update agent

agent.py

@@ -0,0 +1,213 @@
+"""LangGraph Agent"""
+import os
+from dotenv import load_dotenv
+from langgraph.graph import START, StateGraph, MessagesState
+from langgraph.prebuilt import tools_condition
+from langgraph.prebuilt import ToolNode
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_groq import ChatGroq
+from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
+from langchain_community.tools.tavily_search import TavilySearchResults
+from langchain_community.document_loaders import WikipediaLoader
+from langchain_community.document_loaders import ArxivLoader
+from langchain_community.vectorstores import SupabaseVectorStore
+from langchain_core.messages import SystemMessage, HumanMessage
+from langchain_core.tools import tool
+from langchain.tools.retriever import create_retriever_tool
+# from supabase.client import Client, create_client
+
+load_dotenv()
+
+@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 web_search(query: str) -> str:
+    """Search Tavily for a query and return maximum 3 results.
+    
+    Args:
+        query: The search query."""
+    search_docs = TavilySearchResults(max_results=3).invoke(query=query)
+    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 {"web_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}
+
+
+
+# load the system prompt from the file
+with open("system_prompt.txt", "r", encoding="utf-8") as f:
+    system_prompt = f.read()
+
+# System message
+sys_msg = SystemMessage(content=system_prompt)
+
+# # build a retriever
+# 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_KEY"))
+# vector_store = SupabaseVectorStore(
+#     client=supabase,
+#     embedding= embeddings,
+#     table_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,
+    web_search,
+    arvix_search,
+]
+
+# Build graph function
+def build_graph(provider: str = "groq"):
+    """Build the graph"""
+    # Load environment variables from .env file
+    if provider == "google":
+        # Google Gemini
+        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
+    elif provider == "groq":
+        # Groq https://console.groq.com/docs/models
+        llm = ChatGroq(model="qwen-qwq-32b", temperature=0) # optional : qwen-qwq-32b gemma2-9b-it
+    elif provider == "huggingface":
+        # TODO: Add huggingface endpoint
+        llm = ChatHuggingFace(
+            llm=HuggingFaceEndpoint(
+                url="https://api-inference.huggingface.co/models/Meta-DeepLearning/llama-2-7b-chat-hf",
+                temperature=0,
+            ),
+        )
+    else:
+        raise ValueError("Invalid provider. Choose 'google', 'groq' or 'huggingface'.")
+    # Bind tools to LLM
+    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)
+    #     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")
+
+    # Compile graph
+    return builder.compile()
+
+# test
+if __name__ == "__main__":
+    question = "When was a picture of St. Thomas Aquinas first added to the Wikipedia page on the Principle of double effect?"
+    # Build the graph
+    graph = build_graph(provider="groq")
+    # Run the graph
+    messages = [HumanMessage(content=question)]
+    messages = graph.invoke({"messages": messages})
+    for m in messages["messages"]:
+        m.pretty_print()

