langchain/templates/rag-supabase/rag_supabase/chain.py

import os

from langchain_community.chat_models import ChatOpenAI
from langchain_community.embeddings import OpenAIEmbeddings
from langchain_community.vectorstores.supabase import SupabaseVectorStore
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.pydantic_v1 import BaseModel
from langchain_core.runnables import RunnableParallel, RunnablePassthrough
from supabase.client import create_client

supabase_url = os.environ.get("SUPABASE_URL")
supabase_key = os.environ.get("SUPABASE_SERVICE_KEY")
supabase = create_client(supabase_url, supabase_key)

embeddings = OpenAIEmbeddings()

vectorstore = SupabaseVectorStore(
    client=supabase,
    embedding=embeddings,
    table_name="documents",
    query_name="match_documents",
)

retriever = vectorstore.as_retriever()

template = """Answer the question based only on the following context:
{context}

Question: {question}
"""

prompt = ChatPromptTemplate.from_template(template)

model = ChatOpenAI()

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)