tools import multiply,add,subtract,divide,modulus,wiki_search,duckduckgo_search,arvix_search
+
+
+load_dotenv()
+
+with open("system_prompt.txt", "r", encoding="utf-8") as f:
+    system_prompt = f.read()
+
+# System message
+sys_msg = SystemMessage(content=system_prompt)
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/static-similarity-mrl-multilingual-v1", model_kwargs={'device': 'cpu'})
+qdrant = QdrantClient(
+    url=os.environ.get("QDRANT_URL"),
+    api_key=os.environ.get("QDRANT_SERVICE_KEY")
+)
+
+vector_store = Qdrant(
+    client=qdrant,
+    embedding_function=embeddings,
+    collection_name="documents",
+    query_name="match_documents_langchain"
+)
+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.",
+)
+tools = [
+    multiply,
+    add,
+    subtract,
+    divide,
+    modulus,
+    wiki_search,
+    duckduckgo_search,
+    arvix_search,
+]
+
+def build_graph(provider: str = "groq"):
+    """Build the graph"""
+    # Load environment variables from .env file
+    model=""
+    if provider == "google":
+        # Google Gemini
+        model = os.environ.get("GEMINI_MODEL")
+        llm = ChatGoogleGenerativeAI(model=model, temperature=0)
+    elif provider == "groq":
+        # Groq https://console.groq.com/docs/models
+        model = os.environ.get("GROQ_MODEL")
+        llm = ChatGroq(model=model, temperature=0)
+    elif provider == "huggingface":
+        model = os.environ.get("HUGGINGFACEHUB_URL")
+        llm = ChatHuggingFace(
+            llm=HuggingFaceEndpoint(
+                url=model,
+                temperature=0,
+            ),
+        )
+    else:
+        raise ValueError("Invalid provider. Choose 'google', 'groq' or 'huggingface'.")
+    # Bind tools to LLM
+    llm_with_tools = llm.bind_tools(tools)
+
+    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)
+        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]}
+
+    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()

app.py

@@ -3,6 +3,8 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+from langchain_core.messages import HumanMessage
+from agent import build_graph
 
 # (Keep Constants as is)
 # --- Constants ---
@@ -13,11 +15,13 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 class BasicAgent:
     def __init__(self):
         print("BasicAgent 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):
     """

example.env

@@ -0,0 +1,8 @@
+QDRANT_URL='my-qdrant-url'
+QDRANT_SERVICE_KEY='my-qdrant-service-key'
+GEMINI_API_KEY='my-gemini-api-key'
+GEMINI_MODEL='gemini-1.5-flash'
+GROQ_API_KEY='my-groq-api-key'
+GROQ_MODEL='groq-llama-3-70b-instruct'
+HUGGINGFACEHUB_API_TOKEN='my-huggingfacehub-api-token'
+HUGGINGFACEHUB_URL='my-huggingfacehub-url'

requirements.txt

@@ -1,2 +1,17 @@
 gradio
-requests
+requests
+langchain
+langchain-community
+langchain-core
+langchain-google-genai
+langchain-huggingface
+langchain-groq
+langgraph
+huggingface_hub
+qdrant-client
+arxiv
+pymupdf
+wikipedia
+python-dotenv
+duckduckgo-search
+sentence-transformers

system_prompt.txt

@@ -0,0 +1,5 @@
+You are a helpful assistant tasked with answering questions using a set of tools. 
+Now, I will ask you a question. Report your thoughts, and finish your answer with the following template: 
+FINAL ANSWER: [YOUR FINAL ANSWER]. 
+YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
+Your answer should only start with "FINAL ANSWER: ", then follows with the answer.

tools.py

@@ -0,0 +1,94 @@
+from langchain_core.tools import tool
+from langchain_community.tools import DuckDuckGoSearchResults
+from langchain_community.document_loaders import WikipediaLoader, ArxivLoader
+
+@tool
+def multiply(a: int, b: int) -> int:
+    """Multiply two numbers.
+    Args:
+        a: first int
+        b: second int
+    """
+    return a * b
+
+@tool
+def add(a: int, b: int) -> int:
+    """Add two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    return a + b
+
+@tool
+def subtract(a: int, b: int) -> int:
+    """Subtract two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    return a - b
+
+@tool
+def divide(a: int, b: int) -> int:
+    """Divide two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    if b == 0:
+        raise ValueError("Cannot divide by zero.")
+    return a / b
+
+@tool
+def modulus(a: int, b: int) -> int:
+    """Get the modulus of two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    return a % b
+
+@tool
+def wiki_search(query: str) -> str:
+    """Search Wikipedia for a query and return maximum 2 results.
+    
+    Args:
+        query: The search query."""
+    search_docs = WikipediaLoader(query=query, load_max_docs=2).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}
+
+@tool
+def arvix_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 {"arvix_results": formatted_search_docs}
+
+@tool
+def duckduckgo_search(query: str) -> str:
+    """Search DuckDuckGo for a query and return maximum 3 results.
+    
+    Args:
+        query: The search query."""
+    search_results = DuckDuckGoSearchResults(max_results=3).invoke(query)
+    formatted_search_results = "\n\n---\n\n".join(
+        [f'<Document source="{result["href"]}"/>\n{result["body"]}\n</Document>' for result in search_results]
+    )
+    return {"duckduckgo_results": formatted_search_results}