PDF to text
Browse files
app.py
CHANGED
|
@@ -1,7 +1,14 @@
|
|
| 1 |
import streamlit as st
|
| 2 |
from langchain.embeddings import HuggingFaceEmbeddings
|
| 3 |
from langchain.vectorstores import FAISS
|
|
|
|
| 4 |
|
| 5 |
st.title("Embedding Creation for Langchain")
|
| 6 |
-
st.header("
|
| 7 |
files = st.file_uploader("Upload your files", accept_multiple_files=True, type="pdf")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
import streamlit as st
|
| 2 |
from langchain.embeddings import HuggingFaceEmbeddings
|
| 3 |
from langchain.vectorstores import FAISS
|
| 4 |
+
from pdfminer.high_level import extract_text
|
| 5 |
|
| 6 |
st.title("Embedding Creation for Langchain")
|
| 7 |
+
st.header("File Upload")
|
| 8 |
files = st.file_uploader("Upload your files", accept_multiple_files=True, type="pdf")
|
| 9 |
+
|
| 10 |
+
if files:
|
| 11 |
+
st.header("PDFs to Text")
|
| 12 |
+
for file in files:
|
| 13 |
+
text = extract_text(file)
|
| 14 |
+
st.write(text)
|