adding files

agent.py

@@ -0,0 +1,134 @@
+"""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()
+
+# ------------------ Arithmetic Tools ------------------
+@tool
+def multiply(a: int, b: int) -> str:
+    return str(a * b)
+
+@tool
+def add(a: int, b: int) -> str:
+    return str(a + b)
+
+@tool
+def subtract(a: int, b: int) -> str:
+    return str(a - b)
+
+@tool
+def divide(a: int, b: int) -> str:
+    if b == 0:
+        return "Error: Cannot divide by zero."
+    return str(a / b)
+
+@tool
+def modulus(a: int, b: int) -> str:
+    return str(a % b)
+
+# ------------------ Retrieval Tools ------------------
+@tool
+def wiki_search(query: str) -> str:
+    docs = WikipediaLoader(query=query, load_max_docs=2).load()
+    return "\n\n---\n\n".join(doc.page_content for doc in docs)
+
+@tool
+def web_search(query: str) -> str:
+    docs = TavilySearchResults(max_results=3).invoke(query)
+    return "\n\n---\n\n".join(doc.page_content for doc in docs)
+
+@tool
+def arvix_search(query: str) -> str:
+    docs = ArxivLoader(query=query, load_max_docs=3).load()
+    return "\n\n---\n\n".join(doc.page_content[:1000] for doc in docs)
+
+# ------------------ System Setup ------------------
+with open("system_prompt.txt", "r", encoding="utf-8") as f:
+    system_prompt = f.read()
+sys_msg = SystemMessage(content=system_prompt)
+
+# Vector Store Retrieval
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
+supabase: Client = create_client(
+    os.environ["SUPABASE_URL"],
+    os.environ["SUPABASE_SERVICE_KEY"]
+)
+vector_store = SupabaseVectorStore(
+    client=supabase,
+    embedding=embeddings,
+    table_name="documents",
+    query_name="match_documents_langchain"
+)
+
+retriever_tool = create_retriever_tool(
+    retriever=vector_store.as_retriever(),
+    name="Question Search",
+    description="Retrieve similar questions from vector DB."
+)
+
+tools = [multiply, add, subtract, divide, modulus, wiki_search, web_search, arvix_search]
+
+# ------------------ Build Agent Graph ------------------
+def build_graph(provider: str = "groq"):
+    if provider == "google":
+        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
+    elif provider == "groq":
+        llm = ChatGroq(model="qwen-qwq-32b", temperature=0)
+    elif provider == "huggingface":
+        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.")
+
+    llm_with_tools = llm.bind_tools(tools)
+
+    def retriever(state: MessagesState):
+        similar = vector_store.similarity_search(state["messages"][0].content)
+        example_msg = HumanMessage(
+            content=f"Here’s a similar QA pair for grounding:\n\n{similar[0].page_content}"
+        )
+        return {"messages": [sys_msg] + state["messages"] + [example_msg]}
+
+    def assistant(state: MessagesState):
+        result = llm_with_tools.invoke(state["messages"])
+        # Extract only the raw string answer
+        final_response = result.content
+        return {"messages": [HumanMessage(content=final_response.strip())]}
+
+    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()
+
+# ------------------ Local Test Harness ------------------
+if __name__ == "__main__":
+    graph = build_graph(provider="groq")
+    question = "When was a picture of St. Thomas Aquinas first added to the Wikipedia page on the Principle of double effect?"
+    messages = [HumanMessage(content=question)]
+    result = graph.invoke({"messages": messages})
+    print(result["messages"][-1].content)

requirements.txt

@@ -1,2 +1,19 @@
 gradio
-requests
+requests
+langchain
+langchain-community
+langchain-core
+langchain-google-genai
+langchain-huggingface
+langchain-groq
+langchain-tavily
+langchain-chroma
+langgraph
+huggingface_hub
+supabase
+arxiv
+pymupdf
+wikipedia
+pgvector
+python-dotenv
+sentence-transformers

system_prompt.txt

@@ -0,0 +1,33 @@
+You are a helpful assistant tasked with answering questions using a set of tools.
+
+You will receive one question at a time. Think step-by-step, use any relevant tools, and reason carefully before providing your final response.
+
+When you're ready to answer, respond using the following exact format:
+
+FINAL ANSWER: [YOUR FINAL ANSWER]
+
+Your answer must follow these strict formatting rules:
+
+If the answer is a number:
+
+Do not include commas.
+
+Do not include units (e.g., %, $, cm) unless the question explicitly asks for them.
+
+If the answer is a string:
+
+Avoid using articles (a, an, the).
+
+Do not abbreviate (e.g., write "New York City", not "NYC").
+
+Write all digits as words unless the question says otherwise.
+
+If the answer is a comma-separated list:
+
+Apply the above rules for each element based on its type (number or string).
+
+Do not use brackets, bullet points, or extra formatting.
+
+Always begin your final response with exactly: FINAL ANSWER:
+
+Do not include anything else after that line—no thoughts, no commentary. Only the formatted answer.