Greennode 集成

import getpass
import os

if not os.getenv("GREENNODE_API_KEY"):
    os.environ["GREENNODE_API_KEY"] = getpass.getpass("Enter your GreenNode API key: ")

os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
os.environ["LANGSMITH_TRACING"] = "true"

pip install -qU langchain-greennode

from langchain_greennode import GreenNodeRerank

# Initialize the embeddings model
reranker = GreenNodeRerank(
    # api_key="YOUR_API_KEY",  # You can pass the API key directly
    model="BAAI/bge-reranker-v2-m3",  # The default embedding model
    top_n=3,
)

from langchain_classic.retrievers.contextual_compression import ContextualCompressionRetriever
from langchain_community.vectorstores import FAISS
from langchain_core.documents import Document
from langchain_greennode import GreenNodeEmbeddings

# Initialize the embeddings model
embeddings = GreenNodeEmbeddings(
    # api_key="YOUR_API_KEY",  # You can pass the API key directly
    model="BAAI/bge-m3"  # The default embedding model
)

# Prepare documents (finance/economics domain)
docs = [
    Document(
        page_content="Inflation represents the rate at which the general level of prices for goods and services rises"
    ),
    Document(
        page_content="Central banks use interest rates to control inflation and stabilize the economy"
    ),
    Document(
        page_content="Cryptocurrencies like Bitcoin operate on decentralized blockchain networks"
    ),
    Document(
        page_content="Stock markets are influenced by corporate earnings, investor sentiment, and economic indicators"
    ),
]

# Create a vector store and a base retriever
vector_store = FAISS.from_documents(docs, embeddings)
base_retriever = vector_store.as_retriever(search_kwargs={"k": 4})


rerank_retriever = ContextualCompressionRetriever(
    base_compressor=reranker, base_retriever=base_retriever
)

# Perform retrieval with reranking
query = "How do central banks fight rising prices?"
results = rerank_retriever.get_relevant_documents(query)

results

/var/folders/bs/g52lln652z11zjp98qf9wcy40000gn/T/ipykernel_96362/2544494776.py:41: LangChainDeprecationWarning: The method `BaseRetriever.get_relevant_documents` was deprecated in langchain-core 0.1.46 and will be removed in 1.0. Use :meth:`~invoke` instead.
  results = rerank_retriever.get_relevant_documents(query)

[Document(metadata={'relevance_score': 0.125}, page_content='Central banks use interest rates to control inflation and stabilize the economy'),
 Document(metadata={'relevance_score': 0.004913330078125}, page_content='Inflation represents the rate at which the general level of prices for goods and services rises'),
 Document(metadata={'relevance_score': 1.6689300537109375e-05}, page_content='Cryptocurrencies like Bitcoin operate on decentralized blockchain networks')]

test_documents = [
    Document(
        page_content="Carson City is the capital city of the American state of Nevada."
    ),
    Document(
        page_content="Washington, D.C. (also known as simply Washington or D.C.) is the capital of the United States."
    ),
    Document(
        page_content="Capital punishment has existed in the United States since beforethe United States was a country."
    ),
    Document(
        page_content="The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean. Its capital is Saipan."
    ),
]

test_query = "What is the capital of the United States?"
results = reranker.rerank(test_documents, test_query)
results

[{'index': 1, 'relevance_score': 1.0},
 {'index': 0, 'relevance_score': 0.01165771484375},
 {'index': 3, 'relevance_score': 0.0012054443359375}]

from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_greennode import ChatGreenNode

# Initialize LLM
llm = ChatGreenNode(model="deepseek-ai/DeepSeek-R1-Distill-Qwen-32B")

# Create a prompt template
prompt = ChatPromptTemplate.from_template(
    """
Answer the question based only on the following context:

Context:
{context}

Question: {question}
"""
)


# Format documents function
def format_docs(docs):
    return "\n\n".join(doc.page_content for doc in docs)


# Create RAG chain
rag_chain = (
    {"context": rerank_retriever | format_docs, "question": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)

# Run the chain
answer = rag_chain.invoke("How do central banks fight rising prices?")
answer

'\n\nCentral banks combat rising prices, or inflation, by adjusting interest rates. By raising interest rates, they increase the cost of borrowing, which discourages spending and investment. This reduction in demand helps slow down the rate of price increases, thereby controlling inflation and contributing to economic stability.'