mirror of
https://github.com/hwchase17/langchain
synced 2024-11-08 07:10:35 +00:00
60 lines
1.6 KiB
Python
60 lines
1.6 KiB
Python
# Load
|
|
from langchain.chat_models import ChatOllama
|
|
from langchain.document_loaders import WebBaseLoader
|
|
from langchain.embeddings import GPT4AllEmbeddings
|
|
from langchain.prompts import ChatPromptTemplate
|
|
from langchain.pydantic_v1 import BaseModel
|
|
from langchain.schema.output_parser import StrOutputParser
|
|
from langchain.schema.runnable import RunnableParallel, RunnablePassthrough
|
|
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
|
from langchain.vectorstores import Chroma
|
|
|
|
loader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")
|
|
data = loader.load()
|
|
|
|
# Split
|
|
|
|
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-private",
|
|
embedding=GPT4AllEmbeddings(),
|
|
)
|
|
retriever = vectorstore.as_retriever()
|
|
|
|
# Prompt
|
|
# Optionally, pull from the Hub
|
|
# from langchain import hub
|
|
# prompt = hub.pull("rlm/rag-prompt")
|
|
# Or, define your own:
|
|
template = """Answer the question based only on the following context:
|
|
{context}
|
|
|
|
Question: {question}
|
|
"""
|
|
prompt = ChatPromptTemplate.from_template(template)
|
|
|
|
# LLM
|
|
# Select the LLM that you downloaded
|
|
ollama_llm = "llama2:7b-chat"
|
|
model = ChatOllama(model=ollama_llm)
|
|
|
|
# RAG chain
|
|
chain = (
|
|
RunnableParallel({"context": retriever, "question": RunnablePassthrough()})
|
|
| prompt
|
|
| model
|
|
| StrOutputParser()
|
|
)
|
|
|
|
|
|
# Add typing for input
|
|
class Question(BaseModel):
|
|
__root__: str
|
|
|
|
|
|
chain = chain.with_types(input_type=Question)
|