requirements.txt

@@ -1,2 +1,189 @@
-gradio
-requests
+aiofiles==24.1.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.12.4
+aiosignal==1.3.2
+annotated-types==0.7.0
+anyio==4.9.0
+appnope==0.1.4
+asgiref==3.8.1
+asttokens==3.0.0
+attrs==25.3.0
+audioop-lts==0.2.1
+backoff==1.11.1
+bcrypt==4.3.0
+build==1.2.2.post1
+cachetools==5.5.2
+certifi==2025.4.26
+charset-normalizer==3.4.2
+chromadb==1.0.11
+click==8.2.1
+coloredlogs==15.0.1
+comm==0.2.2
+dataclasses-json==0.6.7
+debugpy==1.8.14
+decorator==5.2.1
+Deprecated==1.2.18
+distro==1.9.0
+durationpy==0.10
+executing==2.2.0
+fastapi==0.115.9
+ffmpy==0.5.0
+filelock==3.18.0
+filetype==1.2.0
+flatbuffers==25.2.10
+frozenlist==1.6.0
+fsspec==2025.5.1
+google-ai-generativelanguage==0.6.18
+google-api-core==2.24.2
+google-auth==2.40.2
+googleapis-common-protos==1.70.0
+gradio==5.31.0
+gradio_client==1.10.1
+groovy==0.1.2
+groq==0.26.0
+grpcio==1.73.0rc1
+grpcio-status==1.73.0rc1
+h11==0.16.0
+hf-xet==1.1.2
+httpcore==1.0.9
+httptools==0.6.4
+httpx==0.28.1
+httpx-sse==0.4.0
+huggingface-hub==0.32.3
+humanfriendly==10.0
+idna==3.10
+importlib_metadata==8.6.1
+importlib_resources==6.5.2
+ipykernel==6.29.5
+ipython==9.2.0
+ipython_pygments_lexers==1.1.1
+jedi==0.19.2
+Jinja2==3.1.6
+joblib==1.5.1
+jsonpatch==1.33
+jsonpointer==3.0.0
+jsonschema==4.24.0
+jsonschema-specifications==2025.4.1
+jupyter_client==8.6.3
+jupyter_core==5.8.1
+kubernetes==32.0.1
+langchain==0.3.25
+langchain-chroma==0.2.4
+langchain-community==0.3.24
+langchain-core==0.3.63
+langchain-google-genai==2.1.5
+langchain-groq==0.3.2
+langchain-huggingface==0.2.0
+langchain-tavily==0.2.0
+langchain-text-splitters==0.3.8
+langgraph==0.4.7
+langgraph-checkpoint==2.0.26
+langgraph-prebuilt==0.2.2
+langgraph-sdk==0.1.70
+langsmith==0.3.43
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+marshmallow==3.26.1
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+mmh3==5.1.0
+mpmath==1.3.0
+multidict==6.4.4
+mypy==1.16.0
+mypy_extensions==1.1.0
+nest-asyncio==1.6.0
+networkx==3.5
+numpy==2.2.6
+oauthlib==3.2.2
+onnxruntime==1.22.0
+opentelemetry-api==1.33.1
+opentelemetry-exporter-otlp-proto-grpc==1.11.1
+opentelemetry-instrumentation==0.54b1
+opentelemetry-instrumentation-asgi==0.54b1
+opentelemetry-instrumentation-fastapi==0.54b1
+opentelemetry-proto==1.11.1
+opentelemetry-sdk==1.33.1
+opentelemetry-semantic-conventions==0.54b1
+opentelemetry-util-http==0.54b1
+orjson==3.10.18
+ormsgpack==1.10.0
+overrides==7.7.0
+packaging==24.2
+pandas==2.2.3
+parso==0.8.4
+pathspec==0.12.1
+pexpect==4.9.0
+pillow==11.2.1
+platformdirs==4.3.8
+posthog==4.2.0
+prompt_toolkit==3.0.51
+propcache==0.3.1
+proto-plus==1.26.1
+protobuf==6.31.1
+psutil==7.0.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pyasn1==0.6.1
+pyasn1_modules==0.4.2
+pydantic==2.11.5
+pydantic-settings==2.9.1
+pydantic_core==2.33.2
+pydub==0.25.1
+Pygments==2.19.1
+PyPika==0.48.9
+pyproject_hooks==1.2.0
+python-dateutil==2.9.0.post0
+python-dotenv==1.1.0
+python-multipart==0.0.20
+pytz==2025.2
+PyYAML==6.0.2
+pyzmq==26.4.0
+referencing==0.36.2
+regex==2024.11.6
+requests==2.32.3
+requests-oauthlib==2.0.0
+requests-toolbelt==1.0.0
+rich==14.0.0
+rpds-py==0.25.1
+rsa==4.9.1
+ruff==0.11.12
+safehttpx==0.1.6
+safetensors==0.5.3
+scikit-learn==1.6.1
+scipy==1.15.3
+semantic-version==2.10.0
+sentence-transformers==4.1.0
+setuptools==80.9.0
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+SQLAlchemy==2.0.41
+stack-data==0.6.3
+starlette==0.45.3
+sympy==1.14.0
+tenacity==9.1.2
+threadpoolctl==3.6.0
+tokenizers==0.21.1
+tomlkit==0.13.2
+torch==2.7.0
+tornado==6.5.1
+tqdm==4.67.1
+traitlets==5.14.3
+transformers==4.52.4
+typer==0.16.0
+typing-inspect==0.9.0
+typing-inspection==0.4.1
+typing_extensions==4.13.2
+tzdata==2025.2
+urllib3==2.4.0
+uvicorn==0.34.2
+uvloop==0.21.0
+watchfiles==1.0.5
+wcwidth==0.2.13
+websocket-client==1.8.0
+websockets==15.0.1
+wrapt==1.17.2
+xxhash==3.5.0
+yarl==1.20.0
+zipp==3.22.0
+zstandard==0.23.0

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.