File size: 1,752 Bytes
e46888d 5abcbc8 fd99074 e46888d fd99074 e46888d 0f27d55 e46888d 313ed1c e46888d fd99074 5abcbc8 e46888d fd99074 e46888d fd99074 e46888d 0f27d55 e46888d fd99074 |
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 |
# Import Python modules
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_google_genai import GoogleGenerativeAIEmbeddings
from langchain.prompts import PromptTemplate
from langchain_community.vectorstores import Chroma
from langchain.text_splitter import CharacterTextSplitter
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain.chains import create_retrieval_chain
from langchain_community.document_loaders import PyPDFLoader
# Set your API key
GOOGLE_API_KEY = "APIKEY"
# Load the models with the API key
llm = ChatGoogleGenerativeAI(model="gemini-pro", google_api_key=GOOGLE_API_KEY)
embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=GOOGLE_API_KEY)
# Load the PDF and create chunks
loader = PyPDFLoader("handbook.pdf")
text_splitter = CharacterTextSplitter(
separator=".",
chunk_size=500,
chunk_overlap=50,
length_function=len,
is_separator_regex=False,
)
pages = loader.load_and_split(text_splitter)
# Turn the chunks into embeddings and store them in Chroma
vectordb = Chroma.from_documents(pages, embeddings)
# Configure Chroma as a retriever with top_k=10
retriever = vectordb.as_retriever(search_kwargs={"k": 10})
# Create the retrieval chain
template = """You are a helpful AI assistant. Answer based on the context provided.
context: {context}
input: {input}
answer:"""
prompt = PromptTemplate.from_template(template)
combine_docs_chain = create_stuff_documents_chain(llm, prompt)
retrieval_chain = create_retrieval_chain(retriever, combine_docs_chain)
# Invoke the retrieval chain
response = retrieval_chain.invoke({"input": "如何治療牙周病?"})
# Print the answer to the question
print(response["answer"]) |