Spaces:
Sleeping
Sleeping
File size: 5,133 Bytes
db7e060 |
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 |
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_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_community.document_loaders import WikipediaLoader, ArxivLoader
from langchain_community.vectorstores import SupabaseVectorStore
from langchain_core.messages import SystemMessage, AIMessage, HumanMessage
from langchain_core.tools import tool
from langchain.tools.retriever import create_retriever_tool
from supabase.client import Client, create_client
# Load environment variables
load_dotenv()
# --- Math Tools ---
@tool
def multiply(a: int, b: int) -> int:
"""Multiply two integers."""
return a * b
@tool
def add(a: int, b: int) -> int:
"""Add two integers."""
return a + b
@tool
def subtract(a: int, b: int) -> int:
"""Subtract b from a."""
return a - b
@tool
def divide(a: int, b: int) -> float:
"""Divide a by b, error on zero."""
if b == 0:
raise ValueError("Cannot divide by zero.")
return a / b
@tool
def modulus(a: int, b: int) -> int:
"""Compute a mod b."""
return a % b
# --- Browser Tools ---
@tool
def wiki_search(query: str) -> dict:
"""Search Wikipedia and return up to 2 documents."""
docs = WikipediaLoader(query=query, load_max_docs=2).load()
results = [f"<Document source=\"{d.metadata['source']}\" page=\"{d.metadata.get('page','')}\"/>\n{d.page_content}" for d in docs]
return {"wiki_results": "\n---\n".join(results)}
@tool
def web_search(query: str) -> dict:
"""Search Tavily and return up to 3 results."""
docs = TavilySearchResults(max_results=3).invoke(query=query)
results = [f"<Document source=\"{d.metadata['source']}\" page=\"{d.metadata.get('page','')}\"/>\n{d.page_content}" for d in docs]
return {"web_results": "\n---\n".join(results)}
@tool
def arxiv_search(query: str) -> dict:
"""Search Arxiv and return up to 3 docs."""
docs = ArxivLoader(query=query, load_max_docs=3).load()
results = [f"<Document source=\"{d.metadata['source']}\" page=\"{d.metadata.get('page','')}\"/>\n{d.page_content[:1000]}" for d in docs]
return {"arxiv_results": "\n---\n".join(results)}
# --- Load system prompt ---
with open("system_prompt.txt", "r", encoding="utf-8") as f:
system_prompt = f.read()
# --- System message ---
sys_msg = SystemMessage(content=system_prompt)
# --- Retriever Tool ---
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
supabase = create_client(os.getenv("SUPABASE_URL"), os.getenv("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(
search_type="similarity",
search_kwargs={"k": 5}
),
name="Question Search",
description="A tool to retrieve similar questions from the vector store."
)
tools = [
multiply,
add,
subtract,
divide,
modulus,
wiki_search,
web_search,
arxiv_search,
]
# --- Graph Builder ---
def build_graph(provider: str = "huggingface"):
llm = ChatHuggingFace(
llm=HuggingFaceEndpoint(
repo_id = "Qwen/Qwen2.5-Coder-32B-Instruct"
),
)
# Bind tools to LLM
llm_with_tools = llm.bind_tools(tools)
# Define no def assistant(state: MessagesState):
"""Assistant node"""
return {"messages [ [llm_with_tools.invoke(state["messages"])]}se]}
# Retriever returns AIMessage def retriever(state: MessagesState):
"""Retriever node"""
similar_question = vector_store.similarity_search(state["messages"][0].content)
print('Similar questions:')
print(similar_question)
if len(similar_question) > 0:
example_msg = HumanMessage(
content=f"Here I provide a similar question and answer for reference: \n\n{similar_question[0].page_content}",
ntent}]}
return {"messages": [sys_msg] + state["messages"] + [example_msg]}
return {"messages": [sys_msg] + state["m
# Add nodesessages"]}
builder = StateGraph(MessagesState)
builder.add_node("retriever", retriever)
builder.add_node("assistant", assistant)
builder.add_node("tools",
# Add edgesToolNode(tools))
builder.add_edge(START, "retriever")
builder.add_edge("retriever", "assistant")
builder.add_conditional_edges(
"assistant",
tools_condition,
)
builder.add_edge("tools", "assistant")ever")
# Compile graph
return builder.compile()
|