Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -7,12 +7,8 @@ from langchain.vectorstores import FAISS
|
|
7 |
from langchain.chat_models import ChatOpenAI
|
8 |
from langchain.memory import ConversationBufferMemory
|
9 |
from langchain.chains import ConversationalRetrievalChain
|
10 |
-
|
11 |
-
# Add import for HuggingFaceHub
|
12 |
-
from langchain.llms import HuggingFaceHub
|
13 |
-
|
14 |
-
# Import htmlTemplates, assuming it's a local module
|
15 |
from htmlTemplates import css, bot_template, user_template
|
|
|
16 |
|
17 |
def get_pdf_text(pdf_docs):
|
18 |
text = ""
|
@@ -22,6 +18,7 @@ def get_pdf_text(pdf_docs):
|
|
22 |
text += page.extract_text()
|
23 |
return text
|
24 |
|
|
|
25 |
def get_text_chunks(text):
|
26 |
text_splitter = CharacterTextSplitter(
|
27 |
separator="\n",
|
@@ -32,12 +29,14 @@ def get_text_chunks(text):
|
|
32 |
chunks = text_splitter.split_text(text)
|
33 |
return chunks
|
34 |
|
|
|
35 |
def get_vectorstore(text_chunks):
|
36 |
embeddings = OpenAIEmbeddings()
|
37 |
# embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
|
38 |
vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
|
39 |
return vectorstore
|
40 |
|
|
|
41 |
def get_conversation_chain(vectorstore):
|
42 |
llm = ChatOpenAI()
|
43 |
# llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})
|
@@ -51,6 +50,7 @@ def get_conversation_chain(vectorstore):
|
|
51 |
)
|
52 |
return conversation_chain
|
53 |
|
|
|
54 |
def handle_userinput(user_question):
|
55 |
response = st.session_state.conversation({'question': user_question})
|
56 |
st.session_state.chat_history = response['chat_history']
|
@@ -63,6 +63,7 @@ def handle_userinput(user_question):
|
|
63 |
st.write(bot_template.replace(
|
64 |
"{{MSG}}", message.content), unsafe_allow_html=True)
|
65 |
|
|
|
66 |
def main():
|
67 |
load_dotenv()
|
68 |
st.set_page_config(page_title="Chat with multiple PDFs",
|
@@ -98,5 +99,7 @@ def main():
|
|
98 |
st.session_state.conversation = get_conversation_chain(
|
99 |
vectorstore)
|
100 |
|
|
|
101 |
if __name__ == '__main__':
|
102 |
main()
|
|
|
|
7 |
from langchain.chat_models import ChatOpenAI
|
8 |
from langchain.memory import ConversationBufferMemory
|
9 |
from langchain.chains import ConversationalRetrievalChain
|
|
|
|
|
|
|
|
|
|
|
10 |
from htmlTemplates import css, bot_template, user_template
|
11 |
+
from langchain.llms import HuggingFaceHub
|
12 |
|
13 |
def get_pdf_text(pdf_docs):
|
14 |
text = ""
|
|
|
18 |
text += page.extract_text()
|
19 |
return text
|
20 |
|
21 |
+
|
22 |
def get_text_chunks(text):
|
23 |
text_splitter = CharacterTextSplitter(
|
24 |
separator="\n",
|
|
|
29 |
chunks = text_splitter.split_text(text)
|
30 |
return chunks
|
31 |
|
32 |
+
|
33 |
def get_vectorstore(text_chunks):
|
34 |
embeddings = OpenAIEmbeddings()
|
35 |
# embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
|
36 |
vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
|
37 |
return vectorstore
|
38 |
|
39 |
+
|
40 |
def get_conversation_chain(vectorstore):
|
41 |
llm = ChatOpenAI()
|
42 |
# llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})
|
|
|
50 |
)
|
51 |
return conversation_chain
|
52 |
|
53 |
+
|
54 |
def handle_userinput(user_question):
|
55 |
response = st.session_state.conversation({'question': user_question})
|
56 |
st.session_state.chat_history = response['chat_history']
|
|
|
63 |
st.write(bot_template.replace(
|
64 |
"{{MSG}}", message.content), unsafe_allow_html=True)
|
65 |
|
66 |
+
|
67 |
def main():
|
68 |
load_dotenv()
|
69 |
st.set_page_config(page_title="Chat with multiple PDFs",
|
|
|
99 |
st.session_state.conversation = get_conversation_chain(
|
100 |
vectorstore)
|
101 |
|
102 |
+
|
103 |
if __name__ == '__main__':
|
104 |
main()
|
105 |
+
|