How do I get my code to call/connect to the Anvil site?

Anvil Q&A
1

What I’m trying to do:
the python code below uses the open API to read and query a pdf document found in a google drive and display on a anvil built webpag. when the user inputs a question and clicks submit, the code will read the document.

What I’ve tried and what’s not working:
I believe the code is not properly connected to the anvil site. But I am not sure.

**Code Sample:

!pip install anvil-uplink

anvil.server

anvil.server.connect("server_5YKPABRFZBFLS3ZEVOL4DEOD-QHNRIHAH2NGYOK2A")

!pip install langchain
!pip install openai
!pip install PyPDF2
!pip install faiss-cpu
!pip install tiktoken

from PyPDF2 import PdfReader
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import ElasticVectorSearch, Pinecone, Weaviate, FAISS

import os
os.environ["OPENAI_API_KEY"] = "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"

from google.colab import drive
drive.mount('/content/gdrive', force_remount=True)
root_dir = "/content/gdrive/My Drive/"

reader = PdfReader('/content/gdrive/My Drive/Google Docs/AI—Blessing or Curse.pdf') 

reader

raw_text = ''
for i, page in enumerate(reader.pages):
    text = page.extract_text()
    if text:
        raw_text += text

raw_text[:100]

text_splitter = CharacterTextSplitter(        
    separator = "\n",
    chunk_size = 1000,
    chunk_overlap  = 200,
    length_function = len,
)
texts = text_splitter.split_text(raw_text)

len(texts)

embeddings = OpenAIEmbeddings()

docsearch = FAISS.from_texts(texts, embeddings)

docsearch

from langchain.chains.question_answering import load_qa_chain
from langchain.llms import OpenAI

chain = load_qa_chain(OpenAI(), chain_type="stuff")

@anvil.server.callable

def enter_question(question):
  results = chain.search(docsearch, question)
  return results

@anvil.server.callable

def answer_question(results):
  top_result = results[0]
  answer = top_result['answer']
  confidence = top_result['confidence']
  success = top_result['success']
  return answer, confidence, success

anvil.server.wait_forever()

Clone link:
share a copy of your app

image
image1267×170 10.2 KB

2

First, welcome to the forum!

Second, you are sharing both the Anvil uplink key and the openai api key.

At this point they are exposed, and they will stay exposed forever, even if you edit the post, and anyone can access them both.

You need to reset both the keys and create new ones.

Third, you don’t say what you expect the code to do and what it does instead, so it’s unlikely you will get any helpful answer.

1 Like
3

Thanks for the welcome stefano.menci!

The keys were modified to prior to submitting the code.

I will see how I can be more clear on what I need assistance with.