Add resume loader

app.py

@@ -2,7 +2,7 @@ import streamlit as st
 from langchain import PromptTemplate
 from langchain.llms import Replicate
 import os 
-from langchain.document_loaders import YoutubeLoader
+from langchain.document_loaders import YoutubeLoader, PyPDFLoader
 import requests
 import re
 from langchain.text_splitter import RecursiveCharacterTextSplitter
@@ -68,6 +68,19 @@ def get_query_chain():
   loader = WebBaseLoader(links)
   data = loader.load()
   video_data.extend(data)
+
+  url = 'https://huggingface.co/spaces/ayushtues/personal-assistant/resolve/main/resume.pdf'
+  r = requests.get(url, stream=True)
+
+  with open('resume.pdf', 'wb') as fd:
+      for chunk in r.iter_content(2000):
+          fd.write(chunk)
+
+  loader = PyPDFLoader("resume.pdf")
+  pages = loader.load()
+  video_data.extend(pages)
+
+
   # print(data)
   text_splitter = RecursiveCharacterTextSplitter(chunk_size = 100, chunk_overlap = 0)
   all_splits = text_splitter.split_documents(video_data)

requirements.txt

@@ -8,4 +8,5 @@ sentence_transformers
 youtube-transcript-api
 pytube
 bs4
-lxml
+lxml
+pypdf