initial commit

.gitignore

@@ -0,0 +1,5 @@
+.vscode/
+*.venv/
+__pycache__/
+.ipynb_checkpoints
+.DS_Store

README.md

@@ -1,12 +1,12 @@
 ---
-title: Summarization Webpage Pipeline
-emoji: 🐨
-colorFrom: gray
+title: Summarize Your Webpage
+emoji: ⚡
+colorFrom: indigo
 colorTo: green
 sdk: streamlit
-sdk_version: 1.25.0
+sdk_version: 1.21.0
 app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,83 @@
+import streamlit as st
+
+from langchain import HuggingFaceHub
+
+from langchain.chains.question_answering import load_qa_chain
+
+from langchain.document_loaders import UnstructuredURLLoader
+
+import os
+
+from transformers import pipeline
+
+with st.sidebar:
+    st.title('🌎 Summarize your webpage')
+    st.markdown('''
+    ## About
+    This app is using:
+    - [Streamlit](https://streamlit.io/)
+    - [LangChain](https://python.langchain.com/)
+    - [Flan Alpaca Large](https://huggingface.co/declare-lab/flan-alpaca-large) LLM model
+
+    ## How it works
+    - Load up a web URL
+    - Send the request to the LLM using the *load_qa_chain* in langchain
+    - Get the answer and from Flan Alpaca Large LLM (open source model on HuggingFace)
+ 
+    ''')
+    st.write('Made with 🤖 by [Cazimir Roman](https://cazimir.dev)')
+
+def load_app():
+    # llm = HuggingFaceHub(repo_id="declare-lab/flan-alpaca-large", model_kwargs={"temperature":0, "max_length":512})
+    summarizer = pipeline('summarization')
+    col1, col2 = st.columns([0.8, 0.2])
+
+    url = col1.text_input('Enter a webpage url here to summarize')
+    col2.write("")
+    col2.write("")
+    summarize = col2.button("Summarize")
+
+    if url:
+        loader = UnstructuredURLLoader(urls=[url])
+        data = loader.load()
+        
+        if summarize:
+            with st.spinner("Summarizing..."):
+                # chain = load_qa_chain(llm=llm, chain_type="stuff")
+                # response = chain.run(input_documents=data, question="Summarize in 200 words")
+
+                response = summarizer(data)
+
+                st.success(response)
+
+def main():
+
+    st.header("Summarize your webpage")
+
+    col1, col2 = st.columns([0.8, 0.2])
+    
+    container = col1.container()
+
+    with container:
+        hugging_face_token = os.getenv("HUGGINGFACEHUB_API_TOKEN")  
+        api_key = container.text_input("Enter your HuggingFace API token", type="password", value="" if hugging_face_token == None else hugging_face_token)
+        st.markdown('''You can find your token [here](https://huggingface.co/settings/tokens)''')
+
+        col2.write("")
+        col2.write("")
+        submit = col2.button("Submit")
+        
+        if hugging_face_token:
+            load_app()
+
+        # submit button is pressed
+        if submit:
+            # check if api key length correct
+                if len(api_key) == 37:
+                    os.environ["HUGGINGFACEHUB_API_TOKEN"] = api_key
+                    load_app()
+                else:
+                    st.error("Api key is not correct")
+
+if __name__ == '__main__':
+    main()

requirements.txt

@@ -0,0 +1,12 @@
+langchain
+PyPDF2
+python-dotenv
+streamlit
+faiss-cpu
+streamlit-extras
+openai
+altair
+tiktoken
+huggingface_hub
+sentence_transformers
+unstructured