File size: 5,625 Bytes
a3fa7c6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 |
"""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 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 = [
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() |