Update app.py and requirements.txt with PdfReader
Browse files- app.py +3 -6
- requirements.txt +1 -1
app.py
CHANGED
@@ -11,6 +11,7 @@ from aimakerspace.openai_utils.embedding import EmbeddingModel
|
|
11 |
from aimakerspace.vectordatabase import VectorDatabase
|
12 |
from aimakerspace.openai_utils.chatmodel import ChatOpenAI
|
13 |
import chainlit as cl
|
|
|
14 |
|
15 |
system_template = """\
|
16 |
Use the following context to answer a users question. If you cannot find the answer in the context, say you don't know the answer."""
|
@@ -64,12 +65,8 @@ def process_text_file(file: AskFileResponse):
|
|
64 |
documents = text_loader.load_documents()
|
65 |
texts = text_splitter.split_texts(documents)
|
66 |
elif file.type == 'application/pdf':
|
67 |
-
|
68 |
-
|
69 |
-
texts = ""
|
70 |
-
for page_num in range(len(doc)):
|
71 |
-
page = doc.load_page(page_num)
|
72 |
-
texts += page.get_text()
|
73 |
else:
|
74 |
raise ValueError("Provide a .txt or .pdf file")
|
75 |
|
|
|
11 |
from aimakerspace.vectordatabase import VectorDatabase
|
12 |
from aimakerspace.openai_utils.chatmodel import ChatOpenAI
|
13 |
import chainlit as cl
|
14 |
+
from PyPDF2 import PdfReader
|
15 |
|
16 |
system_template = """\
|
17 |
Use the following context to answer a users question. If you cannot find the answer in the context, say you don't know the answer."""
|
|
|
65 |
documents = text_loader.load_documents()
|
66 |
texts = text_splitter.split_texts(documents)
|
67 |
elif file.type == 'application/pdf':
|
68 |
+
pdf_reader = PdfReader(temp_file_path)
|
69 |
+
documents = [page.extract_text() for page in pdf_reader.pages]
|
|
|
|
|
|
|
|
|
70 |
else:
|
71 |
raise ValueError("Provide a .txt or .pdf file")
|
72 |
|
requirements.txt
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
numpy
|
2 |
chainlit==0.7.700
|
3 |
openai
|
4 |
-
|
|
|
1 |
numpy
|
2 |
chainlit==0.7.700
|
3 |
openai
|
4 |
+
PdfReader
|