mirror of
https://github.com/hwchase17/langchain
synced 2024-11-10 01:10:59 +00:00
ebf998acb6
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Lance Martin <lance@langchain.dev> Co-authored-by: Jacob Lee <jacoblee93@gmail.com>
56 lines
1.6 KiB
Python
56 lines
1.6 KiB
Python
from operator import itemgetter
|
|
from langchain.prompts import ChatPromptTemplate
|
|
from langchain.chat_models import ChatOpenAI
|
|
from langchain.embeddings import OpenAIEmbeddings
|
|
from langchain.schema.output_parser import StrOutputParser
|
|
from langchain.schema.runnable import RunnablePassthrough, RunnableParallel
|
|
from langchain.vectorstores import Chroma
|
|
|
|
# Example for document loading (from url), splitting, and creating vectostore
|
|
|
|
'''
|
|
# Load
|
|
from langchain.document_loaders import WebBaseLoader
|
|
loader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")
|
|
data = loader.load()
|
|
|
|
# Split
|
|
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
|
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
|
|
all_splits = text_splitter.split_documents(data)
|
|
|
|
# Add to vectorDB
|
|
vectorstore = Chroma.from_documents(documents=all_splits,
|
|
collection_name="rag-chroma",
|
|
embedding=OpenAIEmbeddings(),
|
|
)
|
|
retriever = vectorstore.as_retriever()
|
|
'''
|
|
|
|
# Embed a single document as a test
|
|
vectorstore = Chroma.from_texts(
|
|
["harrison worked at kensho"],
|
|
collection_name="rag-chroma",
|
|
embedding=OpenAIEmbeddings()
|
|
)
|
|
retriever = vectorstore.as_retriever()
|
|
|
|
# RAG prompt
|
|
template = """Answer the question based only on the following context:
|
|
{context}
|
|
|
|
Question: {question}
|
|
"""
|
|
prompt = ChatPromptTemplate.from_template(template)
|
|
|
|
# LLM
|
|
model = ChatOpenAI()
|
|
|
|
# RAG chain
|
|
chain = (
|
|
RunnableParallel({"context": retriever, "question": RunnablePassthrough()})
|
|
| prompt
|
|
| model
|
|
| StrOutputParser()
|
|
)
|