Spaces:
Sleeping
Sleeping
File size: 4,688 Bytes
0f6be34 6a3ad81 0f6be34 6a3ad81 0f6be34 de49b6b 0f6be34 de49b6b 0f6be34 de49b6b 0f6be34 de49b6b 0f6be34 de49b6b 0f6be34 de49b6b 0f6be34 |
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 |
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, 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 langchain_community.retrievers import BM25Retriever
from smolagents import DuckDuckGoSearchTool
from smolagents import Tool
from langchain.vectorstores import FAISS
import faiss
from langchain_community.docstore.in_memory import InMemoryDocstore
# Load environment variables
load_dotenv()
class QuestionRetrieverTool(Tool):
name="Question Search",
description="Retrieve similar questions from the vector store."
inputs = {
"query": {
"type": "string",
"description": "The question you want relation about."
}
}
output_type = "string"
def __init__(self, docs):
self.is_initialized = False
self.retriever = BM25Retriever.from_documents(docs)
def forward(self, query: str):
results = self.retriever.get_relevant_documents(query)
if results:
return "\n\n".join([doc.page_content for doc in results[:3]])
else:
return "No matching Questions found."
@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 DDG and return up to 3 results."""
docs = DuckDuckGoSearchTool(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)}
# --- Load system prompt ---
with open("system_prompt.txt", "r", encoding="utf-8") as f:
system_prompt = f.read()
sys_msg = SystemMessage(content=system_prompt)
# --- Retriever Tool ---
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
embedding_dim = 768 # for 'all-mpnet-base-v2'
empty_index = faiss.IndexFlatL2(embedding_dim)
docstore = InMemoryDocstore({})
vector_store = FAISS(embedding_function=embeddings, index=empty_index, docstore=docstore, index_to_docstore_id={})
retriever_tool = create_retriever_tool(
retriever=vector_store.as_retriever(),
name="Question Search",
description="Retrieve similar questions from the vector store."
)
tools = [
wiki_search,
web_search,
retriever_tool,
]
# --- Graph Builder ---
def build_graph():
llm = ChatHuggingFace(
llm=HuggingFaceEndpoint(
repo_id="meta-llama/Llama-2-7b-chat-hf",
temperature=0,
huggingfacehub_api_token=os.getenv("HF_TOKEN")
)
)
# Bind tools to LLM
llm_with_tools = llm.bind_tools(tools)
# Define nodes
def assistant(state: MessagesState):
return {"messages": [llm_with_tools.invoke(state["messages"])]}
# Retriever node returns AIMessage
def retriever(state: MessagesState):
query = state["messages"][-1].content
similar_docs = vector_store.similarity_search(query, k=1)
if similar_docs:
reference = similar_docs[0].page_content
context_msg = HumanMessage(content=f"Here is a similar question and answer for reference:\n\n{reference}")
else:
context_msg = HumanMessage(content="No relevant example found.")
return {
"messages": [sys_msg] + state["messages"] + [context_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()
|