main.py

from fastapi import FastAPI
from transformers import pipeline
from txtai.embeddings import Embeddings
from txtai.pipeline import Extractor

# NOTE - we configure docs_url to serve the interactive Docs at the root path
# of the app. This way, we can use the docs as a landing page for the app on Spaces.
app = FastAPI(docs_url="/")

# Create embeddings model with content support
embeddings = Embeddings({"path": "sentence-transformers/all-MiniLM-L6-v2", "content": True})
embeddings.load('index')

# Create extractor instance
extractor = Extractor(embeddings, "google/flan-t5-base")

pipe = pipeline("text2text-generation", model="google/flan-t5-xxl")


@app.get("/generate")
def generate(text: str):
    """
    deployed flan-t5-xxl model as backend
    """
    output = pipe(text)
    return {"output": output[0]["generated_text"]}


def prompt(question):
  return f"""Answer the following question using only the context below. Say 'no answer' when the question can't be answered.
            Question: {question}
            Context: """


def search(query, question=None):
  # Default question to query if empty
  if not question:
    question = query

  return extractor([("answer", query, prompt(question), False)])[0][1]


@app.get("/rag")
def rag(question: str):
    # question = "what is the document about?"
    answer = search(question)
    # print(question, answer)
    return {answer}