Update app.py
Browse files
app.py
CHANGED
@@ -1,12 +1,51 @@
|
|
1 |
import gradio as gr
|
2 |
-
from langchain.text_splitter import
|
3 |
from langchain.llms import HuggingFaceHub
|
4 |
from langchain.embeddings import HuggingFaceEmbeddings
|
5 |
from langchain.vectorstores import Chroma
|
6 |
from langchain.chains import RetrievalQA
|
7 |
from langchain.document_loaders import PyMuPDFLoader
|
8 |
|
9 |
-
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
|
12 |
demo.launch()
|
|
|
1 |
import gradio as gr
|
2 |
+
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
3 |
from langchain.llms import HuggingFaceHub
|
4 |
from langchain.embeddings import HuggingFaceEmbeddings
|
5 |
from langchain.vectorstores import Chroma
|
6 |
from langchain.chains import RetrievalQA
|
7 |
from langchain.document_loaders import PyMuPDFLoader
|
8 |
|
9 |
+
def load_doc(pdf_doc):
|
10 |
+
|
11 |
+
loader = PyMuPDFLoader(pdf_doc.name)
|
12 |
+
documents = loader.load()
|
13 |
+
embedding = HuggingFaceEmbeddings()
|
14 |
+
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
|
15 |
+
text = text_splitter.split_documents(documents)
|
16 |
+
db = Chroma.from_documents(text, embedding)
|
17 |
+
llm = HuggingFaceHub(repo_id="OpenAssistant/oasst-sft-1-pythia-12b", model_kwargs={"temperature": 1.0, "max_length": 256})
|
18 |
+
global chain
|
19 |
+
chain = RetrievalQA.from_chain_type(llm=llm,chain_type="stuff",retriever=db.as_retriever())
|
20 |
+
return 'Document has successfully been loaded'
|
21 |
+
|
22 |
+
def answer_query(query):
|
23 |
+
question = query
|
24 |
+
return chain.run(question)
|
25 |
+
html = """
|
26 |
+
<div style="text-align:center; max width: 700px;">
|
27 |
+
<h1>ChatPDF</h1>
|
28 |
+
<p> Upload a PDF File, then click on Load PDF File <br>
|
29 |
+
Once the document has been loaded you can begin chatting with the PDF =)
|
30 |
+
</div>"""
|
31 |
+
css = """container{max-width:700px; margin-left:auto; margin-right:auto,padding:20px}"""
|
32 |
+
with gr.Blocks(css=css,theme=gr.themes.Monochrome()) as demo:
|
33 |
+
gr.HTML(html)
|
34 |
+
with gr.Column():
|
35 |
+
gr.Markdown('ChatPDF')
|
36 |
+
pdf_doc = gr.File(label="Load a pdf",file_types=['.pdf','.docx'],type='file')
|
37 |
+
with gr.Row():
|
38 |
+
load_pdf = gr.Button('Load pdf file')
|
39 |
+
status = gr.Textbox(label="Status",placeholder='',interactive=False)
|
40 |
+
|
41 |
+
|
42 |
+
with gr.Row():
|
43 |
+
input = gr.Textbox(label="type in your question")
|
44 |
+
output = gr.Textbox(label="output")
|
45 |
+
submit_query = gr.Button("submit")
|
46 |
+
|
47 |
+
load_pdf.click(load_doc,inputs=pdf_doc,outputs=status)
|
48 |
+
|
49 |
+
submit_query.click(answer_query,input,output)
|
50 |
|
51 |
demo.launch()
|